Agentic reinforcement learning

Technique · Training · 1 item since Aug 2026

Training agents with RL over multi-turn interactions with tools and environments.

Techniques: Self-distillation

Trends

Agents improve themselves through skills, harnesses, and memory

Items

Aug 28
AHEAD adds step-aware hints to agentic RL
A self-distillation method for multi-turn agentic RL that gives environment feedback on every step and LLM-generated corrective hints only on error steps, a minimal change to GRPO worth +13.3 on ALFWorld and +11.0 on WebShop at 7B with no inference overhead.