跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.10315 · v1

Repeating Work Can Lower Energy per Successful Goal in LLM Agents

首次提交 2026-11-07 07:30
版本更新 2026-11-07 07:30
雷达观测 2026-11-10 10:11
arXiv ↗PDF ↗

摘要

When a temporary call failure interrupts a tool-using LLM agent, the framework must choose how much completed work to repeat. Repeating less completed work intuitively saves computation, but recovery mechanisms also change subsequent execution and the chance of success. We compare recovery mechanisms by energy per successful goal (EpG), which divides the energy of all task runs (including failed runs) by the number that finish correctly. In controlled vLLM experiments on one node, we measure board energy above idle for eight recovery options on reliably solved multi-turn tasks, with selected comparisons across three model families. For the model tested across all eight options, with the prefix cache retained, starting over has 22 percent lower EpG than continuing after early failures. Under the same cache condition, continuing has 24 percent lower EpG than starting over after late failures. Among all eight recovery options, repeating only the interrupted turn has the lowest observed EpG after early and late tool failures on this model. Holding recovery fixed, retaining the prefix cache reduces prompt tokens needing fresh computation by 86 percent but reduces recovery energy by only 8 percent at contexts up to 7,333 tokens. These measurements and a condition relating recovery energy and success show when repeating work lowers EpG, helping framework developers choose how their agents recover on their intended models and tasks.

作者备注:17 pages, 6 figures, 7 tables

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 · 2026-11-07 07:30 · 最新观测版本

Repeating Work Can Lower Energy per Successful Goal in LLM Agents

When a temporary call failure interrupts a tool-using LLM agent, the framework must choose how much completed work to repeat. Repeating less completed work intuitively saves computation, but recovery mechanisms also change subsequent execution and the chance of success. We compare recovery mechanisms by energy per successful goal (EpG), which divides the energy of all task runs (including failed runs) by the number that finish correctly. In controlled vLLM experiments on one node, we measure board energy above idle for eight recovery options on reliably solved multi-turn tasks, with selected comparisons across three model families. For the model tested across all eight options, with the prefix cache retained, starting over has 22 percent lower EpG than continuing after early failures. Under the same cache condition, continuing has 24 percent lower EpG than starting over after late failures. Among all eight recovery options, repeating only the interrupted turn has the lowest observed EpG after early and late tool failures on this model. Holding recovery fixed, retaining the prefix cache reduces prompt tokens needing fresh computation by 86 percent but reduces recovery energy by only 8 percent at contexts up to 7,333 tokens. These measurements and a condition relating recovery energy and success show when repeating work lowers EpG, helping framework developers choose how their agents recover on their intended models and tasks.

查看此版本解读 →查看此版本原文 ↗