Almanac
technique

reinforcement learning with belief-state rewards

techniqueactiveprovisionalreinforcement-learning-with-belief-state-rewards-d5939c34·1 events·first seen 18d ago

Aliases: reinforcement learning with belief-state rewards

Co-occurring entities

More like this (12)

Recent events (1)

6arXiv · cs.CL·18d ago·source ↗

BeliefTrack: Benchmarking and Improving Contextual Belief Management in LLMs

This paper introduces Contextual Belief Management (CBM) as a framework for studying how LLMs should update, preserve, or ignore information across long-horizon interactions. The authors release BeliefTrack, a closed-world benchmark with symbolic verifiers enabling exact turn-level evaluation across Rule Discovery and Circuit Diagnosis tasks. Vanilla LLMs show severe CBM failures; reinforcement learning with belief-state rewards reduces failure rates by 70.9% on average, while representation-level steering achieves 46.1% reduction. Probing experiments reveal latent belief-state dynamics underlying these failures.