KnowGPO: Knowledge-Grouped Policy Optimization for Search Agents
[Sztuczna inteligencja] Autorzy: Siqi Chen, Zhengxi Lu, Yuchen Yan i 10 więcej
Deep search agents solve knowledge-intensive tasks through long-horizon, multi-turn interactions, where assigning credit to individual search decisions is fundamentally difficult. Outcome-based reinforcement learning provides only a single terminal reward shared across an entire trajectory. Recent process-supervision methods aim to assign credit at finer granularity, but they typically anchor credit to either surface-level trajectory states or model-internal signals, both of which become unreliable in deep search where observations are heterogeneous and retrieved contexts are long and noisy. We propose KnowGPO, a reinforcement learning framework that aligns trajectories by the task-relevant knowledge they have acquired rather than by their surface observations. For each query, KnowGPO decomposes the information required to derive the answer into atomic knowledge conditions, and represen…
- Kategoria arxiv
- cs.AI
- Kategoria
- Sztuczna inteligencja