Metraipolis › archive › dc_ed95d3574067

From Watching to Steering: Enabling Human-Coding Agent Collaboration through Execution Traces — arXiv:2611.04466

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.04466
License (as archived)
CC0-1.0
Archived
2026-11-04T21:40:03.591Z
SHA-256 of the archived text
81e88cae79d90b9a8bc695e69c89620c215054a3231ad169821203d1bd452bb4
Stable URL of this page
https://metraipolis.com/documento/dc_ed95d3574067

How to cite

From Watching to Steering: Enabling Human-Coding Agent Collaboration through Execution Traces — arXiv:2611.04466 — arXiv (en), https://arxiv.org/abs/2611.04466 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ed95d3574067 (Metraipolis archive dc_ed95d3574067, sha256 81e88cae79d90b9a8bc695e69c89620c215054a3231ad169821203d1bd452bb4)
BibTeX
@misc{dced95d3574067,
  title = {From Watching to Steering: Enabling Human-Coding Agent Collaboration through Execution Traces — arXiv:2611.04466},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04466},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ed95d3574067; sha256 81e88cae79d90b9a8bc695e69c89620c215054a3231ad169821203d1bd452bb4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04466. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent advances in large language models (LLMs) have enabled coding agents to autonomously perform complex software development tasks, yet their long-running execution remains difficult for users to inspect, understand, and steer. We present Vibetrace, an interactive trace visualization and intervention system for agentic programming built upon OpenCode. Vibetrace introduces a human-agent collaboration paradigm of Observe, Understand, Intervene, and Evolve. It (1) visualizes agent workflows as interactive execution traces for inspecting actions, intermediate states, and failures; (2) enables users to fork execution from prior steps and provide targeted corrections without restarting validated progress; and (3) distills traces and human feedback into reusable skills for continual agent evolution. On SWE-bench Verified, distilled skills reduce input tokens by 23.0% and cost by 15.5%, while improving pass rate from 65.0% to 68.0%. User studies further demonstrate improved accuracy and efficiency over conventional log-based interaction.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Human-Computer Interaction (cs.HC) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.04466 — 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 2026-11-04T21:35:49.671Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).