BrowseComp-ZH
PulseAugur coverage of BrowseComp-ZH — every cluster mentioning BrowseComp-ZH across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
Open-source Iris search agent challenges closed-source rivals with advanced context management
AllSpark Research has launched Iris, an open-source search agent that challenges closed-source competitors. Iris utilizes a Mixture-of-Experts architecture and features a 256K context window, with models available under…
-
Iris search agents achieve SOTA open-source results on web benchmarks · 2 sources tracked
Researchers have developed two large-scale search agents, Iris-mini and Iris-pro, trained at 35B and 397B parameters respectively. These agents utilize a novel data pipeline and training methodology that combines superv…
-
G-ReAct framework enhances LLM deep search with graph-guided reasoning
Researchers have introduced G-ReAct, a novel framework designed to enhance deep search capabilities in large language models. This approach structures reasoning as state evolution over a query graph, allowing for explic…
-
New research enhances AI agent memory, reasoning, and grounding
Researchers are developing advanced methods for AI agents to effectively utilize long-term memory and improve their reasoning capabilities. One approach, Query-Conditioned Reuse (QCR), focuses on how agents can adapt pa…
-
New credit assignment methods enhance AI search agent training · 3 sources tracked
Researchers have developed new methods for training long-horizon search agents, which are AI systems designed to perform complex, multi-step tasks. One approach, ABSeeker, uses Answer-Backtracked Credit Assignment (ABC)…
-
New STAMP method improves credit assignment for deep search agents
Researchers have introduced STAMP, a novel method for improving credit assignment in deep search agents. This approach addresses the 'reward-credit mismatch' by providing targeted credit to actions that expose supportin…
-
Mach-Mind-4-Flash: 35B MoE model matches 100B+ performance
Researchers have introduced Mach-Mind-4-Flash, a 35 billion parameter Mixture-of-Experts (MoE) model that activates only 3 billion parameters. Through post-training optimization, this model achieves performance comparab…
-
TreeSeeker framework enhances AI deep search with controlled trial-and-error
Researchers have introduced TreeSeeker, a novel framework designed to improve the efficiency of deep search agents. This system structures search processes as a tree, allowing agents to explore multiple potential paths …