DeepResearch
PulseAugur coverage of DeepResearch — every cluster mentioning DeepResearch across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
Open-source DeepResearch hits 55.15% on GAIA validation
The open-source DeepResearch project has achieved a 55.15% score on the GAIA validation benchmark, an improvement from its previous 46% score. Notably, its code agents demonstrated superior performance compared to JSON …
-
New RewardFlow method enhances LLM agentic reasoning with dense rewards
Researchers have developed RewardFlow, a novel method for estimating state-level rewards in agentic reinforcement learning with large language models. This approach constructs state graphs to capture trajectory topology…
-
Baidu's DuMate AI agent tops PinchBench, DeepResearch rankings
Baidu's DuMate has achieved the top position on the PinchBench benchmark for intelligent agents, securing three spots within the top five. The AI assistant also ranked first on the DeepResearch leaderboard. This news co…