Metraipolis › archive › dc_5d95db2a28fb
Divide, Diagnose, and Compose: Optimizing Agentic Pipelines and Harnesses — arXiv:2611.08723
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.08723
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-09T22:33:30.370Z
- SHA-256 of the archived text
5abfc29e2c46c1333ed84e10cb033860cb7f3b34bf91f6525dd266809c223369- Stable URL of this page
https://metraipolis.com/documento/dc_5d95db2a28fb
How to cite
Divide, Diagnose, and Compose: Optimizing Agentic Pipelines and Harnesses — arXiv:2611.08723 — arXiv (en), https://arxiv.org/abs/2611.08723 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5d95db2a28fb (Metraipolis archive dc_5d95db2a28fb, sha256 5abfc29e2c46c1333ed84e10cb033860cb7f3b34bf91f6525dd266809c223369)
BibTeX
@misc{dc5d95db2a28fb,
title = {Divide, Diagnose, and Compose: Optimizing Agentic Pipelines and Harnesses — arXiv:2611.08723},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.08723},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5d95db2a28fb; sha256 5abfc29e2c46c1333ed84e10cb033860cb7f3b34bf91f6525dd266809c223369},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08723. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Building agentic pipelines that achieve high task performance while keeping cost and latency low requires jointly optimizing heterogeneous and coupled design choices, including prompts, topology, model selection, and tool policies. Manually searching this combinatorial design space is expensive and time-consuming, while existing automated optimizers typically operate within a predefined subset of this space, modify the pipeline monolithically, or provide little structured evidence for pipeline changes. To mitigate these challenges, we introduce the Decomposed Credit-Assignment Framework (DeCAF), which adapts the design space to the given benchmark and pipeline, optimizes each dimension separately, and generates reasoning traces for every decision. Given a task specification, benchmark examples, and a seed pipeline, DeCAF identifies relevant optimization dimensions and generates diverse experimental hypotheses for each. Independent coding-agent sessions then optimize each dimension under a restricted edit scope, jointly evaluating performance, inference cost, and latency while recording all hypotheses, edits, and outcomes of each experiment. A final synthesis session combines compatible findings across all dimensions and uses a component-level trajectory evaluator, which derives role-specific rubrics from each agent's instructions, to localize underperforming components and guide cross-dimension revisions. Across a diverse suite of agentic benchmarks, DeCAF improves average task performance by 2.58 percentage points, while reducing inference cost by 4.30% and end-to-end latency by 42.45% compared to the best overall baseline. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno). Categorie arXiv: Multiagent Systems (cs.MA). Pagina del lavoro: https://arxiv.org/abs/2611.08723 — 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 2026-11-09T22:30:32.043Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).