Metraipolis › archive › dc_e0d8a1508522

SWE-Trail: History-Guided Trajectory Collection for Coding Agent Training — arXiv:2611.02074

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.02074
License (as archived)
CC0-1.0
Archived
2026-11-03T18:13:48.669Z
SHA-256 of the archived text
d0d2f9e3ef644fb18cd8ca2d93fde2c5ad040eca9aab79ca47ae0388897d027e
Stable URL of this page
https://metraipolis.com/documento/dc_e0d8a1508522

How to cite

SWE-Trail: History-Guided Trajectory Collection for Coding Agent Training — arXiv:2611.02074 — arXiv (en), https://arxiv.org/abs/2611.02074 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e0d8a1508522 (Metraipolis archive dc_e0d8a1508522, sha256 d0d2f9e3ef644fb18cd8ca2d93fde2c5ad040eca9aab79ca47ae0388897d027e)
BibTeX
@misc{dce0d8a1508522,
  title = {SWE-Trail: History-Guided Trajectory Collection for Coding Agent Training — arXiv:2611.02074},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.02074},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e0d8a1508522; sha256 d0d2f9e3ef644fb18cd8ca2d93fde2c5ad040eca9aab79ca47ae0388897d027e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02074. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Coding agents solve repository issues through long sequences of exploration, editing, and validation. These trajectories are increasingly used as post-training data, so how they are collected shapes what the trained model learns. A common approach is to sample multiple trajectories independently for each issue and then select or curate them. However, as more trajectories are sampled independently, later trajectories become increasingly redundant, even though earlier trajectories could guide where subsequent collection effort should be spent. A natural way to use this history is to expose it to the coding agent as advice. But training on such trajectories can make the model rely on advice that is unavailable at test time, creating a train-test mismatch. Instead, we argue that history should guide where collection effort is spent, while the coding agent decides what to generate. We introduce SWE-Trail, a trajectory collector that uses earlier trajectories to guide subsequent collection while keeping that history outside the coding agent's context. During a new rollout, SWE-Trail uses history to identify a state where additional collection effort may be useful. There, the coding agent proposes candidate next actions from its ordinary context, and SWE-Trail briefly executes them from the same checkpoint to decide which route continues. We evaluate collection approaches by training student models on the trajectories they produce. For a 124B student initialized from Ling-3.0-flash-base, SWE-Trail improves mean resolution over independent sampling by 2.33 and 1.60 percentage points on SWE-bench Multilingual and SWE-bench Pro, respectively. Without history, the same pipeline produces more resolved trajectories than independent sampling, but improves by only 0.11 points on Multilingual. These results show the value of using history to guide collection without exposing it to the coding agent.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2611.02074 — 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 2026-11-03T18:09:53.370Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).