Polished but Unresolved: Identifying Late-Stage Pressure States in Long-Horizon Tool-Use Agents

• URL: http://arxiv.org/abs/2609.00823v1
• Date: Tue, 01 Sep 2026 07:24:53 GMT
• Title: Polished but Unresolved: Identifying Late-Stage Pressure States in Long-Horizon Tool-Use Agents
• Abstract summary: We study late-stage pressure states, in which an agent is biased toward submitting a final answer that appears complete and polished while key constraints remain unresolved.<n>We propose Probe-Sensed Pressure Relief (PSPR), a plugin that applies lightweight pressure relief direction under moderate pressure and moves to structured organization under high pressure risk.
• Score: 21.24035103429806
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Long-horizon tool-use agents need not only to search and plan, but also to decide when to finalize. We study late-stage pressure states, in which an agent is biased toward submitting a final answer that appears complete and polished while key constraints remain unresolved. We first train a linear probe to show that this pressure state is identifiable from the agent's hidden states. Then, we use activation interventions along this pressure direction and find that shifting the hidden states changes both the pressure score and whether the agent continues tool use or submits early. Through controlled context manipulations, we further see that the pressure is mitigated by constraint clarity and action mapping. Based on these findings, we propose Probe-Sensed Pressure Relief (PSPR), a plugin that applies lightweight pressure relief direction under moderate pressure and moves to structured organization under high pressure risk. Experiments on multiple long-horizon benchmarks show that our method consistently strengthens existing agent methods.

Related papers

• Agentic Pressure: The Endogenous Entropy of Reliable Autonomy [5.721126979967714]
  Agentic Pressure is a kinetic force that spontaneously emerges when the cost of compliance conflicts with the imperative of goal achievement.<n>We propose a theoretical framework that formalizes Agentic Pressure as the ratio between the required work to overcome environmental friction and the remaining capacity of the agent.<n> Empirical experiments validate this framework and show that aligned agents spontaneously compromise safety to preserve autonomy under high-pressure conditions.
  arXiv  Detail & Related papers  (2026-09-05T09:39:18Z)
• Just Noticeable Difference Modeling for Token Compression in Vision-Language-Action Models [62.522141464687195]
  We introduce Action-JND, which extends the principle of just noticeable difference (JND) to embodied perception.<n>A token change is considered tolerable only when the induced action deviation remains within a tolerated margin.<n>The resulting action-tolerance score serves as a plug-and-play criterion for VLA compression paradigms.
  arXiv  Detail & Related papers  (2026-08-21T15:59:37Z)
• Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability [7.183748353637384]
  We show that compression can weaken the influence of recent interactions, increasing blocked actions, repeated exploration, and instability across runs.<n>We introduce TRACE, a verifier-guided framework that evaluates individual compaction events through paired closed-loop continuations from the same environment state.<n>Initial results on AppWorld show improvements over existing compression baselines in task performance, multi-run reliability, and context--execution efficiency.
  arXiv  Detail & Related papers  (2026-08-06T18:42:02Z)
• CoACT: Action-Preserving Observation Compression for Coding Agents [8.484842324052751]
  This paper proposes CoACT, an action-preserving observation compression method for coding agents.<n>CoACT is built on next-action preservation (NAP), which requires a compressed observation to induce the same next action as the raw observation.<n> Experiments on SWE-bench Verified with three agentic models show that CoACT reduces average total token consumption by 33.0%.
  arXiv  Detail & Related papers  (2026-07-03T03:17:52Z)
• Constitutional On-Policy Safe Distillation [64.02536207601112]
  On-policy self-distillation (OPSD) has emerged as an efficient post-training paradigm by using a teacher conditioned on privileged information to provide dense token-level supervision.<n>We propose Constitutional On-Policy Safe Distillation (COPSD), which first calibrates the teacher through a Cross-SFT cold-start and then performs constitution-conditioned on-policy distillation.
  arXiv  Detail & Related papers  (2026-06-02T03:17:56Z)
• Suppressing Forgery-Specific Shortcuts for Generalizable Deepfake Detection [59.056076147081775]
  Deepfake detection suffers from poor generalization across forgery methods.<n>Recent approaches attempt to improve generalization, but lack explicit mechanism to identify and suppress such shortcuts.<n>We propose Shortcut Subspace Suppression (S3) framework that explicitly characterizes and suppresses method-specific shortcuts.
  arXiv  Detail & Related papers  (2026-06-01T07:54:58Z)
• Dance Across Shifts: Forward-Facilitation Continual Test-Time Adaptation through Dynamic Style Bridging [65.11234199720428]
  Continual Test-Time Adaptation aims to empower perception systems to handle dynamic distribution shifts encountered after deployment.<n>We introduce a novel forward-facilitation paradigm through a method termed Dynamic Style Bridging.<n>During test time, to mitigate inherent generative bias and adapt these proxies to incoming data, we propose a multi-level bridging mechanism.
  arXiv  Detail & Related papers  (2026-05-18T16:18:17Z)
• Pressure, What Pressure? Sycophancy Disentanglement in Language Models via Reward Decomposition [4.5328321409938095]
  We operationalise sycophancy through formal definitions of pressure independence and evidence responsiveness.<n>We propose the first approach to sycophancy reduction via reward decomposition.
  arXiv  Detail & Related papers  (2026-04-07T00:28:17Z)
• Why Agents Compromise Safety Under Pressure [6.429973383484847]
  This paper identifies a new concept called Agentic Pressure, which characterizes the endogenous tension emerging when compliant execution becomes infeasible.<n>We demonstrate that under this pressure agents exhibit normative drift where they strategically sacrifice safety to preserve utility.<n>We find that advanced reasoning capabilities accelerate this decline as models construct linguistic rationalizations to justify violation.
  arXiv  Detail & Related papers  (2026-03-16T08:37:34Z)
• Pressure2Motion: Hierarchical Motion Synthesis from Ground Pressure with Text Guidance [47.8091643050689]
  Pressure2Motion is a novel motion capture algorithm that synthesizes human motion from a ground pressure sequence and text prompt.<n>It is suitable for privacy-preserving, low-light, and low-cost motion capture scenarios.
  arXiv  Detail & Related papers  (2025-11-07T07:21:11Z)
• Bandit Quickest Changepoint Detection [55.855465482260165]
  Continuous monitoring of every sensor can be expensive due to resource constraints. We derive an information-theoretic lower bound on the detection delay for a general class of finitely parameterized probability distributions. We propose a computationally efficient online sensing scheme, which seamlessly balances the need for exploration of different sensing options with exploitation of querying informative actions.
  arXiv  Detail & Related papers  (2021-07-22T07:25:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.