Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
The belief-action gap in language model agents
Ayse Sila Okcu, Weisheng Wang, Tongmeng Xie +4
Language model (LM) agents can fail for different reasons, requiring different explanations and interventions. We study how state beliefs, action values, and action preferences int…
cs.LG2026
A Behavioural and Representational Evaluation of Goal-Directedness in Language Model Agents
Raghu Arghal, Fade Chen, Niall Dalton +6
Understanding an agent's goals helps explain and predict its behaviour, yet there is no established methodology for reliably attributing goals to agentic systems. We propose a fram…