Metraipolis › archive › dc_835da62ca1ca

TROVE: Adaptive Agent Skill Orchestration via Trace-Grounded Route Validation and Editing — arXiv:2609.05019

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.05019
License (as archived)
CC0-1.0
Archived
2026-10-16T22:21:07.163Z
SHA-256 of the archived text
06e5d3ced27997489bf0537828c395e46c52e46be80ba6646da93f1d1b11d226
Stable URL of this page
https://metraipolis.com/documento/dc_835da62ca1ca

How to cite

TROVE: Adaptive Agent Skill Orchestration via Trace-Grounded Route Validation and Editing — arXiv:2609.05019 — arXiv (en), https://arxiv.org/abs/2609.05019 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_835da62ca1ca (Metraipolis archive dc_835da62ca1ca, sha256 06e5d3ced27997489bf0537828c395e46c52e46be80ba6646da93f1d1b11d226)
BibTeX
@misc{dc835da62ca1ca,
  title = {TROVE: Adaptive Agent Skill Orchestration via Trace-Grounded Route Validation and Editing — arXiv:2609.05019},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.05019},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_835da62ca1ca; sha256 06e5d3ced27997489bf0537828c395e46c52e46be80ba6646da93f1d1b11d226},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.05019. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Agents tend to optimize, select, or constrain execution structures before decisive runtime outcomes are observed. However, such pre-execution commitment creates an orchestration bottleneck: when intermediate evidence invalidates the pending continuation, agents must either execute stale steps or replan broadly, compounding errors, wasting computation, and discarding progress. We thus propose Trace-grounded Route Orchestration via Validation and Editing (TROVE), which revises only what runtime evidence invalidates. Offline, TROVE distills evaluated workflow-search traces into atomic and composite skills and an outcome-conditioned transition graph, preserving stable fragments while exposing outcome-dependent decisions. Online, it treats a planned route as provisional: after committing one top-level skill, the controller retains a valid continuation, inserts a trace-supported local response, or replaces only the invalid suffix. Evaluation across code-generation, question-answering, and math reasoning benchmarks with different LLM backbones show that TROVE delivers a stronger quality-efficiency trade-off than existing baselines of dataset-level optimization, query-level architecture selection, and graph-constrained scheduling. Quality gains are largest when outcomes change the appropriate continuation, whereas early termination yields substantial efficiency gains on near-saturated tasks. Ablations further show that composite skills capture most offline benefits, insertion enables local correction, and suffix replacement primarily improves efficiency. These findings establish selective route editing as a general principle for adaptive agent orchestration.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-07 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.05019 — 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 2026-10-16T22:18:11.424Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).