arXiv cs.CL· Guanghui Min, Chen Chen·· 2 天前AI 评分32
剪掉摘要而非历史：面向长程智能体的 Source-Judged Compaction
Prune the Summary, Not the History: Source-Judged Compaction for Long-Horizon Agents
AI 导读
针对长程 LLM 智能体的上下文压缩问题，研究者提出免训练的后处理步骤 Source-Judged Compaction（SJC）：用非生成式决策模型 Jev 为摘要中每条内容打分，判断其是否有环境输出或上一版摘要作为来源，并删除无来源条目。
正文 · 原文
Abstract:Long-horizon LLM agents rely on context compaction: when the interaction history outgrows the context window, a compressor replaces it with a natural-language summary. We show that these summaries contain more than a record of what happened. Compaction prompts ask for decisions and next steps, so each summary mixes facts established by the environment with reasoning written by the compressor, and the agent cannot tell the two apart afterwards. In an analysis of a widely used structured compressor, 83% of failed runs trace back to an action that carries out a specific summary entry, most of which no environment output supports. We propose Source-Judged Compaction (SJC), a training-free post-processing step that scores each summary entry for whether it has a source in the environment outputs or the previous summary, and removes the entries that do not. It changes neither the agent nor the compressor and adds one inexpensive judge request per compaction. The judge is Jev, a non-generative decision model that answers the source question with a calibrated probability instead of text. On AppWorld and OfficeBench with two agent models, SJC improves cross-run reliability over the underlying compressor by 2.1%-8.9% without increasing the agent's token usage.
| Comments: | Uses Jev, a non-generative decision model, as the source judge. Code: this https URL |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.20927 [cs.CL] |
| (or arXiv:2610.20927v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.20927 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Guanghui Min [view email]
[v1]
Wed, 14 Oct 2026 20:57:32 UTC (293 KB)
来源：arXiv cs.CL · arxiv.org