Author

PaperAgent

Daily updates, analyzing cutting-edge AI research papers

302

Articles

Likes

1.8k

Views

Comments

Latest from PaperAgent

100 recent articles max

PaperAgent

Jul 15, 2026 · Artificial Intelligence

Surprising Discovery: A Chinese embodied‑AI company solves the distributed Muon bottleneck

The article analyzes how the Muon optimizer, adopted by DeepSeek‑V4 and Kimi‑K2, suffers a 2.2× overhead in distributed training, and how the DMuon system from Zibian Robot reduces that overhead to near‑AdamW levels, achieving up to 97.4× speedup and only 2% slower end‑to‑end training than AdamW.

DMuonDistributed TrainingGPU Optimization

0 likes · 11 min read

Surprising Discovery: A Chinese embodied‑AI company solves the distributed Muon bottleneck

PaperAgent

Jul 13, 2026 · Artificial Intelligence

What Three Days of Reproducing an ACL 2026 Paper Revealed About SFT Failures

Reproducing the ACL 2026 paper on Incomplete Learning Phenomenon shows that about 15.3% of SFT training samples remain unlearned despite low loss, and the authors' Multiple‑Choice conversion with pass@5 detection uncovers five root causes and effective remediation strategies.

ILPKnowledge gapsLLM evaluation

0 likes · 13 min read

What Three Days of Reproducing an ACL 2026 Paper Revealed About SFT Failures

PaperAgent

Jul 12, 2026 · Artificial Intelligence

Anthropic’s Official Loop Engineering Guide Revealed

Anthropic’s newly published Loop Engineering guide organizes existing agent capabilities into a structured framework, defining four loop types—turn‑based, goal‑based, time‑based, and proactive—and explains how to design reliable triggers, verification steps, stop conditions, and cost‑control measures for autonomous AI workflows.

AI AgentsAnthropicAutomation

0 likes · 11 min read

Anthropic’s Official Loop Engineering Guide Revealed

PaperAgent

Jul 12, 2026 · Artificial Intelligence

Three Must-Have Skills Unlock GPT‑5.6’s Super‑Human Performance

The author tests GPT‑5.6 with three custom skills—Anthropic’s frontend‑design, the guizang‑ppt skill, and DeepSeek’s Deli_AutoResearch framework—showing token savings, superior design judgment, automated Swiss‑style PPT generation, and a zero‑interaction autonomous agent that logs its own progress and pivots.

AI designGPT-5.6Skill

0 likes · 7 min read

Three Must-Have Skills Unlock GPT‑5.6’s Super‑Human Performance

PaperAgent

Jul 11, 2026 · Artificial Intelligence

A Systematic Overview of Harness Engineering for AI Self‑Improvement

The article presents a detailed technical survey of Harness Engineering, explaining how it extends classic agent architectures with workflow design, persistent state, and sub‑agent orchestration, and traces its evolution through ACE, MCE, and Meta‑Harness as a practical pathway toward recursive self‑improvement.

AI AgentsContext ManagementHarness Engineering

0 likes · 12 min read

A Systematic Overview of Harness Engineering for AI Self‑Improvement

PaperAgent

Jul 11, 2026 · Artificial Intelligence

Two Supercharged Diagram Skills That Make DeepSeek Unbelievably Powerful

The author compares two AI‑powered diagram skills—fireworks‑tech‑graph and architecture‑diagram‑generator—showing how they turn Chinese prompts into polished SVG or HTML diagrams with multiple styles, interactive controls, and seamless integration, dramatically simplifying architecture visualization.

AI diagram generationDeepSeekHTML

0 likes · 7 min read

Two Supercharged Diagram Skills That Make DeepSeek Unbelievably Powerful

PaperAgent

Jul 10, 2026 · Artificial Intelligence

A Deep Dive into QC‑MHM: Boosting Accuracy in Temporal Knowledge Graph Question Answering

The article analyzes the challenges of temporal KGQA, explains why prior models miss time constraints and multi‑hop reasoning, details the four‑module QC‑MHM framework that integrates time‑aware embeddings, question calibration, multi‑hop modeling, and dual‑channel answer prediction, and shows its state‑of‑the‑art performance and interpretability on benchmark datasets.

AAAI 2024Knowledge GraphMulti-hop Reasoning

0 likes · 9 min read

A Deep Dive into QC‑MHM: Boosting Accuracy in Temporal Knowledge Graph Question Answering

PaperAgent

Jul 9, 2026 · Artificial Intelligence

A New Paradigm for LLM Reward Modeling: Mixing Huber and Hinge Losses in E‑GRM

The article analyzes the E‑GRM framework's need for both accurate score regression and stable ranking signals, proposes a weighted combination of Huber and hinge losses, and demonstrates through extensive ablations and downstream GRPO experiments that the mixed loss yields superior calibration, ranking, and policy‑learning performance.

E‑GRMHinge LossHuber Loss

0 likes · 10 min read

A New Paradigm for LLM Reward Modeling: Mixing Huber and Hinge Losses in E‑GRM

PaperAgent

Jul 9, 2026 · Artificial Intelligence

Microsoft Unveils Two AI‑Powered Research Automation Papers

Microsoft Research recently released two papers—ResearchStudio‑Idea and ResearchStudio‑Reel—that introduce a skill‑based framework for AI‑driven research automation, tackling the challenges of generating novel, evidence‑grounded ideas and producing editable posters, videos, and bilingual blogs, with benchmark results that surpass human authors and existing tools.

AI research automationIdeaSparkLLM

0 likes · 13 min read

Microsoft Unveils Two AI‑Powered Research Automation Papers

PaperAgent

Jul 8, 2026 · Artificial Intelligence

Why Agent Skills Need Self‑Evolution: A Survey of 19 Frameworks and 10 Benchmarks

This survey from Rutgers and UNC Charlotte systematically reviews 19 agent‑skill evolution methods and 10 evaluation benchmarks, revealing critical gaps such as the lack of longitudinal tracking, binary pass/fail metrics, and one‑time security checks, and highlighting how separating diagnosis from rewrite improves cross‑task performance.

AgentEvaluationbenchmark

0 likes · 9 min read

Why Agent Skills Need Self‑Evolution: A Survey of 19 Frameworks and 10 Benchmarks