collaborators

8 papers

cs.AI2026

Fisher-R1: Training LLM Agents for Reliable Hypothesis Testing

Jiacheng Miao, Jin Mu, Guanhua Chen +1

Reliable hypothesis testing is the foundation of many empirical scientific claims. Large language model (LLM) agents are increasingly used to automate this process, as they can ins…

cs.CR2026

"Allow" to Achieve, Over-Privileged Inadvertently: The Unintended Cost of Task-Completion-Driven Pop-up Decisions in Mobile GUI Agents

Dongsheng Chen, Yuxuan Li, Guanhua Chen +5

Mobile GUI agents routinely encounter system permission dialogs during task execution, yet their ability to grant only permissions that are necessary for the delegated task remains…

cs.LG2026

Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs

Lecheng Yan, Ruizhe Li, Guanhua Chen +5

Reinforcement Learning with Verifiable Rewards (RLVR) is highly effective for enhancing LLM reasoning, yet recent evidence shows models like Qwen 2.5 achieve significant gains even…

cs.AI2026

No More Stale Feedback: Co-Evolving Critics for Open-World Agent Learning

Zhicong Li, Lingjie Jiang, Yulan Hu +7

Critique-guided reinforcement learning (RL) has emerged as a powerful paradigm for training LLM agents by augmenting sparse outcome rewards with natural-language feedback. However,…

cs.AI2026

From Abstract to Contextual: What LLMs Still Cannot Do in Mathematics

Bowen Cao, Dongdong Zhang, Yixia Li +8

Large language models now solve many benchmark math problems at near-expert levels, yet this progress has not fully translated into reliable performance in real-world applications.…

cs.AI2026

Rethinking the Role of Entropy in Optimizing Tool-Use Behaviors for Large Language Model Agents

Zeping Li, Hongru Wang, Yiwen Zhao +7

Tool-using agents based on Large Language Models (LLMs) excel in tasks such as mathematical reasoning and multi-hop question answering. However, in long trajectories, agents often…