Story
arxiv_agent_systems_research ยท Nov 16, 2026 ยท paper
Source brief
Instrumenting Failure: Scoring Language Model Agents at Every Decision Node in Imperfect-Information Games
arxiv.orgNov 16, 2026
original source linked
In brief
Agent evaluations report task success and rarely say what an agent did at each decision. We score every decision node of three 12B to 14B instruct-tuned language models (LMs) playing five zero-sum imperfect-informatio...
Feed lens
agentevaluation