1 citations · 1 across the 3 of their papers we have counts for
5 papers
PEARL: Process-Experience Aware Reinforcement Learning for Multi-Turn Agents
Jie Yang, Mianqiu Huang, Yiwei Zhao +3
Terminal rewards make multi-turn agents trainable without step-level annotations, but group-relative advantages provide little guidance about which intermediate decisions to adjust…
Two-Stage Reinforcement Learning for Sound and Adversarial Test Generation in Code LLMs
Jiacheng Xu, Wentao Zhang, Zhiyi Lyu +4
Reinforcement learning (RL) has substantially advanced code generation with large language models (LLMs) through executable feedback. The feedback for coding problems mainly comes…
SkillNet: Create, Evaluate, and Connect AI Skills
Yuan Liang, Ruobin Zhong, Haoming Xu +47
Current AI agents can flexibly invoke tools and execute complex tasks, yet their long-term advancement is hindered by the lack of systematic accumulation and transfer of skills. Wi…
AgentOrchestra: Orchestrating Multi-Agent Intelligence with the Tool-Environment-Agent(TEA) Protocol
Wentao Zhang, Liang Zeng, Yuzhen Xiao +7
Recent advances in LLM-based agent systems have shown promise on complex, long-horizon tasks, but existing agent protocols (e.g., A2A and MCP) do not adequately support lifecycle-a…
Incentivizing LLMs to Self-Verify Their Answers
Fuxiang Zhang, Jiacheng Xu, Chaojie Wang +3
Large Language Models (LLMs) have demonstrated remarkable progress in complex reasoning tasks through both post-training and test-time scaling laws. While prevalent test-time scali…