Who&When
PulseAugur coverage of Who&When — every cluster mentioning Who&When across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
VerifyMAS framework improves failure attribution in LLM multi-agent systems
Researchers have introduced VerifyMAS, a novel hypothesis verification framework designed to improve failure attribution in large language model-driven multi-agent systems (LLM-MAS). This approach tackles the limitation…
-
New AI framework CockpitHAT tackles safety failures in multi-agent systems
A research paper introduces CockpitHAT, a new framework designed to improve the reliability of multi-agent AI systems in safety-critical environments like automotive cockpits. The system addresses "Correctness Collapse,…
-
New DCFA framework improves failure reasoning in LLM multi-agent systems
Researchers have developed DCFA, a novel framework designed to improve failure attribution in large language model (LLM)-based multi-agent systems. This training-free approach addresses challenges like shallow attributi…
-
New Adaptive Influence Graphs improve failure attribution in multi-agent LLM systems
Researchers have developed Adaptive Influence Graphs (AIGs), a novel framework designed to improve failure attribution in multi-agent Large Language Model (LLM) systems. This two-stage approach first converts failed sys…
-
Which Agent Causes Task Failures and When?Researchers from PSU and Duke explores automated failure attribution of LLM Multi-Agent Systems
Researchers from Penn State University and Duke University, alongside collaborators from institutions including Google DeepMind, have introduced a new research problem called "Automated Failure Attribution" for LLM Mult…