LLM agents accumulate valuable task-specific information through their actions, observations, and environmental feedback during multi-turn task execution. When effectively used, this information can help agents refine subsequent decisions and improve task performance. However, the learning value of an interaction depen...
Kang-Cong Li, Hang-Fan Zhang, Shu-Yue Hu et al.· 0 citations
In this report, we introduce Sage-A1.5, a 35B Mixture-of-Experts agentic model that builds on A1 to advance long-horizon problem solving through adaptive capability composition. Compared with A1, Sage-A1.5 learns not only to solve individual tasks, but also to organize work and revise its approach during execution. Sag...
Wenjie Lou, Tian-Shuo Peng, Shi-Yang Feng et al.· 0 citations
StraTA is a simple framework that introduces an explicit trajectory-level strategy into agentic reinforcement learning (RL) and trains strategy generation and action execution jointly with a hierarchical GRPO-style rollout design, further enhanced by diverse strategy rollout and critical self-judgment.
Xiangyuan Xue, Yifan Zhou, Zidong Wang et al.· arXiv.org· 1 citation
This work introduces a student reference KL loss and mask the advantages of special termination tokens to mitigate the problem of excessive generation length and frequent truncation, and improves on science benchmarks such as HLE and HiPhO, suggesting that OPD transfers reasoning capabilities that generalize beyond the...
Hao-Nan He, Hao Lei, Yun Luo et al.· 5 citations· ⚡1
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.