Metraipolis › archive › dc_4a4a35532002

Beyond the Capability Boundary: Zeroth-Order Optimization for Self-Evolving LLM Agents — arXiv:2608.09292

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.09292
License (as archived)
CC0-1.0
Archived
2026-10-19T08:50:56.589Z
SHA-256 of the archived text
07af70f073d16142ab67e3bf12b92448785e944f8294f6e04c6a9252322920ce
Stable URL of this page
https://metraipolis.com/documento/dc_4a4a35532002

How to cite

Beyond the Capability Boundary: Zeroth-Order Optimization for Self-Evolving LLM Agents — arXiv:2608.09292 — arXiv (en), https://arxiv.org/abs/2608.09292 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4a4a35532002 (Metraipolis archive dc_4a4a35532002, sha256 07af70f073d16142ab67e3bf12b92448785e944f8294f6e04c6a9252322920ce)
BibTeX
@misc{dc4a4a35532002,
  title = {Beyond the Capability Boundary: Zeroth-Order Optimization for Self-Evolving LLM Agents — arXiv:2608.09292},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.09292},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4a4a35532002; sha256 07af70f073d16142ab67e3bf12b92448785e944f8294f6e04c6a9252322920ce},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.09292. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Self-evolving methods improve the capabilities of LLM agents by sampling trajectories from the underlying LLMs and learning from these trajectories. However, these methods struggle to learn beyond the inherent capability boundary of the agents, since the agents cannot sample correct trajectories on difficult examples for further improvements. In this paper, we propose a zeroth-order self-evolution framework that enables agents to learn beyond their capability boundary by perturbing LLM parameters to adapt to difficult examples without any trajectory annotations. Specifically, we perturb LoRA parameters of LLMs, run the agent, compute the losses under the perturbed and original parameters, and use the loss difference to estimate gradients and further update the LoRA parameters. We sample trajectories using the updated LLMs for supervised fine-tuning to break through the capability boundary of the agents, forming a closed self-evolution loop. We introduce a parallel perturbation inference mechanism and an adaptive lookup mechanism to reduce time consumption in zeroth-order optimization, with an answer perplexity loss that provides smooth and stable zeroth-order loss values. Experiments on multiple deep research benchmarks show that our method obtains substantially more successful trajectories and consistently outperforms strong baselines, especially on difficult examples. The code and released artifacts are available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-11 in cs.CL).
Categorie arXiv: Machine Learning (cs.LG) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.09292 — 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 2026-10-19T08:49:42.003Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).