Metraipolis › archive › dc_e78e3a8aee40
MicroMouse: Masking Harmful Supervision in Long CoT via Relative Potential — arXiv:2611.02710
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.02710
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:23:44.645Z
- SHA-256 of the archived text
3f689130b2edc79320cb6fcae658389650b267dbcaf2e684deb062d1b884b841- Stable URL of this page
https://metraipolis.com/documento/dc_e78e3a8aee40
How to cite
MicroMouse: Masking Harmful Supervision in Long CoT via Relative Potential — arXiv:2611.02710 — arXiv (en), https://arxiv.org/abs/2611.02710 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e78e3a8aee40 (Metraipolis archive dc_e78e3a8aee40, sha256 3f689130b2edc79320cb6fcae658389650b267dbcaf2e684deb062d1b884b841)
BibTeX
@misc{dce78e3a8aee40,
title = {MicroMouse: Masking Harmful Supervision in Long CoT via Relative Potential — arXiv:2611.02710},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.02710},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e78e3a8aee40; sha256 3f689130b2edc79320cb6fcae658389650b267dbcaf2e684deb062d1b884b841},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02710. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Even successful long CoTs may contain harmful supervision, motivating the need for methods that can automatically identify and mask such signals during SFT. Inspired by the MicroMouse maze-solving process, we view a long CoT as a search trajectory from the input problem toward the target answer. This perspective motivates maintaining a goal-relative measure, analogous to a MicroMouse's spatial coordinates, to quantify how close the current reasoning state is to the target answer. Building on this perspective, we propose MicroMouse, an automated selective-SFT framework for masking harmful supervision in long CoTs. In MicroMouse we introduce a Relative Potential (REP) to measure how closely each reasoning state supports the gold answer. Unlike the perplexity of the gold answer alone, REP measures relative support by contrasting the gold answer with a matched foil. This contrast cancels likelihood variations shared by the pair, yielding a more stable signal of progress toward the target answer. By tracking the REP trajectory, MicroMouse identifies consecutive potential decreases as erroneous exploration and post-peak reasoning as redundant wandering, and masks these harmful supervision during SFT. Extensive experiments across multiple student model scales and reasoning benchmarks show that MicroMouse consistently outperforms Full-CoT SFT and existing selective-SFT baselines, yielding average relative gains of 5.5% in greedy accuracy and 2.6% in Pass@1 relative to Full-CoT SFT. Meanwhile, MicroMouse improves reasoning efficiency by reducing average output length by 8.8%, while identifying harmful supervision in only 1.7 seconds per long CoT on average. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2611.02710 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-03T18:10:07.977Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).