Metraipolis › archive › dc_f35185d48a06

GitHarness: Git Init Your Harness Working Memory for Perpetual User Requirements — arXiv:2609.36789

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.36789
License (as archived)
CC0-1.0
Archived
2026-10-07T16:21:15.650Z
SHA-256 of the archived text
c279a920ef8d8e295dc808aa9fa2baf43b288f1bb6ece8249e43128a7e0bc543
Stable URL of this page
https://metraipolis.com/documento/dc_f35185d48a06

How to cite

GitHarness: Git Init Your Harness Working Memory for Perpetual User Requirements — arXiv:2609.36789 — arXiv (en), https://arxiv.org/abs/2609.36789 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f35185d48a06 (Metraipolis archive dc_f35185d48a06, sha256 c279a920ef8d8e295dc808aa9fa2baf43b288f1bb6ece8249e43128a7e0bc543)
BibTeX
@misc{dcf35185d48a06,
  title = {GitHarness: Git Init Your Harness Working Memory for Perpetual User Requirements — arXiv:2609.36789},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.36789},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f35185d48a06; sha256 c279a920ef8d8e295dc808aa9fa2baf43b288f1bb6ece8249e43128a7e0bc543},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36789. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

LLM-based agents increasingly collaborate with users on long-horizon tasks, accumulating evidence, code, and drafts through extensive search, reasoning, and execution. As users inspect these results, they may supply missing information requirement completion, introduce new requirements requirement elicitation, or revise existing ones requirement shift. These changes often affect only part of the accumulated work, yet agents may carry forward obsolete information or turn local revisions into global rewrites. Existing approaches clarify current intent without determining how prior work should change, or reuse execution histories under a fixed objective. We address this gap by formulating dynamic-requirement collaboration as joint requirement tracking and local update. We introduce GitHarness, a pluggable Git-style framework that organizes requirement states and their corresponding harness work states into a branchable version history. A trainable Git Agent resolves requirement changes and selects a semantically compatible historical state. A unified version interface then restores that state and creates a new branch, enabling the underlying harness to exclude obsolete information, inherit compatible work, and focus execution on affected parts. The Git Agent is trained through interface-level black-box reinforcement learning, with downstream harnesses and task-execution models kept fixed. We also construct MTAgentBench, a verifier-preserving benchmark covering mathematical reasoning, text-to-SQL, agentic search, software engineering, and research synthesis. Experiments demonstrate strong task performance alongside effective requirement tracking, preservation of valid work, and efficient execution.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.MA).
Categorie arXiv: Multiagent Systems (cs.MA) ; Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2609.36789 — 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 2026-10-07T15:54:11.800Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).