FOLLOW A QUESTION FURTHER

Library

Practical lessons, original research, and the details that make systems work.

Refine your reading (1)
2 articlesReset filters

Articles

Research
Berkeley AI Research

Teaching LLMs to Update Beliefs for Efficient Long-Horizon Interaction (opens in a new tab)

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. Self-summarization enables concise, interpretable contexts