Skip to content
Tagged articles

LLM Agents

204 articles · Page 1 of 3
Machine Heart
Machine Heart
Nov 15, 2026 · Artificial Intelligence

SkillMaster: LLM Agents That Autonomously Evolve Their Own Skills via Counterfactual Rewards

Tsinghua University's SkillMaster framework teaches LLM agents to create, update, and retain reusable skills through reinforcement learning, using counterfactual utility rewards and DualAdv-GRPO to jointly optimize task execution and skill management, achieving 98.7% on ALFWorld and 82.0% on WebShop with Qwen2.5-7B.

DualAdv-GRPOLLM AgentsNeurIPS 2026
0 likes · 11 min read
SkillMaster: LLM Agents That Autonomously Evolve Their Own Skills via Counterfactual Rewards
Machine Heart
Machine Heart
Nov 14, 2026 · Artificial Intelligence

How LLM Agents Evolve Through Recursive Self-Improvement: The When, Where, and How Framework

A survey from CAS, Meituan, and partners introduces a unified framework for Recursive Self-Improvement (RSI) in LLM agents, organizing 40 studies around three core questions — when to update, where to modify, and how to validate — and a seven-step lifecycle that turns raw experience into verified, reusable components across Prompt, Memory, Skill, and Harness layers.

Agent LifecycleExperience-Driven LearningHarness Evolution
0 likes · 17 min read
How LLM Agents Evolve Through Recursive Self-Improvement: The When, Where, and How Framework
Machine Heart
Machine Heart
Nov 12, 2026 · Artificial Intelligence

CoACT: 33% Token Reduction for Coding Agents via Action-Preserving Compression

Tsinghua researchers propose CoACT, an observation compression method for coding agents that preserves the agent's next action, cutting token consumption by 33% on SWE-bench Verified while maintaining pass rates, using a two-stage training approach and a Next-Action Preservation criterion.

AI for Software EngineeringICSE 2027LLM Agents
0 likes · 11 min read
CoACT: 33% Token Reduction for Coding Agents via Action-Preserving Compression
Bighead's Algorithm Notes
Bighead's Algorithm Notes
Nov 10, 2026 · Artificial Intelligence

AQuA: Dual Isolated AI Systems Enable Leak-Proof Recursive Self-Improvement in Quant Research

The AQuA framework deploys two independent LLM-driven research systems—one for symbolic factor discovery, another for trainable model development—each confined in sealed sandboxes that freeze data splits, features, labels, and evaluators, achieving 0.190 combined IC in crypto factors and 0.0843 per-stock IC with 2.50 Sharpe in US equities through recursive self-improvement.

AQuALLM Agentsdata leakage prevention
0 likes · 27 min read
AQuA: Dual Isolated AI Systems Enable Leak-Proof Recursive Self-Improvement in Quant Research
Linyb Geek Road
Linyb Geek Road
Nov 9, 2026 · Artificial Intelligence

From Labels to TaskSpecs: How Production Agents Structure Intent Recognition

This article dissects production-grade agent intent recognition, explaining how to move beyond simple classification by defining structured TaskSpecs, resolving multi-turn context, implementing hierarchical routing, calibrating confidence with risk-aware thresholds, and evaluating with metrics that prioritize correct routing over raw accuracy.

Agent Intent RecognitionHierarchical RoutingLLM Agents
0 likes · 20 min read
From Labels to TaskSpecs: How Production Agents Structure Intent Recognition
Cambridge Mofang Notes
Cambridge Mofang Notes
Nov 8, 2026 · Artificial Intelligence

Multi-Agent Architecture Patterns: From Orchestrator to Blackboard

This article analyzes why single-agent systems fail due to context overload and presents five multi-agent architecture patterns—Orchestrator-Workers, Sequential Pipeline, Hierarchical, Network/Handoff, and Blackboard—with their trade-offs, message-passing methods, and a practical selection guide for different business scenarios.

AI agentsAgent ArchitectureLLM Agents
0 likes · 14 min read
Multi-Agent Architecture Patterns: From Orchestrator to Blackboard
Architect
Architect
Nov 7, 2026 · Artificial Intelligence

Anthropic's 'Dreaming' Corrects Agent Memory Errors: A Case Study

Anthropic's research shows how a wrong memory note caused Claude to misinterpret its location in Pokémon Red, and how their 'Dreaming' background process uses raw session logs to detect and correct such errors by preserving evidence trails, applicability conditions, and verification methods.

Agent MemoryAnthropicDreaming
0 likes · 18 min read
Anthropic's 'Dreaming' Corrects Agent Memory Errors: A Case Study
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Nov 6, 2026 · Artificial Intelligence

AI Tool Analyzes 60 Award Papers to Generate Full Conference Drafts from Abstracts

Best-Paper-Writing-Skill analyzes 60 CVPR/ICCV/NeurIPS award-winning papers to extract 475 writing patterns and 8 argumentation routes, enabling AI agents to generate complete 6-page conference drafts from a single abstract while marking missing data as TODO placeholders.

AI-assisted writingCVPRLLM Agents
0 likes · 7 min read
AI Tool Analyzes 60 Award Papers to Generate Full Conference Drafts from Abstracts
Tech Freedom Circle
Tech Freedom Circle
Nov 5, 2026 · Artificial Intelligence

Agent Self-Evolution: Harness Principles from Google, Fudan & EverMind

This article details the principles of Agent Harness self-evolution, covering multi-agent architecture, four-layer observability, recursive self-verification, and compares three technical approaches—Google's Harness², Fudan's AHE, and EverMind's HarnessBank—with engineering implementation steps for building self-improving AI agent systems.

AI EngineeringHarnessLLM Agents
0 likes · 26 min read
Agent Self-Evolution: Harness Principles from Google, Fudan & EverMind
SmartApe AI
SmartApe AI
Nov 4, 2026 · Artificial Intelligence

SkillHone: Tencent WeChat's Continuous Skill Evolution Framework for LLM Agents

Tencent WeChat introduces SkillHone, a framework that persists decision history — failure evidence, candidate fixes, test results, and accept/reject reasons — enabling LLM agents to cumulatively improve skills from real-world failures, with benchmarks showing 13–18% accuracy gains over baselines.

Decision HistoryEMNLP 2026Evaluation-Driven Development
0 likes · 6 min read
SkillHone: Tencent WeChat's Continuous Skill Evolution Framework for LLM Agents
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Nov 4, 2026 · Artificial Intelligence

Cortex: Turning Agent Experience into Long-Term Parametric Memory

Researchers from Zhejiang University, ByteDance Seed, and Tsinghua University propose Cortex, a method that consolidates contextual experience into model parameters via prospective rehearsal and context distillation, enabling agents to retain skills and knowledge without external retrieval, validated across tool use, fact updating, and agent tasks with minimal parameter growth.

Continual LearningKnowledge EditingLLM Agents
0 likes · 39 min read
Cortex: Turning Agent Experience into Long-Term Parametric Memory
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Nov 2, 2026 · Artificial Intelligence

VAST V・STAR: 3D Generation & World Models as the Next AI Research Frontier

VAST launches its V・STAR talent program targeting 3D generation, 3D understanding with agents, and world models, showcasing how its Tripo and Eden projects enable LLM-driven 3D creation and persistent interactive worlds while offering researchers freedom to define problems and own outcomes.

3D generationAI researchEden
0 likes · 25 min read
VAST V・STAR: 3D Generation & World Models as the Next AI Research Frontier
DataFunSummit
DataFunSummit
Nov 2, 2026 · Artificial Intelligence

AWS Strands Harness: Same Model, 77% Lower Cost – Why the Agent Runtime Now Matters More Than the Model

AWS open-sourced Strands Harness, a pre-assembled agent runtime that cuts Terminal-Bench 2.1 costs from $248 to $56 (77% less) while raising accuracy from 61.8 to 69.7 using the same Claude Fable 5 model, proving that context management, prompt caching, layered memory, and skill loading – not just the model – drive agent performance.

AWSAgent RuntimeContext Management
0 likes · 17 min read
AWS Strands Harness: Same Model, 77% Lower Cost – Why the Agent Runtime Now Matters More Than the Model
Data Party THU
Data Party THU
Oct 30, 2026 · Artificial Intelligence

LLM Agents Spontaneously Polarize: Tsinghua Study Reveals Emergent Echo Chambers in Multi-Agent Networks

Tsinghua researchers show that networked LLM agents across five models spontaneously form polarized opinion clusters with homophilic clustering, echo chambers, and backfire effects, and demonstrate that individual-level cognitive interventions reduce polarization more effectively than network rewiring in stable systems.

LLM AgentsNature CommunicationsTsinghua University
0 likes · 9 min read
LLM Agents Spontaneously Polarize: Tsinghua Study Reveals Emergent Echo Chambers in Multi-Agent Networks
PaperAgent
PaperAgent
Oct 27, 2026 · Artificial Intelligence

MemAdapter: Post-Retrieval Calibration Stops Memory-Induced Sycophancy in LLM Agents

MemAdapter introduces a post-retrieval calibration framework that prevents memory-induced sycophancy in LLM agents by dynamically adapting memory usage to task context through counterfactual induction, context-aware reflection, and evidence-driven reasoning, improving accuracy across multiple benchmarks and memory systems without modifying upstream memory stores.

Agent MemoryContext-Aware ReflectionCounterfactual Induction
0 likes · 7 min read
MemAdapter: Post-Retrieval Calibration Stops Memory-Induced Sycophancy in LLM Agents
PaperAgent
PaperAgent
Oct 22, 2026 · Artificial Intelligence

EviRepair: Multi-Agent Evidence Review Boosts Automated Vulnerability Repair

EviRepair introduces a two-phase multi-agent system for automated vulnerability repair that first diagnoses vulnerabilities through parallel evidence-gathering agents and a reviewer, then synthesizes patches validated against the verified vulnerability model, achieving higher fix rates on PatchEval and SEC-bench benchmarks.

EviRepairLLM AgentsPatchEval
0 likes · 7 min read
EviRepair: Multi-Agent Evidence Review Boosts Automated Vulnerability Repair
Machine Heart
Machine Heart
Oct 22, 2026 · Information Security

AI Agents as Trojan Horses: Resource Hijacking Attacks Achieve 89% Success on Top Models

Shanghai Jiao Tong University researchers reveal 'Agent Resource Hijacking' attacks where attackers trick AI agents into consuming enterprise GPU compute and API quotas without stealing credentials, achieving 70-89% success rates across top models like GPT-5.5 and DeepSeek-V4-Pro, while proposed ResGate defense reduces success to 23.6% with minimal usability impact.

AI safetyAI securityLLM Agents
0 likes · 16 min read
AI Agents as Trojan Horses: Resource Hijacking Attacks Achieve 89% Success on Top Models
SmartApe AI
SmartApe AI
Oct 22, 2026 · Artificial Intelligence

HarnessPro: Self-Improving Agents Cut Execution Costs 26% While Raising Pass Rates

Researchers from Tsinghua, Zhipu AI, and others introduce HarnessPro, a framework where agents recursively analyze their own execution traces, identify failures and inefficiencies, and automatically rewrite their operating procedures, achieving a 2.0% pass-rate increase and 26.1% cost reduction across three benchmarks using GPT-5.5 and Codex.

AI agentsCodexGPT-5.5
0 likes · 7 min read
HarnessPro: Self-Improving Agents Cut Execution Costs 26% While Raising Pass Rates
Xiaohongshu Tech REDtech
Xiaohongshu Tech REDtech
Oct 16, 2026 · Artificial Intelligence

Skill2Env: Auto-Generating Evolving Agent Training Tasks from Skills

Xiaohongshu's AllSpark team introduces Skill2Env, a framework that automatically synthesizes executable agent training environments from existing skills by mapping capability requirements to reusable difficulty patterns, iteratively strengthening tasks based on execution feedback, and generating 1.5K high-quality trajectories that improve a Qwen model across seven agent benchmarks.

DoclingLLM AgentsSkill2Env
0 likes · 15 min read
Skill2Env: Auto-Generating Evolving Agent Training Tasks from Skills
Machine Heart
Machine Heart
Oct 16, 2026 · Artificial Intelligence

FlowMAS: AI Teams Learn to Self-Organize via GFlowNets

FlowMAS, a NeurIPS 2026 paper, uses Generative Flow Networks with curiosity-driven and information-theoretic rewards to automatically generate diverse, efficient multi-agent workflow topologies, outperforming baselines across six benchmarks with far lower computational cost.

Automated Architecture DesignCuriosity-Driven ExplorationGFlowNets
0 likes · 11 min read
FlowMAS: AI Teams Learn to Self-Organize via GFlowNets
IT Services Circle
IT Services Circle
Oct 14, 2026 · Artificial Intelligence

Claude Code Wipes C Drive: Why Skipping Permissions Led to Disaster

Developer Zac lost his entire C drive after running Claude Code Opus 5.5 with --dangerously-skip-permissions, but daily NAS backups restored 98% of data; the incident sparked debate over Anthropic's Auto Mode safety classifier, which blocks 89% of dangerous commands, yet a Linux user still lost files even with Auto Mode enabled.

AI safetyAnthropicAuto Mode
0 likes · 9 min read
Claude Code Wipes C Drive: Why Skipping Permissions Led to Disaster
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Oct 13, 2026 · Artificial Intelligence

LightRSI TokenPilot: Slash LLM Agent Context Costs Up to 87% with Smart Cleanup

Zhejiang University's LightRSI project introduces TokenPilot, an EMNLP 2026 accepted system for cache-efficient context management in LLM agents, combining prefix cache stabilization, tool output summarization, and task-level context cleaning to reduce inference costs by up to 87% on Claw-Eval while integrating with six coding agents and providing a visualization dashboard.

Context ManagementEMNLP 2026LLM Agents
0 likes · 13 min read
LightRSI TokenPilot: Slash LLM Agent Context Costs Up to 87% with Smart Cleanup
Qunar Tech Salon
Qunar Tech Salon
Oct 12, 2026 · Artificial Intelligence

LLM-Powered Database Root Cause Analysis: From Manual Triage to Automated AI Diagnosis

Qunar's production AI database operations agent automates root cause analysis through a six-layer LangGraph architecture, five-layer correlation algorithms from Pearson to Granger causality, and human-in-the-loop design, cutting DBA investigation time from minutes to 1-2 minutes with 70% diagnostic accuracy.

AI for DevOpsGranger CausalityLLM Agents
0 likes · 53 min read
LLM-Powered Database Root Cause Analysis: From Manual Triage to Automated AI Diagnosis
SmartApe AI
SmartApe AI
Oct 11, 2026 · Artificial Intelligence

AEWM: World Model That Judges & Corrects Agent Decisions Pre-Execution

Researchers from Renmin University's Gaoling School of AI introduce Agent-Editing World Model (AEWM), which shifts world modeling from predicting environment feedback to judging decision impact and revising erroneous actions before execution, improving agent performance across benchmarks and enabling self-improvement via distilled trajectories.

AEWMAgent Self-ImprovementEditAct
0 likes · 16 min read
AEWM: World Model That Judges & Corrects Agent Decisions Pre-Execution
DataFunSummit
DataFunSummit
Oct 7, 2026 · Artificial Intelligence

EvoOntology: Self-Evolving Ontology Layer Lets Data Agents Maintain Their Own Semantic Knowledge

EvoOntology introduces a self-evolving ontology layer for data agents that transforms static semantic layers into a runtime service, using a three-layer architecture and an evolution loop where agents' execution traces drive continuous ontology updates via builder and evolution agents with validation gates, reducing token usage and improving accuracy across benchmarks.

Data AgentsEvoOntologyLLM Agents
0 likes · 18 min read
EvoOntology: Self-Evolving Ontology Layer Lets Data Agents Maintain Their Own Semantic Knowledge
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Oct 7, 2026 · Artificial Intelligence

Dream-RSI: Google DeepMind's Recursive Self-Improvement via Evolving Worlds Cuts Compute by Orders of Magnitude

Google DeepMind's Dream-RSI introduces a recursive self-improvement framework that treats historical exploration data as an offline simulator to evolve search strategies, reducing compute costs by 1-2 orders of magnitude across algorithm engineering, mathematical optimization, and GPU kernel generation tasks.

AI agentsDream-RSIGPU Kernels
0 likes · 17 min read
Dream-RSI: Google DeepMind's Recursive Self-Improvement via Evolving Worlds Cuts Compute by Orders of Magnitude
Machine Heart
Machine Heart
Oct 4, 2026 · Artificial Intelligence

SocioVerse2: Longitudinal Social Simulation with Counterfactual Branching

SocioVerse2 introduces a social simulation infrastructure that decouples population, environment, and behavior models, enabling longitudinal simulations where researchers can insert interventions at any step to create counterfactual branches, and versioned research loops for iterative design, validated across seven case studies including segregation dynamics, drug procurement, and macroeconomic forecasting.

LLM AgentsSocioVerse2agent-based modeling
0 likes · 15 min read
SocioVerse2: Longitudinal Social Simulation with Counterfactual Branching
dbaplus Community
dbaplus Community
Sep 28, 2026 · Artificial Intelligence

Building the Agent Self-Evolution Flywheel: Evaluation → Memory → Implementation → Control

This article presents a comprehensive four-stage flywheel methodology for agent self-evolution—evaluation, memory, implementation, and human-in-the-loop control—detailing core challenges, engineering practices, and integration patterns to create a continuous improvement loop for AI agents.

AI EngineeringEvaluation SystemsFlywheel Architecture
0 likes · 53 min read
Building the Agent Self-Evolution Flywheel: Evaluation → Memory → Implementation → Control
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Sep 28, 2026 · Artificial Intelligence

Why Plan Mode in AI Coding Tools Is Already Dying

Ayman Nadeem, founder of YC-backed AI coding startup Nuanced, explains why the once-essential Plan Mode — where developers write detailed specs before code generation — is becoming obsolete as models grow capable of autonomous reasoning, iterative action, and self-correction without heavy upfront planning documents.

AI coding assistantsAI-generated documentationClaude Code
0 likes · 14 min read
Why Plan Mode in AI Coding Tools Is Already Dying
Architect
Architect
Sep 28, 2026 · Artificial Intelligence

Dream-RSI: How Agents 'Dream' on Past Searches to Optimize Exploration Budgets

Dream-RSI introduces a recursive self-improvement framework where AI agents improve exploration strategies by replaying historical search trees offline, enabling budget allocation decisions without retraining models, demonstrated across algorithm engineering, math optimization, and GPU kernel tasks with reduced search costs.

AI researchDream-RSIGoogle DeepMind
0 likes · 26 min read
Dream-RSI: How Agents 'Dream' on Past Searches to Optimize Exploration Budgets
AI Large Model Application Practice
AI Large Model Application Practice
Sep 28, 2026 · Artificial Intelligence

JEV in Agent Systems: 8 High-Speed Decision Patterns for LLM Agents

This article details eight practical scenarios where JEV (Judgment and Evaluation) models accelerate agent decision-making, including ReAct loop control, web automation, tool routing, safety guards, task evaluation, model routing, RAG filtering, and real-time robotics control, showing how lightweight classifiers reduce latency and token costs.

Decision ModelsJevLLM Agents
0 likes · 20 min read
JEV in Agent Systems: 8 High-Speed Decision Patterns for LLM Agents
DataFunTalk
DataFunTalk
Sep 25, 2026 · Artificial Intelligence

MemoHarness: Agent Evolution Shifts from Model Weights to External Harness

MemoHarness introduces a six-dimensional external harness system that adapts agent behavior through case-based experience from execution trajectories, showing improvements on terminal, coding, and finance tasks while acknowledging limited experimental scale and selective cross-task transferability.

Agent HarnessFinanceAgentHarness Engineering
0 likes · 16 min read
MemoHarness: Agent Evolution Shifts from Model Weights to External Harness
DataFunSummit
DataFunSummit
Sep 23, 2026 · Artificial Intelligence

MemoHarness: Agent Evolution Shifts from Model Weights to External Harness Systems

MemoHarness introduces a six-dimensional harness framework where agents learn from execution trajectories during development, then adapt to new tasks via case-based retrieval—showing gains on terminal, coding, and finance tasks while acknowledging limited scale, selective transfer, and no online learning.

Agent HarnessFinanceAgentHarness Engineering
0 likes · 18 min read
MemoHarness: Agent Evolution Shifts from Model Weights to External Harness Systems
Amap Tech
Amap Tech
Sep 22, 2026 · Artificial Intelligence

DIANOIA: Multi-Agent Diagnosis & Repair for Navigation Tool Trajectories

Amap introduces DIANOIA, a multi-agent system that diagnoses and repairs low-confidence tool-call trajectories for navigation Live mode by generating diverse candidates, executing them in real tool environments, cross-reviewing failures, and synthesizing corrected sequences, boosting data quality for LLM training while reducing compute costs.

DIANOIAEMNLP 2026LLM Agents
0 likes · 28 min read
DIANOIA: Multi-Agent Diagnosis & Repair for Navigation Tool Trajectories
Data Party THU
Data Party THU
Sep 22, 2026 · Artificial Intelligence

Why Your Multi-Agent System Is Costlier, Slower, and Worse Than a Single Agent

The article analyzes why multi-agent systems often underperform single agents, identifying context isolation as the key benefit only when tasks exceed a single context window, detailing six architectural patterns, cost multipliers up to 15x tokens, and a decision framework for choosing between multi-agent and single-agent approaches with proper engineering practices.

AI EngineeringAgent OrchestrationCost Optimization
0 likes · 19 min read
Why Your Multi-Agent System Is Costlier, Slower, and Worse Than a Single Agent
Machine Heart
Machine Heart
Sep 17, 2026 · Artificial Intelligence

Beyond Prompts: Harness-Policy Co-Evolution for Agent Safety by Shanghai AI Lab

Shanghai AI Lab and university collaborators propose SHE and SafeEvolve, two frameworks that evolve agent safety by learning from execution trajectories: SHE updates a modular safety harness via trajectory-driven evolution, while SafeEvolve distills verified harness experience into the policy model through SFT and RL, reducing attack success rates on benchmarks.

Agent SafetyHarness EvolutionLLM Agents
0 likes · 12 min read
Beyond Prompts: Harness-Policy Co-Evolution for Agent Safety by Shanghai AI Lab
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Sep 16, 2026 · Artificial Intelligence

NetCanvas: Huawei GTS Gives AI Agents an Interactive Visual Topology for Network Troubleshooting

Huawei GTS's NetCanvas provides LLM agents with an interactive visual topology as external working memory, enabling them to 'watch' network topology during troubleshooting; on CTBench, pass rates jump from 30.3% to 54.5% (63.6% with priors), dual-firewall/ECMP tasks soar from ~10% to ~90%, with zero regressions and 26–45% token cost reduction.

CTBenchHuawei GTSLLM Agents
0 likes · 11 min read
NetCanvas: Huawei GTS Gives AI Agents an Interactive Visual Topology for Network Troubleshooting
Machine Heart
Machine Heart
Sep 14, 2026 · Artificial Intelligence

T-Mem: Teaching AI Associative Recall Beyond Similarity Search

Tencent's T-Mem introduces associative recall for LLM agents by pre-storing trigger cues during memory writing, enabling retrieval via semantic associations rather than surface similarity, achieving SOTA on LoCoMo and LoCoMo-Plus benchmarks with minimal performance drop on associative tasks.

EMNLP 2026LLM AgentsLOCOMO benchmark
0 likes · 13 min read
T-Mem: Teaching AI Associative Recall Beyond Similarity Search
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Sep 12, 2026 · Artificial Intelligence

SafeEvolve: Co-Evolving Harness and Policy for Self-Improving Agent Safety

SafeEvolve introduces a co-evolution framework where Agent Harness and Policy jointly learn from execution trajectories, reducing attack success rates to 0.79% on AgentDojo and 2.42% on Qwen3-4B while improving task utility, enabling continuous safety improvement from real-world experience.

AI safetyAgent SafetyHarness-Policy Co-Evolution
0 likes · 9 min read
SafeEvolve: Co-Evolving Harness and Policy for Self-Improving Agent Safety
DataFunSummit
DataFunSummit
Sep 11, 2026 · Artificial Intelligence

Graph Engineering Restructures Agent Systems: From Harness to Ontology

This article reviews a 2026 paper on Graph Engineering for LLM agents, detailing the shift from individual agent intelligence to system intelligence via explicit task DAGs, runtime state management with checkpoints and replay, multi-agent coordination through capability modeling, and ontology engineering for shared semantics.

Agent CoordinationDAG SchedulingGraph Engineering
0 likes · 20 min read
Graph Engineering Restructures Agent Systems: From Harness to Ontology
PaperAgent
PaperAgent
Sep 11, 2026 · Artificial Intelligence

Google's Procedural Graphs: Self-Evolving Execution Structures for LLM Agents

Google introduces Procedural Graphs, a self-evolving graph structure that explicitly encodes procedural knowledge for LLM agents, enabling them to locate, extract, and generate contextual guidance from a (procedure, relation, procedure) triplet graph, achieving 85% survival from 0% in CFO simulation and winning 21 of 24 model-benchmark combinations across 7 benchmarks and 4 LLMs.

Agent ReliabilityGraph-based ReasoningLLM Agents
0 likes · 9 min read
Google's Procedural Graphs: Self-Evolving Execution Structures for LLM Agents
DataFunTalk
DataFunTalk
Sep 9, 2026 · Artificial Intelligence

Graph Engineering Restructures Agent Systems: From Harness to Ontology

A 2026 survey paper introduces Graph Engineering as the next phase for LLM agents, shifting focus from individual model capabilities to system-level organization via explicit task DAGs, runtime state management with provenance and recovery, capability-based agent coordination, and a graph-native control plane that treats tasks, agents, and state as first-class system objects.

Agent CoordinationDAG SchedulingGraph Engineering
0 likes · 22 min read
Graph Engineering Restructures Agent Systems: From Harness to Ontology
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Sep 8, 2026 · Artificial Intelligence

Strong Model ≠ Strong Agent: PolyWorkBench Benchmarks Cross-Lingual Long-Horizon Workflows

PolyWorkBench introduces 67 cross-lingual long-horizon workflow tasks across 5 domains and 10 languages, revealing that top models like Claude Opus 4.8 show 22.5% performance variance across agent harnesses and significant drops on commerce tasks and low-resource languages due to language understanding and cross-lingual coordination errors.

Agent BenchmarksAgent HarnessClaude Opus
0 likes · 10 min read
Strong Model ≠ Strong Agent: PolyWorkBench Benchmarks Cross-Lingual Long-Horizon Workflows
Architecture Development Notes
Architecture Development Notes
Sep 8, 2026 · Artificial Intelligence

OpenTelemetry GenAI Semantic Conventions: Modeling Agent Runs as Span Trees

The article explains how OpenTelemetry GenAI semantic conventions address the gap in agent observability by defining a standardized span tree structure (invoke_agent, execute_tool, chat, etc.) and three critical fields (gen_ai.agent.name, gen_ai.conversation.id, gen_ai.operation.name) to capture tool calls, retries, and child-agent handoffs that auto-instrumentation misses.

GenAILLM AgentsOpenTelemetry
0 likes · 10 min read
OpenTelemetry GenAI Semantic Conventions: Modeling Agent Runs as Span Trees
Machine Heart
Machine Heart
Sep 8, 2026 · Artificial Intelligence

Behavior Consistency Beats State Consistency in Text World Models for Agents

The paper introduces BehR, a behavior consistency reward for training text-based world models, showing that optimizing for agent decision alignment rather than text fidelity improves trajectory-level consistency across 16 configurations, reduces false positives in offline evaluation from 42.5% to 9.5%, and enhances lookahead planning for weaker agents.

Behavior ConsistencyEMNLP 2026GRPO
0 likes · 11 min read
Behavior Consistency Beats State Consistency in Text World Models for Agents
AI Large-Model Wave and Transformation Guide
AI Large-Model Wave and Transformation Guide
Sep 8, 2026 · Artificial Intelligence

AI Agent Development: The Dual Challenge of Thinking Engineering & Distributed Systems

This article argues that AI agent development shifts from traditional coding to dual-system engineering: single agents require thinking logic design (prompt engineering, reasoning frameworks), while multi-agent systems demand distributed architecture skills (task graphs, state management, concurrency control), combining probabilistic reasoning with system reliability challenges.

AI agentsLLM AgentsLangGraph
0 likes · 14 min read
AI Agent Development: The Dual Challenge of Thinking Engineering & Distributed Systems
DataFunTalk
DataFunTalk
Sep 7, 2026 · Artificial Intelligence

Graph Engineering Rebuilds Agent Systems: From Harness to System Intelligence

A 2026 survey paper introduces Graph Engineering as the system layer that organizes LLM agents into reliable multi-agent workflows through explicit DAGs, runtime state management, fault tolerance, and a control plane, shifting focus from individual agent capabilities to system-level engineering.

Agent CoordinationDAG SchedulingGraph Engineering
0 likes · 21 min read
Graph Engineering Rebuilds Agent Systems: From Harness to System Intelligence
DataFunTalk
DataFunTalk
Sep 4, 2026 · Artificial Intelligence

MemoHarness: Agent Evolution Moves Outside the Model to External Harness Systems

This article analyzes MemoHarness, a framework that evolves AI agents by optimizing six external harness dimensions—context assembly, tool interaction, generation control, task orchestration, memory management, and output processing—instead of model weights, demonstrating gains on terminal, coding, and finance tasks while noting limited experimental scale and selective cross-task transfer.

Agent HarnessAgent MemoryExternal System Evolution
0 likes · 22 min read
MemoHarness: Agent Evolution Moves Outside the Model to External Harness Systems
Bighead's Algorithm Notes
Bighead's Algorithm Notes
Sep 1, 2026 · Artificial Intelligence

XAlpha: AI Quant Researcher with Memory & Reflection for Alpha Discovery

XAlpha introduces a memory-driven AI quantitative researcher that automates the full hypothesis-to-code alpha discovery loop via a multi-brain architecture, integrating report knowledge, hypothesis planning, factor evolution, empirical validation, and feedback integration, achieving superior performance on CSI300.

AI quantitative researcherCSI300LLM Agents
0 likes · 35 min read
XAlpha: AI Quant Researcher with Memory & Reflection for Alpha Discovery
AI Engineering
AI Engineering
Sep 1, 2026 · Artificial Intelligence

Why Long-Term LLM Agents Fail: The Same Design Choice Behind Two Deaths

Long‑term LLM agents suffer from ever‑slowing execution and context poisoning because they continuously append every observation, action, and reasoning step to the prompt, but the SKILL.state approach replaces this growing history with a compact mutable state, dramatically cutting token usage while boosting accuracy and robustness across diverse benchmarks.

GeminiGemmaLLM Agents
0 likes · 11 min read
Why Long-Term LLM Agents Fail: The Same Design Choice Behind Two Deaths
Machine Heart
Machine Heart
Aug 29, 2026 · Artificial Intelligence

Recuris: A New Memory Paradigm That Boosts Performance from 3B Models to Claude Opus 5

Recuris introduces a compact task‑state‑driven memory architecture and gated recursive self‑improvement, enabling agents to use and evolve memory more reliably and delivering large, consistent gains from 3B open‑source models up to frontier models such as Claude Opus 5 across multiple long‑horizon benchmarks.

LLM AgentsLong-Horizon TasksMemory Architecture
0 likes · 11 min read
Recuris: A New Memory Paradigm That Boosts Performance from 3B Models to Claude Opus 5
PaperAgent
PaperAgent
Aug 25, 2026 · Artificial Intelligence

A New Paradigm for Teaching Agents Tools: Insights from ACL 2026 ToolCPT

ToolCPT demonstrates that embedding real‑world tool knowledge during LLM pre‑training, rather than fine‑tuning, dramatically improves agent performance, using a mined corpus of 5.1 million proxy tools, detailed playbooks, and a 10 % tool‑data mix that yields up to 7.15‑point gains on benchmark tasks.

ACL 2026Agent BenchmarksLLM Agents
0 likes · 8 min read
A New Paradigm for Teaching Agents Tools: Insights from ACL 2026 ToolCPT
Alibaba Cloud Native
Alibaba Cloud Native
Aug 19, 2026 · Artificial Intelligence

Reproducible Three‑Dimensional Evaluation of DeepSeek Harness on Alibaba Cloud AgentLoop

This article presents a reproducible, three‑dimensional deterministic evaluation framework (outcome, compliance, process) built on Alibaba Cloud AgentLoop, applies it to a 10‑task subset of terminal‑bench 2.1 to benchmark DeepSeek Harness against Codex, details the methodology, results, and future research directions.

AI agent assessmentAgentLoopDeepSeek Harness
0 likes · 26 min read
Reproducible Three‑Dimensional Evaluation of DeepSeek Harness on Alibaba Cloud AgentLoop
AI Engineer Programming
AI Engineer Programming
Aug 15, 2026 · Artificial Intelligence

Mastering Stateful AI Agent Orchestration with LangGraph

LangGraph is an open‑source framework that replaces linear LLM pipelines with graph‑based, stateful agents, offering loops, conditional branching, persistent checkpoints, human‑in‑the‑loop support, and built‑in monitoring, enabling complex multi‑step workflows that scale from simple chatbots to enterprise‑grade AI assistants.

AI workflowAgent OrchestrationLLM Agents
0 likes · 20 min read
Mastering Stateful AI Agent Orchestration with LangGraph
DataFunTalk
DataFunTalk
Aug 9, 2026 · Artificial Intelligence

Beyond Model Scaling: How Agent Training Shifts from Bulk Environments to Designed Worlds

Recent ACL 2026 papers (EnvScaler, AgentScaler, Echoverse, and Beyond Simply Environment Scaling) reveal a transition from merely increasing the number of training environments to carefully designing environment distributions that improve agent performance, with empirical evidence showing both gains and diminishing returns.

Agent ScalingEnvironment ScalingLLM Agents
0 likes · 17 min read
Beyond Model Scaling: How Agent Training Shifts from Bulk Environments to Designed Worlds
TonyBai
TonyBai
Aug 5, 2026 · Artificial Intelligence

Why Filesystem‑Based Memory Beats Expectations for LLM Agents – 5 Surprising Findings

A new multi‑institution study formalizes LLM‑agent memory as a three‑role filesystem store, evaluates six memory shapes across four dialogue and one skill benchmark, and reveals that structured organization halves retrieval cost but does not guarantee higher answer accuracy, with model personality and toolsets driving the shape of the memory store.

LLM Agentsagent managementfilesystem memory
0 likes · 20 min read
Why Filesystem‑Based Memory Beats Expectations for LLM Agents – 5 Surprising Findings
Architect
Architect
Aug 4, 2026 · Artificial Intelligence

From Bug Fixes to Completed Work: Insights from Tencent’s WorkBuddy Bench

WorkBuddy Bench reveals why fixing a bug does not equal finishing a task, proposing a four‑layer completion model and a reproducible benchmark that evaluates agents across Code, Web, Office, and Security workspaces, showing how prompts, context, harnesses, loops and graphs must be verified to claim true completion.

AI-evaluationAgent BenchmarkLLM Agents
0 likes · 19 min read
From Bug Fixes to Completed Work: Insights from Tencent’s WorkBuddy Bench
Architect
Architect
Aug 3, 2026 · Artificial Intelligence

Separating Planning and Execution in LLM Agents: ArbiterOS Governance Kernel

As LLM agents gain the ability to read code, modify files, send emails and call APIs, ArbiterOS introduces a runtime governance layer that turns model intents into structured, traceable instructions, enabling policies to approve, block, or request confirmation before any high‑risk action is executed.

AI safetyArbiterOSLLM Agents
0 likes · 23 min read
Separating Planning and Execution in LLM Agents: ArbiterOS Governance Kernel
DataFunSummit
DataFunSummit
Aug 1, 2026 · Artificial Intelligence

MemoHarness: How Agent Evolution Shifts to the External System

MemoHarness expands the notion of self‑evolving agents by keeping the language model frozen and continuously improving the surrounding control system—context assembly, tool interaction, generation settings, workflow orchestration, memory management, and output handling—demonstrating measurable gains on terminal, code‑generation, and finance tasks while highlighting limited experimental scale and selective cross‑task transfer.

Agent HarnessExperience LearningHarness Engineering
0 likes · 17 min read
MemoHarness: How Agent Evolution Shifts to the External System
Machine Heart
Machine Heart
Jul 23, 2026 · Artificial Intelligence

Teaching Agents to Evolve: The Hierarchical Skill Meta‑Evolving Framework HiSME

HiSME, a lightweight hierarchical skill meta‑evolution framework from Tsinghua and Huawei, enables LLM agents to accumulate execution experience without updating model parameters by evolving both task‑specific skills and the meta‑skills that generate and maintain them, improving performance on multi‑turn tool use and open‑world tasks.

HiSMELLM AgentsMeta-learning
0 likes · 11 min read
Teaching Agents to Evolve: The Hierarchical Skill Meta‑Evolving Framework HiSME
HyperAI Super Neural
HyperAI Super Neural
Jul 23, 2026 · Artificial Intelligence

ChemGraph: 13 Benchmarks Reveal LLM Agent’s Capabilities in Computational Chemistry

The Argonne National Laboratory team introduces ChemGraph, an LLM‑driven agent for computational chemistry, and evaluates it across 13 benchmark tasks, showing that small models excel on simple tasks while larger models and multi‑agent designs dramatically improve performance on complex molecular simulations.

AI automationChemGraphLLM Agents
0 likes · 11 min read
ChemGraph: 13 Benchmarks Reveal LLM Agent’s Capabilities in Computational Chemistry
PaperAgent
PaperAgent
Jul 18, 2026 · Artificial Intelligence

SkillOpt 2.0: A Leaner, Faster Self‑Evolving Agent

The article presents SkillOpt‑Lite, a stripped‑down self‑evolving agent pipeline that achieves lighter computation, faster convergence within the first few steps, and higher performance ceilings across multiple benchmarks, while exposing the underlying zero‑order optimization principles and validation requirements.

AgentLLM AgentsSkillOpt
0 likes · 10 min read
SkillOpt 2.0: A Leaner, Faster Self‑Evolving Agent
o-ai.tech
o-ai.tech
Jul 17, 2026 · Artificial Intelligence

When Does Trajectory Review Boost Agent Success? Five Key Factors Explained

Recent research shows that letting agents review their own execution trajectories can improve task success rates, but only under clear conditions such as reliable external feedback, concrete planning outputs, appropriate timing, sufficient model capability, and manageable cost‑benefit trade‑offs.

Agent EngineeringLLM Agentsdynamic replanning
0 likes · 31 min read
When Does Trajectory Review Boost Agent Success? Five Key Factors Explained
Black & White Path
Black & White Path
Jul 17, 2026 · Information Security

A Complete AI Penetration Testing Landscape: 56 Open‑Source Agents, 73 Papers, and Key Models

The article surveys the emerging field of AI‑driven offensive security, cataloguing 56 open‑source penetration‑testing agents, 73 academic papers, six offensive models, benchmark suites, and DARPA AIxCC 2025 finalists, offering researchers and practitioners a consolidated view of tools, research trends, and evaluation frameworks.

AI modelsAI securityDARPA AIxCC
0 likes · 8 min read
A Complete AI Penetration Testing Landscape: 56 Open‑Source Agents, 73 Papers, and Key Models
Ray's Galactic Tech
Ray's Galactic Tech
Jul 16, 2026 · Artificial Intelligence

K8s, Kafka, Nacos Agent Platform to Prevent Token Bankruptcy and Skill Avalanches

The article details how a production‑grade Agent platform built on Kubernetes, Kafka, and Nacos addresses token budget overruns, uncontrolled skill execution, and RAG hallucinations by introducing a four‑layer runtime architecture, token pre‑allocation, explicit state management, dynamic governance policies, and robust skill specifications.

KafkaKubernetesLLM Agents
0 likes · 32 min read
K8s, Kafka, Nacos Agent Platform to Prevent Token Bankruptcy and Skill Avalanches
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Jul 15, 2026 · Artificial Intelligence

How SEAGym Tackles Evaluation Challenges of Self‑Evolving LLM Agents

The SEAGym benchmark reframes LLM agent evaluation from static success rates to dynamic harness evolution, offering multi‑view metrics, detailed snapshot diagnostics, and extensive experiments that reveal validation gains, OOD generalization gaps, batch‑size trade‑offs, and cross‑model transfer effects.

Harness EngineeringLLM AgentsSEAGym
0 likes · 15 min read
How SEAGym Tackles Evaluation Challenges of Self‑Evolving LLM Agents
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Jul 13, 2026 · Artificial Intelligence

LegalWorld: Building a Full‑Lifecycle Interactive Simulation World for Legal AI Agents

LegalWorld creates an interactive environment that simulates the entire Chinese civil litigation process—from consultation to second‑instance trial—using over 75,000 paired first‑ and second‑instance judgments, supports heterogeneous LLM agents, and provides the LongJud‑Bench benchmark to evaluate and improve legal AI performance.

LLM AgentsLegal AILongJud-Bench
0 likes · 15 min read
LegalWorld: Building a Full‑Lifecycle Interactive Simulation World for Legal AI Agents
AI2ML AI to Machine Learning
AI2ML AI to Machine Learning
Jul 13, 2026 · Artificial Intelligence

From QA to Task‑Oriented Agents: Recent Trends in Large Language Models

The article surveys the latest advances in large language model agents, covering multi‑agent collaboration, long‑horizon planning, self‑evolution, trust and safety, test‑time scaling techniques, new foundation and multimodal models, open‑source and closed‑source breakthroughs, world‑model integration, and emerging vertical applications.

LLM AgentsTest-Time ScalingWorld Models
0 likes · 12 min read
From QA to Task‑Oriented Agents: Recent Trends in Large Language Models
Data Party THU
Data Party THU
Jul 13, 2026 · Artificial Intelligence

From QA to Task Completion: Survey of LLM Agent Systems and Harness Design

This survey argues that modern LLM agents should be viewed as a coupled system of a foundational model and an execution harness, analyzes the evolution from prompt engineering to harness engineering, defines six core harness responsibilities, examines task pressures, proposes richer evaluation metrics, and outlines future research directions.

Agent EngineeringExecution HarnessLLM Agents
0 likes · 16 min read
From QA to Task Completion: Survey of LLM Agent Systems and Harness Design
Machine Heart
Machine Heart
Jul 12, 2026 · Artificial Intelligence

Agentic Era: Shifting Recommendation from Platform-Centric to User-Governed

Recent research argues that the traditional platform‑centric recommendation paradigm is reaching its limits, proposing a user‑governed personalization model enabled by LLM agents that can aggregate cross‑platform data, with experimental evidence showing significant performance gains over platform‑only approaches.

LLM Agentsartificial intelligencecross-platform data
0 likes · 20 min read
Agentic Era: Shifting Recommendation from Platform-Centric to User-Governed
AI Engineering
AI Engineering
Jul 11, 2026 · Artificial Intelligence

Why Logs Should Be the Agent Itself, Not Just a Byproduct

The article analyzes Yohei Nakajima’s "The Log is the Agent" paper, showing how ActiveGraph unifies goals, rules, tool calls, LLM responses, and artifacts into a single append‑only event log, enabling deterministic replay, cheap forking, and full provenance for LLM‑driven agents.

ActiveGraphAgent ArchitectureLLM Agents
0 likes · 13 min read
Why Logs Should Be the Agent Itself, Not Just a Byproduct
Machine Heart
Machine Heart
Jul 2, 2026 · Artificial Intelligence

How AReaL 2.0 Accelerates Self‑Evolving Agents

AReaL 2.0 introduces an online reinforcement‑learning infrastructure that turns real‑world agent interactions into a learning loop, defining three pillars—trajectory data protocol, data proxy, and evolution control plane—to enable agents to not only execute tasks but continuously improve from their own experience.

AReaLLLM AgentsMicroservice Architecture
0 likes · 16 min read
How AReaL 2.0 Accelerates Self‑Evolving Agents
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Jun 25, 2026 · Artificial Intelligence

AutoResearch Advances: RUC & Microsoft Open‑Source Arbor Gives Agents Research Memory

Arbor, an open‑source autonomous research framework from RUC’s Gaoling AI Institute and Microsoft Research, structures the research loop with a growing hypothesis‑tree and insight back‑propagation, allowing agents to retain hypotheses, evidence, and failures, and achieves the best held‑out results on six real AO tasks, surpassing Codex and Claude Code.

AI research automationArbor frameworkLLM Agents
0 likes · 18 min read
AutoResearch Advances: RUC & Microsoft Open‑Source Arbor Gives Agents Research Memory
Architect
Architect
Jun 25, 2026 · Artificial Intelligence

Why a Concise CLAUDE.md Entry File Is Critical for LLM Agents in Your Repo

The article explains how a short, well‑structured CLAUDE.md file injects the minimal yet essential context an LLM coding agent needs before it scans a repository, preventing common mis‑assumptions about tech stack, commands, boundaries, and completion criteria.

AGENTS.mdAI toolingCLAUDE.md
0 likes · 16 min read
Why a Concise CLAUDE.md Entry File Is Critical for LLM Agents in Your Repo
PaperAgent
PaperAgent
Jun 20, 2026 · Artificial Intelligence

Vertical Domain Agents Gain 88.5% Boost by Adapting the Runtime Interface, Not Retraining

The paper shows that many failures of deterministic LLM agents stem from mismatched model‑environment interfaces, and introduces LIFE‑HARNESS—a four‑layer runtime harness that extracts reusable failure patterns from training trajectories without updating model weights, delivering an average 88.5% relative performance gain across 126 model‑environment settings.

Deterministic AgentsLLM AgentsLife-Harness
0 likes · 8 min read
Vertical Domain Agents Gain 88.5% Boost by Adapting the Runtime Interface, Not Retraining
Machine Heart
Machine Heart
Jun 19, 2026 · Artificial Intelligence

Which Multi‑Agent Communication Protocol Wins? UIUC Introduces ProtocolBench at ICML 2026

The UIUC team presents ProtocolBench, a systematic benchmark that compares four multi‑agent communication protocols across four realistic scenarios, revealing distinct trade‑offs in latency, reliability, and security, and proposes ProtocolRouter to automatically select the most suitable protocol per workload.

LLM AgentsProtocolBenchProtocolRouter
0 likes · 14 min read
Which Multi‑Agent Communication Protocol Wins? UIUC Introduces ProtocolBench at ICML 2026
Code Mala Tang
Code Mala Tang
Jun 19, 2026 · Artificial Intelligence

Five Skeptical Questions About RTK’s Token Compression Claims

The article critically examines RTK’s token‑compression promises, exposing misleading savings metrics, silent‑failure bugs, missing task‑success benchmarks, its status as a fragile feature rather than a product, and the brittleness of its output parser, before offering concrete guidance on when to use it.

CLI output parsingLLM AgentsRTK
0 likes · 8 min read
Five Skeptical Questions About RTK’s Token Compression Claims
HyperAI Super Neural
HyperAI Super Neural
Jun 18, 2026 · Artificial Intelligence

Weekly AI Paper Digest: D4RT 300× Faster 4D Reconstruction, SAI Theory Challenges AGI, and More

This week’s AI paper roundup covers DeepMind’s D4RT framework that accelerates dynamic 4D reconstruction by up to 300×, a Columbia‑NYU proposal of Superhuman Adaptable Intelligence that questions AGI, MIT‑UW findings on chatbot delusional spiraling, security risks of autonomous agents, a new ARA protocol for executable research artifacts, a vision of AI‑driven software engineering, and a memory‑caching approach that expands RNN capacity while reducing complexity.

AI safetyD4RTDynamic 4D Reconstruction
0 likes · 11 min read
Weekly AI Paper Digest: D4RT 300× Faster 4D Reconstruction, SAI Theory Challenges AGI, and More
Machine Heart
Machine Heart
Jun 17, 2026 · Artificial Intelligence

Why RL‑Trained Agents Still Fail to Reason Actively: The Information Self‑Locking Problem

The paper reveals that outcome‑based reinforcement learning often traps LLM agents in an information self‑locking regime where weak action selection and belief tracking prevent proper credit assignment, and introduces AREW, a lightweight advantage‑reweighting method that restores active reasoning across multiple tasks and models.

AREWLLM Agentsactive reasoning
0 likes · 24 min read
Why RL‑Trained Agents Still Fail to Reason Actively: The Information Self‑Locking Problem
PaperAgent
PaperAgent
Jun 17, 2026 · Artificial Intelligence

Spatial-Agent: A New Concept‑Transformation Paradigm for Map Agents

The paper introduces Spatial‑Agent, which models geospatial question answering as a concept‑transformation process using a GeoFlow Graph intermediate representation, outlines a five‑step workflow, defines core concepts and functional roles, and demonstrates its effectiveness on MapEval‑API and MapQA benchmarks with detailed error and cost analyses.

GISGeoFlow GraphLLM Agents
0 likes · 13 min read
Spatial-Agent: A New Concept‑Transformation Paradigm for Map Agents
Machine Heart
Machine Heart
Jun 15, 2026 · Artificial Intelligence

Breaking the SWE‑bench Score‑Only Myth: Open‑Source Benchmark that Independently Measures Harnesses

The article critiques the reliance on raw SWE‑bench scores for programming agents, introduces the Claw‑SWE‑Bench benchmark and a dedicated adapter that isolates harness effects, and presents extensive experiments showing how model choice, harness design, and cost impact real-world coding performance across multiple languages.

HarnessLLM AgentsPass@1
0 likes · 14 min read
Breaking the SWE‑bench Score‑Only Myth: Open‑Source Benchmark that Independently Measures Harnesses
Java Tech Enthusiast
Java Tech Enthusiast
Jun 13, 2026 · Artificial Intelligence

Why Bigger 1M‑Token Windows Still Need Careful Context Engineering

Even though modern LLMs like DeepSeek‑V4, GPT‑5.5 and Claude Opus 4.7 support 1 million‑token windows, simply stuffing more data does not improve agent performance; effective Context Engineering—selecting, structuring, and managing the right information—remains essential for reliable results.

LLM AgentsMemoryRAG
0 likes · 32 min read
Why Bigger 1M‑Token Windows Still Need Careful Context Engineering
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Jun 12, 2026 · Artificial Intelligence

The Next Frontier for Large‑Scale LLM Agents: 17 Must‑Read Papers on Self‑Evolving Harnesses

This article surveys 17 recent core papers that explore how the system‑level harness surrounding large‑model agents can be automatically generated, evolved, and audited, covering topics such as system boundaries, failure‑driven improvement, memory and skill optimization, source‑level rewriting, scaling laws, aging, and safety.

Agent MemoryHarness EngineeringLLM Agents
0 likes · 18 min read
The Next Frontier for Large‑Scale LLM Agents: 17 Must‑Read Papers on Self‑Evolving Harnesses
Data Party THU
Data Party THU
Jun 11, 2026 · Artificial Intelligence

Boost 18 LLM Agents Without Retraining Using LIFE‑HARNESS

The article introduces LIFE‑HARNESS, a runtime‑interface adaptation framework that keeps model weights unchanged, extracts reusable failure patterns from a single model's training trace, and achieves an average 88.5% relative performance gain across 18 LLM agents and 7 deterministic environments, with successful transfer to 17 other models.

Cross-Model TransferLLM AgentsRuntime Harness
0 likes · 8 min read
Boost 18 LLM Agents Without Retraining Using LIFE‑HARNESS
Network Intelligence Research Center (NIRC)
Network Intelligence Research Center (NIRC)
Jun 11, 2026 · Artificial Intelligence

Scaling Automated Formalization of Mathematics: Inside Meta’s AutoformBot and the ATLAS Lean 4 Library

Meta’s recent paper presents AutoformBot, a multi‑agent system that treats formalizing entire mathematics textbooks as a large‑scale software‑engineering project, generating the ATLAS Lean 4 library with over 45,000 declarations and demonstrating a 71 % success rate across 26 open‑access books.

AutoformBotLLM AgentsLean 4
0 likes · 14 min read
Scaling Automated Formalization of Mathematics: Inside Meta’s AutoformBot and the ATLAS Lean 4 Library
Xike
Xike
Jun 9, 2026 · Artificial Intelligence

From Demo to Production: Key Practices for Engineering LLM Agents

The article explains how to transform a prototype LLM agent into a reliable production service by defining service contracts, externalizing configuration, handling session state, implementing multi‑level rate limiting, and integrating observability, deployment, and rollback mechanisms to avoid common engineering pitfalls.

ConfigurationLLM Agentsdeployment
0 likes · 25 min read
From Demo to Production: Key Practices for Engineering LLM Agents
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Jun 8, 2026 · Artificial Intelligence

Re‑evaluating the Token World of LLM Agents: A Dual‑View Economics Overview

The paper surveys the rapid growth of token consumption in LLM agents, proposes a dual‑view Token Economics framework that treats tokens as production factors, exchange media, and accounting units, and classifies optimization challenges from single‑agent efficiency to ecosystem‑level pricing, security, and future research directions.

AI Resource ManagementCost OptimizationLLM Agents
0 likes · 10 min read
Re‑evaluating the Token World of LLM Agents: A Dual‑View Economics Overview
Alibaba Cloud Native
Alibaba Cloud Native
Jun 8, 2026 · Artificial Intelligence

Code Harness vs. Model-Driven Harness: Can Agent Control Be Expressed as Executable Natural Language?

The article reviews the "Natural-Language Agent Harnesses" paper, explains the distinction between code, middleware, and harness layers for LLM agents, introduces NLAH and IHR concepts, and details experimental evaluations that show natural‑language harnesses can match code‑based control while exposing new trade‑offs and risks.

Agent OrchestrationIntelligent Harness RuntimeLLM Agents
0 likes · 13 min read
Code Harness vs. Model-Driven Harness: Can Agent Control Be Expressed as Executable Natural Language?
TechVision Expert Circle
TechVision Expert Circle
Jun 2, 2026 · Artificial Intelligence

How to Build a System with True Self‑Decision Capability

This article details a CTO‑driven initiative to give core business systems genuine self‑decision ability by defining the concept, presenting a four‑layer architecture, and sharing concrete design choices, safety mechanisms, governance practices, and real‑world lessons learned from an e‑commerce fulfillment use case.

KafkaLLM AgentsMulti-Agent Architecture
0 likes · 14 min read
How to Build a System with True Self‑Decision Capability