BrowseComp-Plus
PulseAugur coverage of BrowseComp-Plus — every cluster mentioning BrowseComp-Plus across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
PANINI-DR system enhances deep research with multi-agent approach · 2 sources tracked
Researchers have developed PANINI-DR, a multi-agent system designed to enhance deep research by managing complex search, reasoning, and computation steps. The system utilizes a Generative Semantic Workspace to record su…
-
New research explores LLM context management and recall mechanisms · 4 sources tracked
Researchers are exploring how large language models (LLMs) manage contextual information, with new papers proposing distinct approaches. One study introduces "Context Language Models" (CLMs) that natively manage their c…
-
New 'Question's Gambit' module enhances AI agent research accuracy
Researchers have introduced "Question's Gambit," a novel module designed to improve the initial retrieval step for deep research agents. This module decomposes complex questions into clues, reformulates them into comple…
-
OpenResearcher pipeline enables offline synthesis of AI research trajectories
Researchers have developed OpenResearcher, an open-source pipeline designed for synthesizing long-horizon research trajectories for training deep research agents. This pipeline operates offline, utilizing three explicit…
-
BRACE method enhances asynchronous RL for language models
Researchers have introduced BRACE, a novel method for improving asynchronous reinforcement learning in language models. This technique addresses the bias introduced by policy lag in asynchronous training by employing an…
-
AtlasNav framework enhances LLM agent corpus navigation, cutting costs
Researchers have developed AtlasNav, a new framework for large language model agents to interact with external corpora more effectively. This system organizes the corpus into a persistent "Corpus Atlas" once, allowing q…
-
New method adapts agentic search benchmarks to realistic corpora
Researchers have developed a new method to adapt existing benchmarks for agentic search by projecting them onto larger, more realistic corpora. This approach, demonstrated by adapting the BrowseComp-Plus benchmark to NV…
-
New BOUND framework improves LLM search agent accuracy
Researchers have developed BOUND, a new framework designed to improve the accuracy of large language model (LLM)-based search agents. This method addresses issues like persistent wrong-anchor drift and constraint drift …
-
New study explores KV cache compaction for LLM agents
A new study published on arXiv explores practical methods for online KV cache compaction in Large Language Model (LLM) agents. The research focuses on reducing inference bottlenecks caused by long agent trajectories by …
-
Meta and CMU unveil agentic context management tools for long-horizon AI tasks
Researchers from Meta and CMU have developed a new approach to agentic context management for long-horizon tasks. Their method, detailed in a paper published by the Association for Computing Machinery, equips agents wit…
-
New TRACE method enhances AI agent tool-use on long-horizon tasks · 2 sources tracked
Researchers have developed TRACE, a novel method for improving the performance of multi-turn AI agents in complex, long-horizon tasks. This technique addresses the challenge of credit assignment by deriving per-action r…
-
New VISTA interface enhances LLM agent context management
Researchers have developed VISTA, a novel training-free interface designed to improve how large language model (LLM) agents manage their context. VISTA addresses the limitation that LLMs are "proprioceptively blind" to …
-
New Multi-Prefix Embedding method improves long-context retrieval
Researchers have introduced Multi-Prefix Embedding (MPE), a novel technique designed to improve long-context retrieval in information retrieval systems. MPE addresses the trade-off between detail loss in single-vector e…
-
Dr-DCI framework scales agentic search with dynamic workspace expansion
Researchers have developed Dr-DCI, a novel framework designed to enhance agentic search capabilities over large corpora. This system dynamically expands a local workspace by retrieving relevant documents, allowing agent…
-
New Research Questions Multi-Agent System Superiority Over Single-Agent Systems
A new paper challenges the prevailing notion that multi-agent systems (MAS) inherently outperform single-agent systems (SAS). Researchers found that automatically generated MAS, despite higher computational costs, often…
-
New research tackles LLM memory for long contexts and reliability
Multiple research papers explore novel methods for enhancing large language model (LLM) memory systems to handle long contexts and improve reliability. These approaches include using test-time gradient descent for writi…