Post by Jiang Yulun

Name: Meta-RL Induces Exploration in Language Agents Exploration is essential for LLM agents, but how can
Uploaded: 2025-12-22T10:00:21.770Z
Channel: Jiang Yulun
Description: Meta-RL Induces Exploration in Language Agents Exploration is essential for LLM agents, but how can we train an agent that actively explores? Introducing 🌊LaMer, a general Meta-RL framework that en

就读于洛桑

Meta-RL Induces Exploration in Language Agents Exploration is essential for LLM agents, but how can we train an agent that actively explores? Introducing 🌊LaMer, a general Meta-RL framework that enables LLM agents to explore and learn from the environment feedback at test time. Key idea: (i) Cross-episode training to encourage exploration and long-term reward optimization (ii) In-context policy adaptation via self-reflection, allowing agents to update behavior from feedback without gradient updates LaMer trains the agents to explore in the early episodes and adapt to the environment in the subsequent episodes, leading to: (i) More diverse trajectories of trained agents compared to RL baselines (ii) Stronger performance and test-time scaling (iii) Better generalization to hard or out-of-distribution tasks 📄Paper: https://lnkd.in/eKD63K4E 💻Code: https://lnkd.in/eW9qBDSx Had fun collaborating with Liangze Jiang and his advisor Damien Teney, and huge thanks to my amazing advisors @Maria Brbic and Michael Moor

Video Content