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.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Pakhomov, E., & Nijkamp, E. (2026). Does an Agent's History Tell You When Compaction Will Hurt? A Modest, Bounded Effect on the TRACE Paired-Replay Corpus. https://omanscience.com/en/articles/does-an-agent-s-history-tell-you-when-compaction-will-hurt-a-modest-bounded-effect-on-the-trace-paired-replay-corpus
MLA 9
Pakhomov, Egor, and Erik Nijkamp. "Does an Agent's History Tell You When Compaction Will Hurt? A Modest, Bounded Effect on the TRACE Paired-Replay Corpus." https://omanscience.com/en/articles/does-an-agent-s-history-tell-you-when-compaction-will-hurt-a-modest-bounded-effect-on-the-trace-paired-replay-corpus.
Chicago (author–date)
Pakhomov, Egor, and Erik Nijkamp. 2026. "Does an Agent's History Tell You When Compaction Will Hurt? A Modest, Bounded Effect on the TRACE Paired-Replay Corpus." https://omanscience.com/en/articles/does-an-agent-s-history-tell-you-when-compaction-will-hurt-a-modest-bounded-effect-on-the-trace-paired-replay-corpus.
Harvard
Pakhomov, E. and Nijkamp, E. (2026) 'Does an Agent's History Tell You When Compaction Will Hurt? A Modest, Bounded Effect on the TRACE Paired-Replay Corpus', Available at: https://omanscience.com/en/articles/does-an-agent-s-history-tell-you-when-compaction-will-hurt-a-modest-bounded-effect-on-the-trace-paired-replay-corpus.
Vancouver
Pakhomov E, Nijkamp E. Does an Agent's History Tell You When Compaction Will Hurt? A Modest, Bounded Effect on the TRACE Paired-Replay Corpus. https://omanscience.com/en/articles/does-an-agent-s-history-tell-you-when-compaction-will-hurt-a-modest-bounded-effect-on-the-trace-paired-replay-corpus
IEEE
E. Pakhomov, and E. Nijkamp, "Does an Agent's History Tell You When Compaction Will Hurt? A Modest, Bounded Effect on the TRACE Paired-Replay Corpus," https://omanscience.com/en/articles/does-an-agent-s-history-tell-you-when-compaction-will-hurt-a-modest-bounded-effect-on-the-trace-paired-replay-corpus.