跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.17662 · v1

Learn then Bet: Learning Interpretable Rules for Reliable Agent Intervention

首次提交 2026-11-13 10:14
版本更新 2026-11-13 10:14
雷达观测 2026-11-17 04:57
arXiv ↗PDF ↗

摘要

Autonomous agents now run for hundreds of steps with little or no human supervision. In practice, practitioners use runtime monitors such as turn limits and keyword filters to decide when a run should be stopped, upgraded, or assisted. However, these heuristics may stop runs that would otherwise succeed or allow failing runs to continue. To address this limitation, we introduce LeBet (Learn then Bet), a statistical learning framework that derives its learning objective from sufficient conditions for valid and powerful intervention. In particular, LeBet learns an interpretable OR-of-AND monitor and accumulates evidence through a fixed betting statistic, intervening when the evidence reaches a prescribed threshold. Under finite within-class exchangeability and leave-one-out stability, we derive finite-sample guarantees for false-positive control (validity) and detection power conditional on the training data, using the same trajectories for learning and calibration without assuming independent and identically distributed trajectories. To address the intractable combinatorial optimization problem in our learning formulation, we use stochastic local search that leverages the monitor's Boolean structure to propose rule edits aimed at improving empirical separation. On SWE-bench Lite with Ministral 3 8B, the learned monitor saves 34.46%34.46\% of input-plus-output tokens and increases output precision from 18.33%18.33\% to 21.59%21.59\%. The empirical false-positive rate is 13.64%13.64\%. Our results show how to formalize the learning problem over interpretable rule sets with statistical conditions and establish training-conditional guarantees for reliable intervention based on partial histories.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-13 10:14 · 最新观测版本

Learn then Bet: Learning Interpretable Rules for Reliable Agent Intervention

Autonomous agents now run for hundreds of steps with little or no human supervision. In practice, practitioners use runtime monitors such as turn limits and keyword filters to decide when a run should be stopped, upgraded, or assisted. However, these heuristics may stop runs that would otherwise succeed or allow failing runs to continue. To address this limitation, we introduce LeBet (Learn then Bet), a statistical learning framework that derives its learning objective from sufficient conditions for valid and powerful intervention. In particular, LeBet learns an interpretable OR-of-AND monitor and accumulates evidence through a fixed betting statistic, intervening when the evidence reaches a prescribed threshold. Under finite within-class exchangeability and leave-one-out stability, we derive finite-sample guarantees for false-positive control (validity) and detection power conditional on the training data, using the same trajectories for learning and calibration without assuming independent and identically distributed trajectories. To address the intractable combinatorial optimization problem in our learning formulation, we use stochastic local search that leverages the monitor's Boolean structure to propose rule edits aimed at improving empirical separation. On SWE-bench Lite with Ministral 3 8B, the learned monitor saves 34.46%34.46\% of input-plus-output tokens and increases output precision from 18.33%18.33\% to 21.59%21.59\%. The empirical false-positive rate is 13.64%13.64\%. Our results show how to formalize the learning problem over interpretable rule sets with statistical conditions and establish training-conditional guarantees for reliable intervention based on partial histories.

查看此版本解读 →查看此版本原文 ↗