arXiv：cs.LG· Egor Pakhomov, Erik Nijkamp·· 7 小时前AI 评分35
Agent 历史能否预测压缩何时有害？TRACE 配对回放语料上的一项有限效应研究
Does an Agent's History Tell You When Compaction Will Hurt? A Modest, Bounded Effect on the TRACE Paired-Replay Corpus
AI 导读
研究基于 TRACE 公开语料库中 590 个 AppWorld 压缩边界，检验智能体近期行为能否预测上下文压缩带来的损害。结果显示，边界前历史对压缩后损害的预测能力很弱，最佳协议触发器在留出集上仅达 AUROC 0.66，低于同边界复现的 0.72；最佳冻结触发器可避开 21% 的有害边界并保留 84% 的压缩机会。在匹配保留率下，最佳触发器能否胜过 token 预算规则尚无法评估。
正文
Abstract:Many long-horizon agents compact their context on a global rule, usually a token budget, blind to what the agent was doing. We ask whether the agent's recent behaviour predicts when a compaction will hurt. TRACE's public corpus of 590 harness-triggered AppWorld compaction boundaries replays each boundary from a re-executed prefix state under the pre-compaction context and under the summary, and records the burden of the next actions: calls that error or repeat a call already made. We find that pre-boundary history predicts post-compaction harm only weakly. An internally prespecified contrast by prefix placement is a wide null, and the naive "has-written" label behind it turns out to measure trajectory phase. The best extension-protocol trigger reaches held-out AUROC 0.66 (0.64 on the replicate's own label) against a same-boundary replicate of 0.72; the best frozen, interpretable trigger avoids 21% of harmful (positive-burden) boundaries while keeping 84% of compaction opportunities, and exceeds the random-rule expectation on count but not on burden mass (a post hoc comparison). Whether the best trigger beats a token-budget rule at matched retention cannot be evaluated on the release. We state what corpora should ship to answer it.
| Comments: | Accepted at the IAB Workshop (Interpreting Agent Behavior) at NeurIPS 2026 (non-archival). 20 pages |
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.08722 [cs.AI] |
| (or arXiv:2610.08722v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.08722 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Egor Pakhomov [view email]
[v1]
Tue, 6 Oct 2026 17:26:57 UTC (68 KB)
来源：arXiv：cs.LG · arxiv.org