BestHub
Sign in
Tagged articles

reasoning

79 articles · Page 1 of 1
Machine Heart
Machine Heart
Sep 30, 2026 · Artificial Intelligence

ME-Decoding: Reframing LLM Decoding as Ensemble Pruning with Semantic Redundancy Control

Renmin University researchers propose ME-Decoding, a method that selects candidate tokens by jointly optimizing probability confidence and semantic diversity via Mahalanobis distance, outperforming probability-only truncation on reasoning and open-ended generation across multiple models and temperatures with only 3% latency overhead.

EMNLP 2026LLM decodingMahalanobis distance
0 likes · 11 min read
ME-Decoding: Reframing LLM Decoding as Ensemble Pruning with Semantic Redundancy Control
AI Large-Model Wave and Transformation Guide
AI Large-Model Wave and Transformation Guide
Sep 9, 2026 · Artificial Intelligence

Why LLMs Fail at Critical Decisions: Ontologies Provide the Missing World Model

The author details how LLMs failed in underwater battlefield simulations despite trying prompts, agents, RAG, and knowledge graphs, and explains why ontologies — formal, reasoning-capable world models — are essential for trustworthy AI decisions, illustrating with a concrete case and a six-step ontology engineering process.

AI decision-makingLLM LimitationsOntoL
0 likes · 12 min read
Why LLMs Fail at Critical Decisions: Ontologies Provide the Missing World Model
AI Large-Model Wave and Transformation Guide
AI Large-Model Wave and Transformation Guide
Aug 6, 2026 · Databases

Ontology vs Graph Inference Engine: How the Wrong Choice Can Render Your Knowledge Graph Useless

Choosing between OWL‑based ontologies and graph‑database inference engines fundamentally affects knowledge‑graph design: ontologies provide formal logical consistency and open‑world reasoning, while graph inference offers fast, flexible queries, with each suited to different constraints, scalability, and maintenance scenarios.

Neo4jOWLOntology
0 likes · 9 min read
Ontology vs Graph Inference Engine: How the Wrong Choice Can Render Your Knowledge Graph Useless
Data Party THU
Data Party THU
Jul 28, 2026 · Artificial Intelligence

The Three Paradoxes Blocking Mature AI Agents: Memory, Reasoning, and Self‑Evolution

The article reviews recent AI agent research, exposing three structural paradoxes—memory, reasoning, and evolution—each illustrated with concrete systems, benchmarks, and safety studies, and argues that only coordinated progress across all three dimensions can yield truly mature, self‑improving agents.

AI AgentsHarness EngineeringRecursive Self-Improvement
0 likes · 16 min read
The Three Paradoxes Blocking Mature AI Agents: Memory, Reasoning, and Self‑Evolution
Bilibili Tech
Bilibili Tech
Jul 1, 2026 · Artificial Intelligence

FATE Series (SABER & CASTER) Debuts at ACL 2026: Advanced LLM Reasoning

At ACL 2026 in San Diego, Bilibili’s tech team introduced the FATE series—SABER, which reduces overthinking in LLMs with a token‑budgeted switchable training, and CASTER, a community‑aware evaluation system built on Social‑CoT and the MEDEA framework that outperforms GPT‑5.2 and Claude‑4.5‑Opus on the new CASTER‑Bench, while also promoting the B‑UP talent recruitment program.

BenchmarkLLMMultimodal Evaluation
0 likes · 10 min read
FATE Series (SABER & CASTER) Debuts at ACL 2026: Advanced LLM Reasoning
Qborfy AI
Qborfy AI
Jun 25, 2026 · Artificial Intelligence

Understanding Reasoning Control Parameters in Large Model APIs: A Deep Dive into reasoning_effort, thinking, and max_completion_tokens

This article explains how inference‑oriented LLMs differ from standard models, details the three key reasoning‑control parameters (reasoning_effort, thinking, max_completion_tokens), compares their usage across OpenAI o1, Anthropic Claude, DeepSeek‑R1 and Kimi, and provides practical guidance on selecting values, managing costs, and deciding when to employ reasoning models.

API parametersLLMcost control
0 likes · 18 min read
Understanding Reasoning Control Parameters in Large Model APIs: A Deep Dive into reasoning_effort, thinking, and max_completion_tokens
AI Large-Model Wave and Transformation Guide
AI Large-Model Wave and Transformation Guide
Jun 17, 2026 · Artificial Intelligence

Don’t Mix Prediction, Reasoning, Inference, and Decision in the Ontology Era

The article explains how prediction, reasoning, and inference differ, why a pure prediction model leaves the decision chain broken, and how a dynamic ontology‑driven feature framework—temporal, functional, and relational features—creates explainable, verifiable, and iterative decision loops.

Ontologydecision-makingdynamic ontology
0 likes · 9 min read
Don’t Mix Prediction, Reasoning, Inference, and Decision in the Ontology Era
AI Large Model Application Practice
AI Large Model Application Practice
Jun 11, 2026 · Artificial Intelligence

Ontology Meets AI Agents: From Reasoning to Enterprise Semantic Infrastructure

The article demonstrates how an ontology can serve as a business‑semantic layer for enterprise AI agents, covering multi‑relationship propagation, schema‑to‑concept mapping, cross‑system customer views, and a unified semantic query engine, while also discussing practical limits and rollout advice.

AI AgentsEnterprise AIOntology
0 likes · 11 min read
Ontology Meets AI Agents: From Reasoning to Enterprise Semantic Infrastructure
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Jun 10, 2026 · Artificial Intelligence

OneReason: Enabling Recommendation Systems to Reason

OneReason introduces a systematic reasoning capability into industrial recommendation models through multi‑stage pre‑training, chain‑of‑thought fine‑tuning, and reinforcement learning, achieving significant gains in click‑through, revenue, and cross‑domain recommendation performance while preserving the underlying language abilities of the base model.

PretrainingReinforcement Learningchain-of-thought
0 likes · 29 min read
OneReason: Enabling Recommendation Systems to Reason
Machine Heart
Machine Heart
Jun 9, 2026 · Artificial Intelligence

OneReason: When Recommendation Systems Learn to Reason

The OneReason report details how Kuaishou’s recommendation team injects reasoning into large‑scale recommender models through a four‑level pre‑training pipeline, chain‑of‑thought (CoT) fine‑tuning, and specialized reinforcement learning, achieving significant offline gains and a 10.33% exposure lift in a live A/B test.

CoTLLMPretraining
0 likes · 31 min read
OneReason: When Recommendation Systems Learn to Reason
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
May 19, 2026 · Artificial Intelligence

From P(y|x) to P(y): Reinforcement Learning in Pre‑train Space Unlocks Endogenous Reasoning

The paper introduces PreRL, which removes the input condition to directly optimize the reasoning trajectory (P(y)) of large language models, and combines it with standard RL in Dual Space RL (DSRL), achieving consistent gains on math and out‑of‑distribution benchmarks, faster training, and richer reasoning behaviors.

DSRLMath BenchmarksPreRL
0 likes · 11 min read
From P(y|x) to P(y): Reinforcement Learning in Pre‑train Space Unlocks Endogenous Reasoning
Xiaomi Tech
Xiaomi Tech
May 14, 2026 · Artificial Intelligence

500 M Videos Yield the Largest Open‑Source GUI Dataset; 3B Model Cuts Inference Tokens 71% and Beats Larger Models (Xiaomi AI at ICML 2026)

Xiaomi’s AI team extracted 5 billion video frames to create the world’s largest open‑source GUI dataset, demonstrated that a 3 B‑parameter model can reduce inference tokens by 71% while surpassing larger models, and presented a suite of ICML 2026 papers covering data scaling, benchmarking, reasoning, multimodal perception, and training stability for GUI agents and other AI tasks.

GUI AgentMultimodalbenchmarking
0 likes · 21 min read
500 M Videos Yield the Largest Open‑Source GUI Dataset; 3B Model Cuts Inference Tokens 71% and Beats Larger Models (Xiaomi AI at ICML 2026)
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Apr 28, 2026 · Artificial Intelligence

Can Reasoning Models Keep Improving? TEMPO Uses EM to Stop Reward Drift

The paper introduces TEMPO, a test‑time training framework inspired by the Expectation‑Maximization algorithm, which alternates policy optimization (M‑step) with Critic calibration (E‑step) to prevent reward‑signal drift, and demonstrates on Qwen3 and OLMO3 models that it continuously improves reasoning performance and maintains output diversity beyond the saturation point of existing TTT methods.

EM algorithmReinforcement LearningTest-Time Training
0 likes · 14 min read
Can Reasoning Models Keep Improving? TEMPO Uses EM to Stop Reward Drift
Machine Heart
Machine Heart
Apr 28, 2026 · Artificial Intelligence

Can LLMs Answer More Accurately While Writing Less? Introducing SHAPE’s Reasoning Tax

The SHAPE framework (Stage‑aware Hierarchical Advantage via Potential Estimation) adds a milestone‑based “reasoning tax” to large language model inference, providing step‑wise correctness signals and penalizing verbosity, which yields an average 3% accuracy gain and a 30% reduction in token consumption across multiple math‑reasoning benchmarks.

ACL 2026LLMReinforcement Learning
0 likes · 10 min read
Can LLMs Answer More Accurately While Writing Less? Introducing SHAPE’s Reasoning Tax
AgentGuide
AgentGuide
Apr 2, 2026 · Artificial Intelligence

Understanding ReAct: The Reason‑Act Loop Behind LLM Agents

The article explains ReAct—a Reason‑Act framework for large language model agents that observes, reasons, takes actions via tools, receives feedback, and iterates—highlighting its distinction from plain QA, its step‑by‑step workflow, practical importance, and a weather‑query example.

AI workflowLLM agentsReAct
0 likes · 5 min read
Understanding ReAct: The Reason‑Act Loop Behind LLM Agents
Architect's Alchemy Furnace
Architect's Alchemy Furnace
Mar 20, 2026 · Artificial Intelligence

Why Vector‑Based RAG Falls Short and How PageIndex’s Reasoning‑Based Retrieval Solves It

This article analyzes the fundamental limitations of traditional vector‑based Retrieval‑Augmented Generation, introduces Vectify AI’s reasoning‑driven PageIndex framework, and explains how hierarchical, non‑vector indexing enables more accurate, context‑aware document retrieval for complex, domain‑specific texts.

AILLMPageIndex
0 likes · 15 min read
Why Vector‑Based RAG Falls Short and How PageIndex’s Reasoning‑Based Retrieval Solves It
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Mar 6, 2026 · Artificial Intelligence

Why Reasoning and Tool-Use Clash in Agentic RL—and How DART Solves It

Recent studies reveal that in Agentic RL, jointly training reasoning and tool-use on shared parameters creates a persistent negative interaction, with gradients nearly orthogonal, limiting performance; a disentangled tuning approach (DART) using separate LoRA adapters isolates the two abilities and restores gains across benchmarks.

Agentic RLDartGradient Interference
0 likes · 12 min read
Why Reasoning and Tool-Use Clash in Agentic RL—and How DART Solves It
AI Large Model Application Practice
AI Large Model Application Practice
Mar 2, 2026 · Artificial Intelligence

How to Build Your First Business Ontology for AI Agents – A Step‑by‑Step Guide

This article walks you through why enterprise AI agents need a semantic ontology, explains TBox and ABox concepts, outlines a general modeling workflow, introduces RDF/OWL standards and tools like Protégé and reasoners, and provides a hands‑on example—including Python code with Owlready2—to create and test a business ontology for order‑expedition rules.

OWLOntologyRDF
0 likes · 18 min read
How to Build Your First Business Ontology for AI Agents – A Step‑by‑Step Guide
AI Large Model Application Practice
AI Large Model Application Practice
Feb 19, 2026 · Artificial Intelligence

When Should You Add a Knowledge Graph? 6 Practical Decision Criteria

This article outlines six concrete criteria—relationship‑centric data, reproducible reasoning, evolving schemas, multi‑hop queries, explainable decisions, and cross‑system data integration—to help engineers decide whether a knowledge graph is the right solution or if a relational database will suffice.

AI EngineeringData IntegrationGraph Databases
0 likes · 15 min read
When Should You Add a Knowledge Graph? 6 Practical Decision Criteria
AI Engineering
AI Engineering
Jan 30, 2026 · Artificial Intelligence

Why Letting LLMs Argue Improves Their Reasoning Quality

Google’s recent study of over 8,000 reasoning tasks shows that advanced LLMs like DeepSeek‑R1 spontaneously develop multiple internal “expert” personas that debate, and that activating a discovered “social switch” dramatically raises accuracy, revealing that engineered conflict can enhance AI reasoning.

AI debateFeature ControlLLM
0 likes · 8 min read
Why Letting LLMs Argue Improves Their Reasoning Quality
AI Large Model Application Practice
AI Large Model Application Practice
Jan 26, 2026 · Artificial Intelligence

Why Enterprise AI Agents Fail and How Ontology Can Fix Them

This article examines why most enterprise AI agents stumble—due to hallucinations, semantic mismatches, and lack of explainability—then introduces ontology as a semantic layer that structures business concepts, rules, and constraints to enable reliable reasoning, centralized rule management, and transparent AI behavior.

AgentOntologyenterprise-ai
0 likes · 17 min read
Why Enterprise AI Agents Fail and How Ontology Can Fix Them
Network Intelligence Research Center (NIRC)
Network Intelligence Research Center (NIRC)
Jan 14, 2026 · Artificial Intelligence

From Black‑Box Guessing to Quantitative Deconstruction: Unveiling the Mystery Inside Large Language Models

At EMNLP 2025, the BUPT NIRC team presented a paper that introduces the ARR metric to quantitatively separate latent reasoning from factual shortcuts in LLMs, using Logit Lens and Attention Knockout to reveal distinct internal pathways and shares their conference experience.

ARR metricAttention KnockoutEMNLP2025
0 likes · 6 min read
From Black‑Box Guessing to Quantitative Deconstruction: Unveiling the Mystery Inside Large Language Models
PMTalk Product Manager Community
PMTalk Product Manager Community
Jan 5, 2026 · Artificial Intelligence

Turning Base Models from Semi‑Finished to Killer AI Products: A PM’s Playbook

The article breaks down how AI product managers can transform a raw base model into a market‑ready, high‑impact product by applying supervised fine‑tuning, tool‑use routing, RLHF alignment, and chain‑of‑thought reasoning, while highlighting trade‑offs, cost shifts, and evaluation metrics.

Artificial IntelligenceRLHFSFT
0 likes · 13 min read
Turning Base Models from Semi‑Finished to Killer AI Products: A PM’s Playbook
DataFunTalk
DataFunTalk
Dec 25, 2025 · Artificial Intelligence

How DeepAgent Redefines General AI Reasoning with Scalable Toolsets

DeepAgent, a new end‑to‑end reasoning agent, integrates autonomous thinking, dynamic tool search, and execution to handle over 16,000 APIs, embodied tasks, and research assistance, achieving state‑of‑the‑art performance on benchmarks like TMDB, ToolBench, ALFWorld, WebShop, and GAIA.

Reinforcement Learninglarge language modelmemory management
0 likes · 15 min read
How DeepAgent Redefines General AI Reasoning with Scalable Toolsets
KooFE Frontend Team
KooFE Frontend Team
Dec 13, 2025 · Artificial Intelligence

Unlocking LLM Reasoning: Advanced Chain‑of‑Thought Prompting Techniques Explained

This article explains how Chain‑of‑Thought prompting and its variants—zero‑shot CoT, Thread of Thought, Tabular CoT, Analogical Prompting, and Step‑back Prompting—enable large language models to perform multi‑step reasoning by breaking problems into intermediate steps, with practical prompts, examples, and implementation details.

Zero-shot Learningchain-of-thoughtreasoning
0 likes · 12 min read
Unlocking LLM Reasoning: Advanced Chain‑of‑Thought Prompting Techniques Explained
Wu Shixiong's Large Model Academy
Wu Shixiong's Large Model Academy
Dec 11, 2025 · Artificial Intelligence

Why Reward Models Need Reasoning: From Scalar Scores to RM‑R1

Interviewers increasingly ask why modern reward models must go beyond scalar scores to incorporate reasoning, and this article explains the limitations of traditional scalar reward models, the benefits of the RM‑R1 framework, and how reasoning‑based rewards improve alignment, stability, and task performance in large language model training.

AI AlignmentLLMRLHF
0 likes · 11 min read
Why Reward Models Need Reasoning: From Scalar Scores to RM‑R1
Meituan Technology Team
Meituan Technology Team
Nov 3, 2025 · Artificial Intelligence

Introducing VitaBench: A Real-World Agent Benchmark That Reveals a 30% Success Gap

VitaBench, a new open‑source benchmark from Meituan’s LongCat team, evaluates LLM‑driven agents across three realistic life‑service scenarios—food ordering, restaurant dining, and travel planning—using 66 tools and quantifying reasoning, tool, and interaction complexities, exposing a mere 30% success rate on complex cross‑scene tasks.

AIAgentBenchmark
0 likes · 14 min read
Introducing VitaBench: A Real-World Agent Benchmark That Reveals a 30% Success Gap
Software Engineering 3.0 Era
Software Engineering 3.0 Era
Sep 28, 2025 · Artificial Intelligence

Why Large Language Models Appear So Smart: The Science of Emergence

The article explains how massive language models achieve seemingly intelligent behavior through emergence at a critical scale, hierarchical planning, attention-driven global coherence, multimodal understanding, and progressive training techniques that turn simple token prediction into sophisticated reasoning and creativity.

Attention Mechanismemergencelarge language models
0 likes · 15 min read
Why Large Language Models Appear So Smart: The Science of Emergence
Meituan Technology Team
Meituan Technology Team
Sep 22, 2025 · Artificial Intelligence

LongCat-Flash-Thinking: The New SOTA Open-Source LLM for Deep Reasoning and Tool Use

Meituan’s LongCat team unveiled LongCat-Flash-Thinking, an open‑source large language model that combines deep logical reasoning with tool‑calling capabilities, achieving state‑of‑the‑art performance across logic, mathematics, code, and agentic tasks, and introducing novel training frameworks such as domain‑parallel RL and DORA.

AIBenchmarklarge language model
0 likes · 7 min read
LongCat-Flash-Thinking: The New SOTA Open-Source LLM for Deep Reasoning and Tool Use
Data Party THU
Data Party THU
Sep 18, 2025 · Artificial Intelligence

How Reinforcement Learning is Shaping the Future of Large Reasoning Models

This article surveys recent advances in applying reinforcement learning to large reasoning models, outlining the historical background, key breakthroughs like OpenAI o1 and DeepSeek‑R1, current challenges in reward design and scalability, and future research directions toward more capable AI systems.

AI researchRLHFreasoning
0 likes · 9 min read
How Reinforcement Learning is Shaping the Future of Large Reasoning Models
Data Party THU
Data Party THU
Sep 9, 2025 · Artificial Intelligence

From Chain‑of‑Thought to Graph‑of‑Thought: The Evolution of LLM Reasoning

This article examines how large language model reasoning has progressed from linear Chain‑of‑Thought prompting to parallel Tree‑of‑Thought and flexible Graph‑of‑Thought approaches, highlighting each method’s mechanism, strengths, limitations, computational costs, and the broader shift toward cognitive‑centric AI research.

AI researchGraph-of-ThoughtTree of Thought
0 likes · 7 min read
From Chain‑of‑Thought to Graph‑of‑Thought: The Evolution of LLM Reasoning
Baobao Algorithm Notes
Baobao Algorithm Notes
Sep 3, 2025 · Artificial Intelligence

How Atom-Searcher Boosts LLM Reasoning with Atomic Thought Rewards

Atom-Searcher introduces an atomic‑thought reinforcement‑learning framework that decomposes complex reasoning into fine‑grained units, uses a Reasoning Reward Model to assign step‑wise rewards, dynamically balances process and result incentives, and achieves state‑of‑the‑art performance on multiple LLM benchmarks.

Agentic ResearchAtomic ThoughtLLM
0 likes · 12 min read
How Atom-Searcher Boosts LLM Reasoning with Atomic Thought Rewards
Data Party THU
Data Party THU
Sep 1, 2025 · Artificial Intelligence

Why Intermediate Tokens Make LLMs Reason Better: Insights from Denny Zhou

The article analyzes Denny Zhou's Stanford CS25 lecture on large language model reasoning, explaining how intermediate token generation, chain‑of‑thought prompting, self‑consistency, reinforcement‑learning fine‑tuning, and answer aggregation together unlock powerful reasoning capabilities beyond traditional greedy decoding.

AI researchLLMchain-of-thought
0 likes · 17 min read
Why Intermediate Tokens Make LLMs Reason Better: Insights from Denny Zhou
Data Thinking Notes
Data Thinking Notes
Aug 21, 2025 · Artificial Intelligence

Why Intermediate Tokens Matter: Denny Zhou’s Deep Insights into LLM Reasoning

This article distills Denny Zhou’s Stanford CS25 lecture, explaining how large language models achieve reasoning through intermediate token generation, chain‑of‑thought prompting, self‑consistency, reinforcement‑learning fine‑tuning, and answer aggregation, while highlighting theoretical foundations and practical breakthroughs.

LLMReinforcement Learningchain-of-thought
0 likes · 18 min read
Why Intermediate Tokens Matter: Denny Zhou’s Deep Insights into LLM Reasoning
Alibaba Cloud Big Data AI Platform
Alibaba Cloud Big Data AI Platform
Aug 8, 2025 · Artificial Intelligence

What Von Neumann’s Brain Theory Reveals About Prompt Engineering for LLMs

The article explores how Von Neumann’s insights on the brain‑computer analogy illuminate modern large‑language‑model prompt engineering, comparing logical reasoning chains, memory mechanisms, and DSL‑driven computation to improve accuracy, reduce hallucinations, and balance reasoning depth with precise calculation.

DSLRAGcomputation
0 likes · 14 min read
What Von Neumann’s Brain Theory Reveals About Prompt Engineering for LLMs
Amap Tech
Amap Tech
Jul 24, 2025 · Artificial Intelligence

FingER: Fine-Grained Evaluation and Reasoning for AI-Generated Videos

The paper introduces FingER, an entity-level evaluation framework and the FingER-Instruct-60k dataset for assessing AI-generated video quality with fine-grained reasoning, and demonstrates state-of-the-art zero-shot performance on multiple benchmarks using novel training strategies.

AI-generated videodatasetfine-grained evaluation
0 likes · 9 min read
FingER: Fine-Grained Evaluation and Reasoning for AI-Generated Videos
DaTaobao Tech
DaTaobao Tech
Jul 16, 2025 · Artificial Intelligence

From GPT‑4 to Agentic AI: How LLM Architecture Evolved (2023‑2025)

Since GPT‑4’s 2023 debut, large language models have shifted from sheer scale to efficiency‑driven designs, advanced reasoning with chain‑of‑thought, and agentic tool use, as illustrated by MoE, MLA, and new attention mechanisms, reshaping benchmarks, commercial strategies, and the future of AI.

Agentic AILLMefficiency
0 likes · 24 min read
From GPT‑4 to Agentic AI: How LLM Architecture Evolved (2023‑2025)
High Availability Architecture
High Availability Architecture
Jul 9, 2025 · Artificial Intelligence

How LLMs Evolved from GPT‑4 to Agentic AI: Trends, Techniques, and Future Directions

This article analyzes the rapid evolution of large language models from the GPT‑4 era through efficiency‑focused sparsity and attention innovations, to inference‑time reasoning and tool‑using agents, highlighting key architectures, benchmark breakthroughs, competitive strategies, and emerging research directions toward embodied AI.

Agentic AILLMTransformer
0 likes · 24 min read
How LLMs Evolved from GPT‑4 to Agentic AI: Trends, Techniques, and Future Directions
Alibaba Cloud Developer
Alibaba Cloud Developer
Jul 8, 2025 · Artificial Intelligence

From GPT‑4 to Thinking Models: How LLM Architecture Evolved After 2023

This article traces the evolution of large language models from the GPT‑4 era through 2024‑2025, highlighting the shift from pure scaling to efficiency‑focused architectures, the rise of reasoning‑centric "thinking" models, and the emergence of agentic capabilities that enable tools and real‑world interaction.

AgentsLLMTransformer
0 likes · 27 min read
From GPT‑4 to Thinking Models: How LLM Architecture Evolved After 2023
AI Frontier Lectures
AI Frontier Lectures
Jun 9, 2025 · Artificial Intelligence

AI Research Highlights: Robo-DM, DeepKD, LLM Security, and Reasoning Innovations

This roundup presents recent AI breakthroughs, including Robo‑DM’s efficient robot dataset management, DeepKD’s decoupled knowledge‑distillation trainer, a novel informed white‑box attack exposing weaknesses in LLM alignment defenses, the RePPL hallucination detector, Self‑GIVE’s associative reasoning framework, and LLM‑driven RL ensemble methods.

AIknowledge distillationreasoning
0 likes · 15 min read
AI Research Highlights: Robo-DM, DeepKD, LLM Security, and Reasoning Innovations
AI Frontier Lectures
AI Frontier Lectures
Jun 5, 2025 · Artificial Intelligence

Bridging Thought Leaps: How CoT‑Bridge Boosts LLM Reasoning Accuracy

This paper introduces the Thought Leap Bridge task and the CoT‑Bridge model, which detect and fill missing intermediate steps in chain‑of‑thought reasoning, dramatically improving large language model performance on mathematical and logical benchmarks and enhancing downstream distillation and reinforcement‑learning pipelines.

Chain-of-ThoughtCoT-BridgeLLM
0 likes · 8 min read
Bridging Thought Leaps: How CoT‑Bridge Boosts LLM Reasoning Accuracy
DataFunTalk
DataFunTalk
Jun 3, 2025 · Artificial Intelligence

Meta‑Capability Alignment: Psychologically Inspired Training to Endow Large Language Models with Stable Reasoning

Researchers from NUS, Tsinghua and Salesforce AI Research introduce a meta‑capability alignment framework that integrates deductive, inductive and abductive reasoning via a psychology‑based triple, automatically generates and validates training data, and demonstrates over 10% accuracy gains on math, coding and scientific benchmarks for 7B and 32B models.

Meta‑Capability Alignmentlarge language modelsmodel training
0 likes · 8 min read
Meta‑Capability Alignment: Psychologically Inspired Training to Endow Large Language Models with Stable Reasoning
Alibaba Cloud Big Data AI Platform
Alibaba Cloud Big Data AI Platform
May 29, 2025 · Artificial Intelligence

How OmniThought Enables Adaptive Reasoning Chains for Better LLM Performance

This article introduces the OmniThought dataset, which annotates over two million chain‑of‑thought reasoning steps with Reasoning Verbosity and Cognitive Difficulty scores, and explains how these metrics guide the training of DistilQwen‑ThoughtX models that adapt chain length to task difficulty, achieving superior performance compared to existing distilled LLMs.

CoTLLMdataset
0 likes · 16 min read
How OmniThought Enables Adaptive Reasoning Chains for Better LLM Performance
Model Perspective
Model Perspective
May 19, 2025 · Fundamentals

Master Logical Reasoning: Methods, Fallacies, and Persuasive Argument Frameworks

This guide systematically explores deductive, inductive, analogical, and causal reasoning, outlines common logical fallacies, presents argument structures and evaluation criteria, and introduces the Toulmin model, offering readers practical tools to strengthen critical thinking and construct persuasive, well‑grounded arguments.

Fallaciesargumentationcritical thinking
0 likes · 6 min read
Master Logical Reasoning: Methods, Fallacies, and Persuasive Argument Frameworks
DevOps
DevOps
May 18, 2025 · Artificial Intelligence

Why the Focus Has Shifted from AI Agents to Agentic Workflows

Although large language models have enabled AI agents that mimic human digital interactions, their commercial accuracy remains far below production standards, prompting the industry to pivot toward agentic workflows and data synthesis, which promise more reliable task automation, reasoning, and observable, auditable processes for knowledge work.

Data Synthesisagentic workflowsknowledge work
0 likes · 6 min read
Why the Focus Has Shifted from AI Agents to Agentic Workflows
Baobao Algorithm Notes
Baobao Algorithm Notes
May 2, 2025 · Artificial Intelligence

Do Reinforcement Learning Techniques Really Boost LLM Reasoning? A Deep Dive into Recent Models

This article analyzes whether reinforcement learning enhances large language model reasoning, compares findings from DeepSeek-Math, a Tsinghua‑Shanghai Jiao‑Tong paper, and Qwen3, and outlines practical training pipelines—including Seed‑Thinking‑v1.5, DeepSeek‑R1, Kimi‑K1.5, and Qwen3—that aim to endow LLMs with robust reasoning capabilities.

Artificial IntelligenceLLMReinforcement Learning
0 likes · 12 min read
Do Reinforcement Learning Techniques Really Boost LLM Reasoning? A Deep Dive into Recent Models
DataFunTalk
DataFunTalk
Apr 25, 2025 · Artificial Intelligence

Does Reinforcement Learning Really Expand Reasoning Capacity in Large Language Models? Insights from Recent Empirical Study

Recent empirical research by Tsinghua’s LeapLab and Shanghai Jiao Tong University reveals that reinforcement‑learning‑based fine‑tuning (RLVR) improves sampling efficiency but does not extend the fundamental reasoning abilities of large language models beyond their base capabilities, as demonstrated across mathematics, code, and visual reasoning benchmarks.

AI researchRLVRReinforcement Learning
0 likes · 12 min read
Does Reinforcement Learning Really Expand Reasoning Capacity in Large Language Models? Insights from Recent Empirical Study
AI Frontier Lectures
AI Frontier Lectures
Apr 23, 2025 · Artificial Intelligence

Why Skipping the Thinking Step Makes Large Language Models More Accurate

UC Berkeley researchers found that forcing large language models to skip explicit reasoning—using a “NoThinking” mode—can achieve comparable or better accuracy with significantly fewer tokens, especially under token budget constraints, across math, coding, and theorem‑proving benchmarks.

NoThinkingreasoningtoken efficiency
0 likes · 7 min read
Why Skipping the Thinking Step Makes Large Language Models More Accurate
AntTech
AntTech
Apr 10, 2025 · Artificial Intelligence

Ant Group Presents Four AI Research Papers at ICLR 2025 Live Showcase

At the ICLR 2025 live session in Singapore, Ant Group showcased four cutting‑edge papers—CodePlan, Animate‑X, Group Position Embedding, and OmniKV—demonstrating advances in large‑language‑model reasoning, universal character animation, layout‑aware document understanding, and efficient long‑context inference.

AI researchMultimodaldocument understanding
0 likes · 6 min read
Ant Group Presents Four AI Research Papers at ICLR 2025 Live Showcase
Rare Earth Juejin Tech Community
Rare Earth Juejin Tech Community
Mar 24, 2025 · Artificial Intelligence

AI SDK 4.2 Release: New Reasoning, MCP Client, useChat Message Components, Image Generation, URL Sources, and Provider Updates

The AI SDK 4.2 release introduces powerful new features such as step‑by‑step reasoning support, a Model Context Protocol (MCP) client for tool integration, useChat message components, multimodal image generation, standardized URL sources, OpenAI Responses API support, Svelte 5 compatibility, and numerous middleware and provider enhancements, all illustrated with practical JavaScript/TypeScript examples.

AI SDKJavaScriptMCP
0 likes · 19 min read
AI SDK 4.2 Release: New Reasoning, MCP Client, useChat Message Components, Image Generation, URL Sources, and Provider Updates
Model Perspective
Model Perspective
Mar 21, 2025 · Artificial Intelligence

How DeepSeek’s Tree‑Based Reasoning Transforms AI Interaction

DeepSeek’s R1 inference mode replaces linear chain‑of‑thought with a transparent, multi‑path tree reasoning system, offering layered analysis, intent understanding, memory management, emotion detection, and hallucination mitigation, illustrated through a practical example of buying authentic cigarettes and detailed technical breakdowns.

Artificial IntelligenceMemoryhallucination
0 likes · 16 min read
How DeepSeek’s Tree‑Based Reasoning Transforms AI Interaction
AI Algorithm Path
AI Algorithm Path
Mar 11, 2025 · Artificial Intelligence

AI Agents Overview: Foundations, Core Components, and When to Use Them

This article provides a comprehensive overview of AI Agents, tracing their evolution from traditional chatbots to LLM‑driven agents, explaining core components such as perception, reasoning, action, knowledge bases, learning and communication interfaces, and discussing practical use cases, interaction cycles, and future prospects.

AI AgentsRetrieval-Augmented Generationautonomous systems
0 likes · 15 min read
AI Agents Overview: Foundations, Core Components, and When to Use Them
Architect
Architect
Mar 3, 2025 · Artificial Intelligence

Unlocking Reasoning LLMs: Methods, DeepSeek R1 Insights, and Cost‑Effective Strategies

This article examines how to build and improve reasoning‑capable large language models, explains the definition and use‑cases of reasoning models, details DeepSeek‑R1’s training pipeline, compares four key enhancement methods—including inference‑time scaling, pure RL, SFT + RL, and distillation—and offers budget‑friendly advice.

AI researchDeepSeekInference Scaling
0 likes · 27 min read
Unlocking Reasoning LLMs: Methods, DeepSeek R1 Insights, and Cost‑Effective Strategies
Java Tech Enthusiast
Java Tech Enthusiast
Feb 19, 2025 · Artificial Intelligence

xAI's Grok 3 Model: Benchmarks, Reasoning, and Industry Reactions

Elon Musk’s xAI introduced the Grok 3 family—trained on roughly 200,000 GPUs and offered in standard, mini and Reasoning versions—that claims top‑slot performance on math, science and coding benchmarks, outpacing Google Gemini, DeepSeek V3, Claude and OpenAI GPT‑4o, while pricing starts at $30 per month and drawing both praise for its speed and criticism for lingering hallucinations and ethical sensitivities.

AIBenchmarkDeepSearch
0 likes · 16 min read
xAI's Grok 3 Model: Benchmarks, Reasoning, and Industry Reactions
Cognitive Technology Team
Cognitive Technology Team
Feb 3, 2025 · Artificial Intelligence

DeepSeek R1 Introduces Group‑Related Policy Optimization for Advanced Reasoning in Large Language Models

DeepSeek AI’s new open‑source model DeepSeek‑R1 leverages a novel Group‑Related Policy Optimization (GRPO) reinforcement‑learning framework and multi‑stage training to dramatically boost complex reasoning performance, achieving AIME 2024 Pass@1 scores comparable to OpenAI’s o1 model.

AIDeepSeekGRPO
0 likes · 4 min read
DeepSeek R1 Introduces Group‑Related Policy Optimization for Advanced Reasoning in Large Language Models
Tencent Cloud Developer
Tencent Cloud Developer
Dec 5, 2024 · Industry Insights

Why Most RAG Projects Fail and How Tencent’s LeXiang AI Assistant Overcomes Them

The article analyses the rapid growth of Retrieval‑Augmented Generation (RAG) in enterprises, explains why self‑built RAG solutions often collapse under cost and maintenance pressures, and demonstrates how Tencent LeXiang AI Assistant addresses these issues through a robust knowledge‑management core, extensive industry experience, scalable resources, and advanced multimodal capabilities.

AI assistantEnterprise AIKnowledge Management
0 likes · 16 min read
Why Most RAG Projects Fail and How Tencent’s LeXiang AI Assistant Overcomes Them
Baobao Algorithm Notes
Baobao Algorithm Notes
Nov 24, 2024 · Artificial Intelligence

How Marco‑o1 Merges Chain‑of‑Thought Fine‑Tuning with Monte‑Carlo Tree Search for Superior Reasoning

The article introduces Marco‑o1, an open‑source LLM that enhances complex reasoning by fine‑tuning on Chain‑of‑Thought data, integrating Monte‑Carlo Tree Search, introducing mini‑step actions and a reflection mechanism, and evaluates its performance on multilingual math and translation benchmarks.

Artificial IntelligenceLLMMonte Carlo Tree Search
0 likes · 15 min read
How Marco‑o1 Merges Chain‑of‑Thought Fine‑Tuning with Monte‑Carlo Tree Search for Superior Reasoning
CSS Magic
CSS Magic
Sep 14, 2024 · Artificial Intelligence

Why OpenAI’s New o1 Model Outperforms Its Rivals

The article examines OpenAI’s newly released o1 model, highlighting its superior performance in complex reasoning tasks such as math, programming, and science, and explains how model‑level chain‑of‑thought optimization and product‑level UI design give it an edge over competitors like Claude.

AI evaluationChatGPTOpenAI
0 likes · 8 min read
Why OpenAI’s New o1 Model Outperforms Its Rivals
Data Thinking Notes
Data Thinking Notes
Sep 13, 2024 · Artificial Intelligence

How OpenAI’s o1 Series Redefines Complex Reasoning and AI Safety

OpenAI’s new o1 series, including o1‑preview and o1‑mini, leverages reinforcement‑learning‑based chain‑of‑thought reasoning to achieve superior performance on academic exams, coding contests, and safety benchmarks, offering faster, cost‑effective options while advancing AI alignment and human‑preference evaluation.

AI safetyBenchmarkCoding
0 likes · 15 min read
How OpenAI’s o1 Series Redefines Complex Reasoning and AI Safety
DataFunSummit
DataFunSummit
Jul 16, 2024 · Artificial Intelligence

Knowledge Graph Construction, Reasoning, and QA for Intelligent Hypertension Diagnosis

This article presents a comprehensive exploration of knowledge‑graph‑based modeling, neural‑symbolic multi‑hop reasoning, and large‑model‑driven question answering applied to precise medication decision‑making in hypertension, detailing system architecture, experimental evaluations, real‑world deployments, and future research directions.

Medical AIhypertensionknowledge graph
0 likes · 26 min read
Knowledge Graph Construction, Reasoning, and QA for Intelligent Hypertension Diagnosis
Alibaba Cloud Big Data AI Platform
Alibaba Cloud Big Data AI Platform
Dec 7, 2023 · Artificial Intelligence

How Alibaba Cloud’s PAI Breakthroughs Are Shaping AI at EMNLP 2023

Alibaba Cloud’s AI platform PAI had four papers accepted at EMNLP 2023, presenting advances in automatic prompt engineering for text‑to‑image, domain‑specific knowledge‑enhanced language models, cognitive‑tree reasoning with small LLMs, and cross‑lingual machine reading comprehension, all demonstrating cutting‑edge AI research and product integration.

Artificial Intelligenceknowledge graphsprompt engineering
0 likes · 9 min read
How Alibaba Cloud’s PAI Breakthroughs Are Shaping AI at EMNLP 2023
DataFunTalk
DataFunTalk
Nov 2, 2023 · Artificial Intelligence

Enhancing Language and Vision Models with External Knowledge and Tools: OREO‑LM, REVEAL, and AVIS

This article reviews recent research on augmenting language and multimodal models with external knowledge sources and tool‑calling mechanisms, covering three systems—OREO‑LM for knowledge‑graph reasoning, REVEAL for multi‑source visual‑language pretraining, and AVIS for dynamic tool selection—and their experimental results and implications.

Multimodalknowledge graphlanguage model
0 likes · 28 min read
Enhancing Language and Vision Models with External Knowledge and Tools: OREO‑LM, REVEAL, and AVIS
Baidu Geek Talk
Baidu Geek Talk
May 8, 2023 · Artificial Intelligence

Augmented Language Models: Reasoning and External Tool Utilization

The survey shows that once language models exceed roughly ten billion parameters they spontaneously acquire two complementary abilities—step‑by‑step reasoning, often elicited by chain‑of‑thought prompts or scratch‑pad training, and the capacity to invoke external tools such as search engines, calculators, or robots—enabling them to retrieve up‑to‑date information, perform complex computations, and act in the world, thereby advancing toward general artificial intelligence.

AIRetrieval Augmentationprompt engineering
0 likes · 20 min read
Augmented Language Models: Reasoning and External Tool Utilization
DataFunTalk
DataFunTalk
May 2, 2022 · Artificial Intelligence

RNNLogic: Learning Logic Rules for Knowledge Graph Reasoning

This article reviews recent advances in knowledge graph reasoning, introduces the RNNLogic framework that jointly learns a rule‑generating LSTM and a stochastic logic programming predictor, and demonstrates its competitive performance and interpretability on benchmark datasets while outlining future neural‑symbolic directions.

AIRNNLogicknowledge graph
0 likes · 10 min read
RNNLogic: Learning Logic Rules for Knowledge Graph Reasoning
DataFunTalk
DataFunTalk
May 15, 2021 · Artificial Intelligence

Knowledge Graph Course Syllabus Overview

This teaching plan outlines a comprehensive Knowledge Graph course covering fundamentals, representation, storage, extraction, reasoning, fusion, question answering, graph algorithms, and emerging technologies across nine detailed chapters, including language integration, ontology matching, and multimodal extensions.

Artificial IntelligenceGraph Algorithmscourse syllabus
0 likes · 4 min read
Knowledge Graph Course Syllabus Overview
DataFunTalk
DataFunTalk
Nov 7, 2020 · Artificial Intelligence

Knowledge Graph Reasoning: Deductive, Inductive, and Embedding‑Based Methods

This article surveys knowledge‑graph reasoning, explaining deductive and inductive reasoning fundamentals, description‑logic and logic‑programming approaches, and modern embedding techniques such as TransE, TransH, TransR and TransD, while highlighting their theoretical bases, practical implementations and recent research progress.

AIDescription Logicdeductive reasoning
0 likes · 13 min read
Knowledge Graph Reasoning: Deductive, Inductive, and Embedding‑Based Methods
Ctrip Technology
Ctrip Technology
Jul 29, 2016 · Artificial Intelligence

Reasoning Techniques in Knowledge Graphs and Their Application to a High‑School Exam Robot

The talk reviews the history and concepts of knowledge graphs, explains logical and statistical reasoning methods—including rule‑based and representation‑learning approaches—and demonstrates how these techniques can be applied to build an intelligent robot that assists students in solving high‑school exam problems.

Semantic Webexam robotknowledge graph
0 likes · 5 min read
Reasoning Techniques in Knowledge Graphs and Their Application to a High‑School Exam Robot