BrowseComp-Plus
A benchmark for evaluating deep research capabilities of AI agents on complex information retrieval and synthesis tasks. It serves as an extended version of BrowseComp, targeting more demanding scenarios that require multi-step search and comprehensive analytical reasoning.
Timeline (last 90 days)
On BrowseComp-Plus, attribution-guided SFT matches the effect of full-turn exact-context SFT using only about 30% of the training tokens.
On BrowseComp-Plus, attribution-guided PPO is 4.1 percentage points higher than PPO using only outcome rewards.
BrowseComp-Plus is a controlled version of BrowseComp that uses a fixed corpus instead of the live web to eliminate evaluation noise caused by network fluctuations and page changes.
On the BrowseComp-Plus benchmark, CLM paired with Qwen3 27B achieves 59.4%, approximately 11% higher than the best summarization solution, with about one-fifth less computation.
All Facts (4)
On BrowseComp-Plus, attribution-guided SFT matches the effect of full-turn exact-context SFT using only about 30% of the training tokens.
50%UnverifiedOn BrowseComp-Plus, attribution-guided PPO is 4.1 percentage points higher than PPO using only outcome rewards.
50%UnverifiedBrowseComp-Plus is a controlled version of BrowseComp that uses a fixed corpus instead of the live web to eliminate evaluation noise caused by network fluctuations and page changes.
50%UnverifiedOn the BrowseComp-Plus benchmark, CLM paired with Qwen3 27B achieves 59.4%, approximately 11% higher than the best summarization solution, with about one-fifth less computation.
50%