Skip to content
Berkeley AI Research·· 2026-07-26

Teaching LLMs to Update Beliefs for Efficient Long-Horizon Interaction

Teaching LLMs to Update Beliefs for Efficient Long-Horizon Interaction

AI summary

Overview of ABBEL compared to traditional recursive summarization. Beliefs replace the full interaction history as the agent’s working context, and belief grading improves performance by supervising the contents of each belief state.. As task horizons grow, LLM contexts can’t scale forever.

Selection record

Not admittedSum of both 76 < twice the threshold 120

Source tier
Official, first-hand; this tier's threshold is 60
Pre-filter
passed:LLM信念更新与长程交互研究

A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.

Source: Berkeley AI Research · bair.berkeley.edu