読書リサーチレーダー投資フレームワーク
ログイン / 新規登録
← 読解に戻る
ニュースクイックテイク1 分で読めるDisconfirmAI 編集部

Self-reported RIR framework lets long-horizon LLM agents roll back, repair, and keep reflective memory

Self-reported by authors including Yi Yu, the RIR framework models error recovery as rollback-boundary control, repairing the environment while distilling reflective memory, with consistent gains reported on three long-horizon benchmarks.

2026-09-23 12:00 GMT+8

Readers can now learn a new way for long-horizon LLM agents to recover from errors: the RIR (Rollback-Induced Reflection) framework models error recovery as a rollback-boundary control problem, rolling back to a selected prior state to repair a corrupted environment while retaining reflective memory distilled from discarded trajectories, so the agent avoids repeating mistakes.

Previously, agents lacked such memory-carrying rollback: once an environment was corrupted it was hard to repair, and retries could repeat the same mistakes.

The authors self-report consistent task-performance improvements across three long-horizon benchmarks and multiple LLM backbones; the abstract gives no concrete numbers, the results are self-tested by the authors, and independent verification is still pending.

Boundary: the result covers no concrete figures or additional benchmarks; it was submitted by five authors including Yi Yu to arXiv as a preprint on September 16 (v2 updated September 17, id 2609.18304), and no independent team has yet reproduced it.

ソース

  • arxiv.org↗
リサーチを続ける →
ログイン / 新規登録
読書リサーチレーダー投資フレームワーク