The Verdict Is Not the Lever: An Interpretable Task-Completion Feature Predicts but Does Not Cause Long-Horizon Agent Termination
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
1Topics & keywords
Topics
Keywords
- Residual
- Context (archaeology)
- Feature (linguistics)
- Detector
- Baseline (sea)
- Constant false alarm rate
- Property (philosophy)
- ALARM
No related works found for this paper.