12 papers
Agent Skills Can Be Harmful: An Empirical Study of Skill-Induced Failures in LLM Agents
Gen Dong, Yanjie Gao, Liqun Li +3
Agent skills are the de facto mechanism for extending LLM agents with reusable guidance. A skill can shape the agent's task execution, including planning, tool use, problem-solving…
SkillReason: Reasoning-Enhanced Agent Skill Retrieval for Implicit User Requests
Donghong Jiang, Endian Lin, Luoping Cui +6
Large language model agents increasingly rely on reusable skills to extend their capabilities beyond parametric knowl- edge. However, retrieving the appropriate skill from a large-…
MagicSelector: Joint Optimization for Agent Tool Selection via Counterfactual Decomposition and Progressive Reranking
HONOR Agentic Search Team, Zhengzong Chen, Lei Tang +27
We present MagicSelector, a joint optimization framework integrating Counterfactual task decomposition, Progressive reranking, and Dynamic Top-K, designed to address the fundamenta…
MathScape: Benchmarking Multimodal Large Language Models in Real-World Mathematical Contexts
Hao Liang, Linzhuang Sun, Minxuan Zhou +7
With the rapid progress of Multimodal LLMs, evaluating their mathematical reasoning capabilities has become an increasingly important research direction. In particular, visual-text…
ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning
Mingyang Chen, Linzhuang Sun, Tianpeng Li +10
Large Language Models (LLMs) have shown remarkable capabilities in reasoning, exemplified by the success of OpenAI-o1 and DeepSeek-R1. However, integrating reasoning with external…
Baichuan-M2: Scaling Medical Capability with Large Verifier System
M2 Team, Chengfeng Dou, Chong Liu +31
As large language models (LLMs) advance in conversational and reasoning capabilities, their practical application in healthcare has become a critical research focus. However, there…