LLM-based agentic systems
PulseAugur coverage of LLM-based agentic systems — every cluster mentioning LLM-based agentic systems across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New technique grafts latent knowledge to improve LLM agent failure attribution
Researchers have identified a "knows-but-won't-say gap" in large language model (LLM)-based agentic systems, where models possess the internal information to correctly attribute failures but do not explicitly output thi…
-
New benchmark reveals AI agents vulnerable to harmful actions
Researchers have developed a new benchmark called BAD-ACTS to evaluate the robustness of AI agentic systems against adversarial attacks designed to elicit harmful actions. The benchmark includes five distinct agentic sy…
-
New OAT method efficiently traces LLM agent failures without step-level data
Researchers have developed a new method called OAT for unsupervised failure attribution in LLM-based agentic systems. This approach trains on successful trajectories to identify error steps in failure trajectories at in…