6 papers
Agents' Last Exam
Yiyou Sun, Xinyang Han, Weichen Zhang +306
Recent AI systems have achieved strong results on a wide range of benchmarks, yet these gains have not translated into economically meaningful deployment across many professional d…
What Should Agents Say? Action-state Communication for Efficient Multi-Agent Systems
Chen Huang, Yuhao Wu, Wenxuan Zhang
Multi-agent systems (MAS) built on large language models are typically organized around roles, pipelines, and turn schedules, while the content that agents pass to one another is o…
Diagnosing Harmful Continuation in Answer-Correct Long-CoT Training Traces
Chen He, Yuhao Wu, Lei Wang +2
Long chain-of-thought (CoT) traces are widely used as supervision for reasoning-oriented LLM SFT, yet answer-correct traces can still lead to markedly different fine-tuning outcome…
GeoFaith: A Spatio-Temporal Dual View of Faithful Chain-of-Thought
Weijiang Lv, Wentong Zhao, Jiayu Wang +3
Chain-of-Thought (CoT) reasoning has advanced large language models (LLMs), but outcome-based supervision leads to pervasive post-hoc rationalization, producing plausible yet unfai…
Balanced Aggregation: Understanding and Fixing Aggregation Bias in GRPO
Zhiyuan Zeng, Jiameng Huang, Zhangyue Yin +8
Reinforcement learning with verifiable rewards (RLVR) has become a central paradigm for improving reasoning and code generation in large language models, and GRPO-style training is…
NOTAM-Evolve: A Knowledge-Guided Self-Evolving Optimization Framework with LLMs for NOTAM Interpretation
Maoqi Liu, Quan Fang, Yuhao Wu +3
Accurate interpretation of Notices to Airmen (NOTAMs) is critical for aviation safety, yet their condensed and cryptic language poses significant challenges to both manual and auto…