跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2606.17541 · v2

Offline Preference-Based Trajectory Evaluation

首次提交 2026-06-16 13:42
版本更新 2026-11-17 03:51
雷达观测 2026-11-18 19:44
arXiv ↗PDF ↗

摘要

Offline evaluation of agentic systems often collapses trajectories into a binary terminal success value, discarding information about partial progress. This, in turn, results in widespread ties that create statistical inefficiency by reducing effective sample size and weakening the ability to distinguish systems. We propose preference-based trajectory evaluation, an evaluation measure that compares pairs of trajectories directly by using temporal preferences between time-to-return profiles. We find that, across diverse agentic and interactive benchmarks, success-based metrics result in tied comparisons on roughly 75% of instances, while trajectory-aware preferences reduce ties to roughly 35%, improving discriminative power, ranking stability, and data efficiency. Our results suggest that benchmark saturation, often portrayed as the result of poor data collection or problem difficulty, may also be explained by the design of the evaluation measure.

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

本站首次收录为 v2,暂无更早版本可对照。

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。

v2 · 2026-11-17 03:51 · 最新观测版本

Offline Preference-Based Trajectory Evaluation

Offline evaluation of agentic systems often collapses trajectories into a binary terminal success value, discarding information about partial progress. This, in turn, results in widespread ties that create statistical inefficiency by reducing effective sample size and weakening the ability to distinguish systems. We propose preference-based trajectory evaluation, an evaluation measure that compares pairs of trajectories directly by using temporal preferences between time-to-return profiles. We find that, across diverse agentic and interactive benchmarks, success-based metrics result in tied comparisons on roughly 75% of instances, while trajectory-aware preferences reduce ties to roughly 35%, improving discriminative power, ranking stability, and data efficiency. Our results suggest that benchmark saturation, often portrayed as the result of poor data collection or problem difficulty, may also be explained by the design of the evaluation measure.

查看此版本解读 →查看此版本原文 ↗