Large Language Models (LLMs) are prone to generating hallucinated content, which compromises their reliability in knowledge-intensive tasks. To address this challenge without sacrificing creativity, we propose HARPO, a reinforcement learning framework designed to jointly optimize faithfulness and creativity. HARPO inco...
Tie-Zheng Yu, Yu-Xin Jiang, Jin-Peng Li et al.· 0 citations
On-policy Verbal Distillation is introduced, a framework that uses verbal scores from black-box teachers to rank student-generated sub-trajectories, retaining high-scoring ones and replacing low-scoring ones with teacher-generated continuations and suggests that retaining student-generated prefixes helps preserve explo...
Jing Xiong, Hui Shen, Shansan Gong et al.· arXiv.org· 8 citations
LLM agents resend their whole conversation on every turn, and most of it was already processed on the previous turn. Serving systems avoid recomputing it by caching its key-value (KV) state and, when GPU memory runs out, by offloading that state to host memory. For agents, offloading gives inconsistent results: on the...
Kun-Ming Shao, Jie-Run Chen, Jiang-Nan Yu et al.· 0 citations
Experiments show that agentic review continuously improves PRs through a generate-review-revise loop, outperforms single-turn fixed-context review in both decision accuracy and resolve rate after revision, transfers beyond review to improve issue-resolution models, and enables effective and efficient test-time scaling.
Ruoyu Wang, Jierun Chen, Shaowei Wang et al.· arXiv.org· 4 citations
This work presents OptiMAS, a task-agnostic agentic optimizer that leverages textual interaction trajectories and task feedback as loss signals for end-to-end MAS evolution and sustains performance improvement over extended optimization horizons.
Yuxin Cheng, Chang Liu, Hanxin Yu et al.· 0 citations
Reinforcement learning for coding agents increasingly relies on long-running agent harnesses to manage tool integration, repository contexts, and execution feedback. However, the native execution environments of these harnesses are inherently misaligned with policy-gradient training: environmental crashes and reward ha...
Yi-Ming Du, Yu-Xin Jiang, Tao Yuan et al.· 3 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
