Does an Agent's History Tell You When Compaction Will Hurt? A Modest, Bounded Effect on the TRACE Paired-Replay Corpus
Paper recorded by Signals 4 on 2026-10-06 in cs.AI. Abstract reproduced from arXiv; link to the original below.
Published 2026-10-06 on arXiv · recorded by Signals 4 on 2026-10-07
Category: cs.AI · 人工智能 · first seen 2026-10-07
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 re
Read on arXiv →
Cite this page: Does an Agent's History Tell You When Compaction Will Hurt? A Modest, Bounded Effect on the TRACE Paired-Replay Corpus: the #411 most recent of 960 cs.AI papers we have recorded (as of 2026-10-06). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/does-an-agent-s-history-tell-you-when-compaction-will-hurt-a-modest-bounded-effe.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable:
papers.json
Get 4 AI signals a day by email — free.
Get 4 AI signals a day by email — free