Home / AI Research / Evidence-Based Credit Assignment for Search-Augmented Language Models
EVAI Research
Evidence-Based Credit Assignment for Search-Augmented Language Models
by tencent · Wen Wang, Jindong Wang, Jiahua Bao, Tu Yongsiqi, Yihao Liu, Junwei He
Reinforcement learning from terminal answer rewards enables search-augmented language models to interleave reasoning and retrieval without step-level annotations, yet outcome supervision assigns identical credit to every search in a trajectory regardless of whether it retrieved useful information. This limitation is especially severe when all sampled rollouts for a question fail, collapsing group-centered outcome advantages to zero even when trajectories gather markedly different evidence. We present Evidence-based Credit Assignment (ECA), which augments terminal outcome rewards with a training-only auxiliary signal measuring how retrieved documents improve the likelihood of a reference…
Upvotes7
Comments4
Published17 Nov 2026