Metraipolis › archive › dc_6cf76393f150
Consistent Plan-Act for Long-Horizon Agentic Tasks — arXiv:2609.38891
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.38891
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T12:42:18.760Z
- SHA-256 of the archived text
d25a9ebb0d210398f60e08f0e05dd8194263ad186b1daa79f2a8dacfbd500f85- Stable URL of this page
https://metraipolis.com/documento/dc_6cf76393f150
How to cite
Consistent Plan-Act for Long-Horizon Agentic Tasks — arXiv:2609.38891 — arXiv (en), https://arxiv.org/abs/2609.38891 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6cf76393f150 (Metraipolis archive dc_6cf76393f150, sha256 d25a9ebb0d210398f60e08f0e05dd8194263ad186b1daa79f2a8dacfbd500f85)
BibTeX
@misc{dc6cf76393f150,
title = {Consistent Plan-Act for Long-Horizon Agentic Tasks — arXiv:2609.38891},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.38891},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6cf76393f150; sha256 d25a9ebb0d210398f60e08f0e05dd8194263ad186b1daa79f2a8dacfbd500f85},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38891. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Long-horizon agentic tasks demand strong reasoning and efficient execution across successive interactions with dynamic environments. A common approach decouples high-level planning from low-level execution through separate planner and actor roles. To investigate coordination failures in these tasks, we prompt both agents for structured state assertions and compare their reports programmatically to detect explicit contradictions. Our analyses reveal systematic disagreement about the same task-relevant state facts, a phenomenon we term planner-actor state mismatch. We further find that providing agents with task-relevant state information reduces mismatch and improves coordination and task performance. Based on the systematic analysis of the state mismatch, we propose Consistent Plan-Act (ConPAct), which feeds detected contradictions back to both agents to form consistent state interpretations and fine-tunes them on curated consistent interactions for better coordination. ConPAct improves performance across various environments and model configurations, e.g., increasing MiniGrid success rate from 38.6% to 54.4% with GPT-5.6-sol/terra as planner and actor respectively, demonstrating that state consistency can guide both inference-time correction and coordination training. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.38891 — 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 2026-10-07T12:14:13.706Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).