The Flow has not summarised this story yet — read it at arXiv Machine Learning.
AHEAD is a step‑aware framework that augments reinforcement learning for multi‑turn LLM agents by matching different supervision sources to different step types. The teacher receives environment feedback on all steps and LLM‑generated corrective hints only on error steps, providing finer‑grained guidance than uniform trajectory‑level rewards. Across ALFWorld, WebShop, and Search‑based QA, AHEAD improves task success by 13.3 points on ALFWorld and 11.0 on WebShop at 7B, reaches target success rates faster, and solves tasks within tighter interaction budgets compared to outcome‑only RL and prior self‑distillation baselines.
arXiv:2610.16523v1 Announce Type: new Abstract: Training LLM agents to interact with users over multiple turns is challenging because the learning signal depends not only on the agent, but also on th...
arXiv:2606. 02355v1 Announce Type: new Abstract: Long-horizon LLM agents can benefit from reusable skills, yet existing skill-based methods often rely on external skill generators during training or persistent skill retrieval at inference, increasing engineering complexity, context length, and deployment latency.
The paper introduces CoPE, a method that trains language agents by adding multi‑step action targets to the policy backbone. By supervising each action forecasted from preceding histories, CoPE enables acting and forecasting to co‑evolve without extra inference cost. Across five benchmarks, CoPE outperforms existing RL baselines, achieving up to twice the sample efficiency on ScienceWorld and improving overall performance on realistic applications.
arXiv:2607. 14004v1 Announce Type: new Abstract: Most reported gains from agent-optimization methods are one-shot: an agent is optimized against a fixed benchmark and the resulting improvement is reported as if it were a stable property of the method.
arXiv:2608. 07371v1 Announce Type: new Abstract: Recent agentic reinforcement learning methods use hindsight to complement sparse outcome rewards.