We have 5 of 21 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
The results support OPD as preparation for RL and favor forward KL when OPD is followed by RL in the authors' comparison, which highlights the importance of both objective choice and the states receiving supervision for subsequent RL.
SearchMaster is presented, a self-play framework that trains a single LLM from search tasks it generates, solves, and verifies in a local search environment, showing that grounded and regulated self-play can provide effective search-agent training data without human-labeled QA pairs or expert demonstrations.
A benchmark that evaluates whether LLM auditors can localize, attribute, and repair search-agent failures through evidence-grounded adjudication, and proposes SearchAuditor, a multi-perspective auditing framework that effectively localizes, attributes, and repairs search-agent failures through evidence-grounded adjudic...
This work proposes OrthoSkillVLA, a parameter-efficient framework for continual skill learning in pretrained VLA models without demonstration replay, and introduces a lightweight feature-aware MoE decoder that better preserves prior skills while acquiring new ones.
FailForge is proposed, an agentic framework that converts failed rollouts into training signal, and recovers over 26% of previously failed instances at marginal additional cost, and training Qwen3.5-4B on the augmented corpus improves the SWE-bench Verified resolve rate by 6.6 points over a strong RFT baseline.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
