ByteDance Paper: Keeping Raw Attempt History Outperforms Summaries for LLM Reasoning

rohanpaul_ai · x · 2026-08-31

A new ByteDance paper explores test-time computation optimization, introducing the Chain-of-Experience (CoE) method. Contrary to traditional approaches that summarize past attempts into concise memories, CoE advocates keeping the full history of earlier attempts and feedback in context, asking the model to try again based on this raw data.

Across 6 benchmarks covering math, coding, and knowledge, the CoE method with self-feedback achieved an average score of 71.0%, compared to 66.8% for iterative solving without feedback. This suggests that retaining the 'messy' history of attempts can be more effective than compressing it into 'neat' summaries for specific tasks.

Related event: ByteDance Paper: Keeping Full Trial History Beats Summarized Memory for LLM Agents(3 posts)→

Original post →

More from Research

Research channel →