Metraipolis › archive › dc_e8b07a708ca3

Self-Evolving Agentic Workflows via Semantic Decomposition of Complex Tasks — arXiv:2611.01840

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.01840
License (as archived)
CC0-1.0
Archived
2026-11-03T10:19:43.319Z
SHA-256 of the archived text
ac43090ebb1ea39882c20109840c210a118ba95c44a494443f7ebc7b83bd3c36
Stable URL of this page
https://metraipolis.com/documento/dc_e8b07a708ca3

How to cite

Self-Evolving Agentic Workflows via Semantic Decomposition of Complex Tasks — arXiv:2611.01840 — arXiv (en), https://arxiv.org/abs/2611.01840 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e8b07a708ca3 (Metraipolis archive dc_e8b07a708ca3, sha256 ac43090ebb1ea39882c20109840c210a118ba95c44a494443f7ebc7b83bd3c36)
BibTeX
@misc{dce8b07a708ca3,
  title = {Self-Evolving Agentic Workflows via Semantic Decomposition of Complex Tasks — arXiv:2611.01840},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01840},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e8b07a708ca3; sha256 ac43090ebb1ea39882c20109840c210a118ba95c44a494443f7ebc7b83bd3c36},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01840. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Agentic workflows organize complex tasks into reusable procedures. However, invoking an LLM at every step incurs repeated inference costs and delays. We propose a framework for self-evolving agentic workflows through semantic task decomposition. Each subtask has explicit applicability conditions and a procedure that executes code or invokes a model as needed. An agent uses execution feedback to refine the decomposition and update these procedures. Experiments in the GLEE competition show the framework on bargaining, negotiation and persuasion. Most observed final-decision procedures are implemented in code. Code is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2611.01840 — 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 2026-11-03T10:19:34.833Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).