Metraipolis › archive › dc_7eedaf00eb85
Verify--Backtrack Loop: Structured Precondition Recovery for Long-Horizon Language Agents — arXiv:2610.41564
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.41564
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T07:31:37.268Z
- SHA-256 of the archived text
af0d31a06c6109749a2f90a7fedb263e702557c75144bceca475dd8a71426ca6- Stable URL of this page
https://metraipolis.com/documento/dc_7eedaf00eb85
How to cite
Verify--Backtrack Loop: Structured Precondition Recovery for Long-Horizon Language Agents — arXiv:2610.41564 — arXiv (en), https://arxiv.org/abs/2610.41564 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7eedaf00eb85 (Metraipolis archive dc_7eedaf00eb85, sha256 af0d31a06c6109749a2f90a7fedb263e702557c75144bceca475dd8a71426ca6)
BibTeX
@misc{dc7eedaf00eb85,
title = {Verify--Backtrack Loop: Structured Precondition Recovery for Long-Horizon Language Agents — arXiv:2610.41564},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.41564},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7eedaf00eb85; sha256 af0d31a06c6109749a2f90a7fedb263e702557c75144bceca475dd8a71426ca6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41564. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Language agents increasingly tackle long-horizon tasks in interactive environments, where actions often depend on latent preconditions. The core difficulty is not trajectory length but recovery: when a prerequisite is missing or an earlier decomposition fails, trying another plausible action rarely helps. ReAct and later reflection or adaptive-planning methods support local correction, but express recovery as free-form text, with no explicit control state linking the terminal goal, the active goal, and the failure source. We introduce the Verify--Backtrack Loop (VBL), a training-free extension of ReAct that turns precondition discovery and failure diagnosis into structured planning-state updates. VBL maintains the task decomposition as a bounded goal stack and, on goal activation, execution failure, or material state change, jointly verifies two horizons---whether the active goal contributes to the terminal goal and whether it is feasible in the current state. These dual-horizon judgments, combined with typed failure attribution, trigger explicit operations---Push, Pop, retry, or BacktrackTo the parent. We evaluate VBL with Qwen3.5-9B, GPT-4o, and DeepSeek-V3.2 on AppWorld, ALFWorld, and ScienceWorld. VBL improves over ReAct and reflection-based control on every backbone--benchmark pair. On the challenging AppWorld setting, it improves task success by up to 22.07 percentage points over ReAct. Ablations show that removing either verification or diagnosis degrades performance, in several settings below ReAct, confirming that the two mechanisms are complementary. These results show that reliable long-horizon interaction benefits from revising the planning state, not merely the next action. 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/2610.41564 — 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 2026-11-03T07:29:33.633Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).