conftrace_

deep search agent

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

citation-aware reward (1) evidence chain (1) multi-hop query (1) group relative policy optimization (1) retrieval-augmented generation (1) evaluation benchmark (1) information retrieval (1) reinforcement learning (1)

Papers

BrowseComp-Plus: A Fair and Disentangled Evaluation Benchmark for Deep Search Agents ACL 2026 Chaining the Evidence: Robust Reinforcement Learning for Deep Search Agents with Citation-Aware Rubric Rewards ACL 2026