RefineRL introduces Skeptical-Agent, an iterative self-refinement agent equipped with local execution tools to validate generated solutions against public test cases of CP problems and highlights self-refinement as a promising direction for scaling LLMs' general reasoning ability.
Shaopeng Fu, Xingxing Zhang, Li Dong et al.· arXiv.org· 1 citation
Automated red teaming often replays a fixed set of prompts, which measures known risks but cannot learn from failures found during testing. We present CART (Closed-Loop Adaptive Red Teaming), a framework that uses each result to guide what it tests next. CART begins with broad risk coverage, follows weaknesses that eme...
Dong-Dong Zhang, Teng-Chao Lv, Yi-Ling Jia et al.· 0 citations
The number of agents is revealed as a new scaling dimension for multi-agent organizations to expand the frontier of general intelligence, offering a practical solution for complex tasks under hard latency constraints or time budgets.
Zhi-Hao Zhan, Ting Song, Li Dong et al.· 1 citation
This work proposes Learning to Coach (L2C), a framework that trains a dedicated LLM-as-a-Coach to extract actionable experiential knowledge from an actor model's previous trajectory, and studies two such rewards: a same-instance reward, which improves subsequent responses on the original problem, and a cross-instance r...
Guan-Heng Chen, Tian-Zhu Ye, Li Dong et al.· 0 citations
ReOPD turns expensive agent-environment interaction into a reusable offline resource, enabling scalable distillation across tools, tasks, and environments and preserves or improves OPD-level accuracy, uses zero tool calls during student training, and is at least 4$\times faster per rollout than OPD.
Baohao Liao, Hanze Dong, C. Monz et al.· arXiv.org· 7 citations· ⚡1
Experiential Learning is proposed, which repurposes the feedback model from an LLM-as-a-Judge into an LLM-as-a-Coach, and establishes experiential knowledge as a richer and more generalizable learning signal for post-training on non-verifiable tasks.
Tianzhu Ye, Li Dong, Guanheng Chen et al.· arXiv.org· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
