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

Read full text
Authors: Caio Vicentino
Cited by: 20
References: 5

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 consistent across all five layers (4/5 raw p

Fields of Study & Subjects

Space Science and Extraterrestrial Life Visual perception and processing mechanisms Embodied and Extended Cognition

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
3 June 2026