activity
20242026
most citedAgent models: Internalizing Chain-of-Action Generation into Reasoning models

1 citations · 1 across the 4 of their papers we have counts for

collaborators
Showing 2026Show all

1 paper · 1 filter

cs.AI2026

Evaluate-as-Action: Self-Evaluated Process Rewards for Retrieval-Augmented Agents

Jiangming Shu, Yuxiang Zhang, Ye Ma +2

Retrieval-augmented agents can query external evidence, yet their reliability in multi-step reasoning remains limited: noisy retrieval may derail multi-hop question answering, whil…