LLM agents: planning, tool use, multi-agent systems, computer/web agents and agent benchmarks.
125 papers this month
Agents struggle to accumulate evidence, adjust strategies, and verify results over long, open-ended tasks in real-world settings.
Coding agents often produce systems that appear to meet requirements but fail to deliver the intended behavior on held-out cases.
Agents cannot reliably identify when historical information is relevant, leading to missed or misapplied context.
Safety checks that only inspect screens can be bypassed by reusing legitimate screens in unexpected transitions.
Agents often rely on pretrained knowledge rather than acquiring new knowledge through interaction in novel settings.
Named by an AI from these papers' abstracts.