Metraipolis › archive › dc_62bef4cf6ba7

Thinking Before Thinking: Scaling Agentic Inference Through Meta-Reasoning — arXiv:2609.38147

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.38147
License (as archived)
CC0-1.0
Archived
2026-10-07T16:24:32.803Z
SHA-256 of the archived text
498c5c6fde5c8cacd788d7b91ce98a5c87c99d86e218afec2136e4589f0f3666
Stable URL of this page
https://metraipolis.com/documento/dc_62bef4cf6ba7

How to cite

Thinking Before Thinking: Scaling Agentic Inference Through Meta-Reasoning — arXiv:2609.38147 — arXiv (en), https://arxiv.org/abs/2609.38147 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_62bef4cf6ba7 (Metraipolis archive dc_62bef4cf6ba7, sha256 498c5c6fde5c8cacd788d7b91ce98a5c87c99d86e218afec2136e4589f0f3666)
BibTeX
@misc{dc62bef4cf6ba7,
  title = {Thinking Before Thinking: Scaling Agentic Inference Through Meta-Reasoning — arXiv:2609.38147},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.38147},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_62bef4cf6ba7; sha256 498c5c6fde5c8cacd788d7b91ce98a5c87c99d86e218afec2136e4589f0f3666},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38147. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

As agents take on longer and more complex problems, controlling the execution becomes a task in its own right. Each step in the run brings new control choices, like which partial work to build on, whether to start fresh, or when to stop. We introduce agentic meta-reasoning, an inference-time harness that makes these choices an explicit and structured reasoning process. Workers carry out the task-level computation, while a controller consolidates what the run has established, explores next options, assesses what each option is worth under the remaining budget, and dispatches the chosen work with context drawn from persistent memory. Between decisions the controller carries only a compact account of the run rather than replaying its full history. Our baselines span production coding agents and research harnesses, together with a Direct Control Agent using the same workers and compute budget allowance. On ProgramBench, which tests long-horizon agentic capability through program reconstruction, meta-reasoning achieves 71.5% with GPT-5.5 against 58.0% for Codex; with Opus 4.8 it achieves 67.2% against 65.5% for Claude Code. On the other benchmarks, spanning abstract reasoning, multi-domain long-horizon reasoning, and proof generation, it gains between 3.6 and 4.2 points over direct control, averaged across three frontier models. It keeps improving over the tested budget ranges where direct control plateaus, though its overhead can hurt at small budgets. Artifact-graph analysis reveals more reuse of earlier work, higher coverage of correct solutions in most settings, and nonuniform gains in final selection. These results indicate that spending computation on structured control becomes more important as agents scale to longer runs.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.38147 — 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 2026-10-07T15:54:53.695Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).