Output quality is important when working with AI coding agents, but true efficiency comes from getting work done quickly, efficiently, and with the right context. That’s why token count of individual interactions alone isn’t a meaningful measure of efficiency. The goal shouldn’t be to use fewer tokens, but to tap into the right amount of context to

Sep 2, 2026

LLMs & agents Model evaluation Performance Developer tools

Research

Berkeley AI Research

Teaching LLMs to Update Beliefs for Efficient Long-Horizon Interaction

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

Jul 26, 2026

LLMs & agents Model evaluation Training Machine learning