Metraipolis › archive › dc_7730bcbef535

StateTape: Action-Conditioned Evidence Lifecycle Modeling for Long-Horizon Coding Agents — arXiv:2609.36319

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.36319
License (as archived)
CC0-1.0
Archived
2026-10-07T16:22:27.809Z
SHA-256 of the archived text
bf77b3ef62d8bcd7854fe2a7f27ee76ed6fc9f18ec770be3739a7e7e9f97f3bd
Stable URL of this page
https://metraipolis.com/documento/dc_7730bcbef535

How to cite

StateTape: Action-Conditioned Evidence Lifecycle Modeling for Long-Horizon Coding Agents — arXiv:2609.36319 — arXiv (en), https://arxiv.org/abs/2609.36319 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7730bcbef535 (Metraipolis archive dc_7730bcbef535, sha256 bf77b3ef62d8bcd7854fe2a7f27ee76ed6fc9f18ec770be3739a7e7e9f97f3bd)
BibTeX
@misc{dc7730bcbef535,
  title = {StateTape: Action-Conditioned Evidence Lifecycle Modeling for Long-Horizon Coding Agents — arXiv:2609.36319},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.36319},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7730bcbef535; sha256 bf77b3ef62d8bcd7854fe2a7f27ee76ed6fc9f18ec770be3739a7e7e9f97f3bd},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36319. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Despite the recent success of coding agents built on large language models, it remains challenging to run them over long horizons, since every observation is appended to the context and the context grows with each one. History-based maintenance is a common remedy, which masks or summarizes old observations, or prunes what a model reads as useless, and bounds the context at little cost. However, it decides from the text of the history alone and sees nothing of how the code is connected. Since a coding agent edits code many times over a single task, and each write can change what code elsewhere means, such maintenance may keep records a write has falsified, drop ones that still hold, and miss code the agent needs next. To overcome these challenges, this paper proposes StateTape, a novel and scalable framework that rewrites a coding agent's context as the repository changes rather than as the context grows. The key idea of StateTape is to model the repository as a symbol-level code graph, whose dependencies and language rules expose which symbols a write can affect. Upon this graph, a tape marks the symbols each write changed, which turns staleness from an inference about text into an observation of the agent's writes. We propose a per-write procedure in which the tape nominates the records a write could have falsified while a small manager model settles what the write log cannot, and further provide a theoretical analysis and TraceBench, a benchmark that labels what an agent is holding against what is actually needed. Empirically, we demonstrate that StateTape can effectively clear falsified records and retrieve what is needed, and thus achieve a higher resolve rate in all experiments spanned by six coding agents and three edit-heavy benchmarks with little computational overhead.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.36319 — 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 2026-10-07T15:54:53.486Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).