articleOpen MINDJun 3, 2026GREEN OA

The Verdict Is Not the Lever: An Interpretable Task-Completion Feature Predicts but Does Not Cause Long-Horizon Agent Termination

OpenBiome

Indexed indatacite

Abstract

Companion note to the four-paper WANDERING arc, reporting a pre-registered NEGATIVE. Motivated by the context-rot literature (long-context degradation is representational, not retrieval; arXiv:2510.05381), we ask whether the residual stream carries an earlier or better detector of long-horizon agent WANDERING than the cheap probe-free tool-entropy signal -- does the geometry rot before the behavior does? On the same 99 Qwen3.6-27B SWE-bench Pro trajectories (CPU re-analysis, no new compute): Stage 1 (raw residual geometry, no SAE) finds a real but weak fingerprint, representational velocity-freezing -- WANDERING trajectories settle toward an attractor sooner (smaller early per-turn state change), directionally…

Citation impact

20
total citations
FWCI
133.66
Percentile
100%
References
5
Too recent for citation history.

Authors

1

Topics & keywords

Keywords
  • Residual
  • Context (archaeology)
  • Feature (linguistics)
  • Detector
  • Baseline (sea)
  • Constant false alarm rate
  • Property (philosophy)
  • ALARM
No related works found for this paper.