9 papers
SWE-Touch: Benchmarking Coding Agents When Users Touch the Code
Yuqiao Tan, Jinxiang Meng, Fangyu Lei +4
Real-world software development requires coding agents to operate in shared workspaces where users may inspect and modify code during an ongoing task, yet existing repository-level…
Mitigating the Safety-utility Trade-off in LLM Alignment via Adaptive Safe Context Learning
Yanbo Wang, Minzheng Wang, Jian Liang +3
While reasoning models have achieved remarkable success in complex reasoning tasks, their increasing power necessitates stringent safety measures. For safety alignment, the core ch…
Bottom-up Policy Optimization: Your Language Model Policy Secretly Contains Internal Policies
Yuqiao Tan, Minzheng Wang, Shizhu He +6
Existing reinforcement learning (RL) approaches treat large language models (LLMs) as a unified policy, overlooking their internal mechanisms. In this paper, we decompose the LLM-b…
Breaking the Impasse: Dual-Scale Evolutionary Policy Training for Social Language Agents
Minzheng Wang, Run Luo, Yanbo Wang +6
While Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for closed-ended tasks, extending it to open-ended social language games via self-play reveals a cr…
From to : Investigating Reinforcement Learning in Pre-train Space
Yuqiao Tan, Minzheng Wang, Bo Liu +5
While reinforcement learning with verifiable rewards (RLVR) significantly enhances LLM reasoning by optimizing the conditional distribution P(y|x), its potential is fundamentally b…
Adaptive Social Learning via Mode Policy Optimization for Language Agents
Minzheng Wang, Yongbin Li, Haobo Wang +6
Effective social intelligence simulation requires language agents to dynamically adjust reasoning depth, a capability notably absent in current studies. Existing methods either lac…