Metraipolis › archive › dc_0ab34ef077e4
Tracing the Thoughts of a Coding Agent Playing ARC-AGI-3: Lessons for Continual Learning — arXiv:2610.11450
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.11450
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T05:47:47.797Z
- SHA-256 of the archived text
8c8628843b24c8ba2603eee073c748e7cb3a8b32e04449e517f9b749af64cfe6- Stable URL of this page
https://metraipolis.com/documento/dc_0ab34ef077e4
How to cite
Tracing the Thoughts of a Coding Agent Playing ARC-AGI-3: Lessons for Continual Learning — arXiv:2610.11450 — arXiv (en), https://arxiv.org/abs/2610.11450 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0ab34ef077e4 (Metraipolis archive dc_0ab34ef077e4, sha256 8c8628843b24c8ba2603eee073c748e7cb3a8b32e04449e517f9b749af64cfe6)
BibTeX
@misc{dc0ab34ef077e4,
title = {Tracing the Thoughts of a Coding Agent Playing ARC-AGI-3: Lessons for Continual Learning — arXiv:2610.11450},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.11450},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0ab34ef077e4; sha256 8c8628843b24c8ba2603eee073c748e7cb3a8b32e04449e517f9b749af64cfe6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11450. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study how a coding agent learns across a sequence of abstract reasoning tasks. The agent runs on a frozen foundation model inside a fixed harness and acts by writing and running Python and shell scripts. It retains no state across turns other than its written artifacts, so every thought it forms, carries, corrects or abandons leaves a trace, where a thought is any belief, rule or plan committed to a file. We let the agent play ARC-AGI-3, a set of interactive reasoning games that provide no instructions. Each game is a sequence of levels, and a strategy that clears one level can fail on the next, so every new level is in effect a new task. The agent records what it learns as Python scripts and text notes, while the harness keeps a complete log of every action and observation. Our contribution is a measurement protocol that traces each thought through these files, from the task where it forms to the task where it is corrected or abandoned, applied to seven evaluation runs with three backbones from two model families. Scripts written for one task are almost never called again in a later task (33 of 630 references cross a task boundary), because most scripts embed the state of the current level. Instead, the agent rewrites its knowledge into new scripts, keeping the general rules and dropping the level-specific details, and abandons 74% of the scripts it wrote before a boundary. The notes, which only the model reads, are never revised: the agent appends without removing earlier claims, and the contradictions that accumulate are settled against the log. Because the log preserves everything, the agent forgets selectively, not catastrophically. The most costly error is a hard-coded value carried into a task where it no longer holds. These findings come from the files the agent wrote, without access to the model, and constitute a white-box analysis of how a coding agent continually learns. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.11450 — 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 2026-10-09T05:47:00.713Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).