Metraipolis › archive › dc_e2b4d7437248

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? — arXiv:2608.00155

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.00155
License (as archived)
CC0-1.0
Archived
2026-10-31T12:42:36.947Z
SHA-256 of the archived text
88c7d7d0517d34c35f4aa8fe04b6be51a4cd79e70a25a65434a373895a0663f7
Stable URL of this page
https://metraipolis.com/documento/dc_e2b4d7437248

How to cite

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? — arXiv:2608.00155 — arXiv (en), https://arxiv.org/abs/2608.00155 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e2b4d7437248 (Metraipolis archive dc_e2b4d7437248, sha256 88c7d7d0517d34c35f4aa8fe04b6be51a4cd79e70a25a65434a373895a0663f7)
BibTeX
@misc{dce2b4d7437248,
  title = {AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? — arXiv:2608.00155},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.00155},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e2b4d7437248; sha256 88c7d7d0517d34c35f4aa8fe04b6be51a4cd79e70a25a65434a373895a0663f7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.00155. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language model (LLM) agents can self-evolve by continually improving from their own accumulated experience. However, existing studies predominantly adopt independent evaluation. Consequently, the behavior of self-evolving agents in realistic streaming settings, where agents adapt to diverse and complex task streams, remains poorly understood. To address this gap, we introduce AgentStream, a unified framework that evaluates self-evolving agents spanning diverse evolution components by organizing agentic benchmarks into a configurable task stream and instantiating the \texttt{Isolated}, \texttt{Sequential}, and \texttt{Interleaved} streaming scenarios at test time, which progressively vary the scope and domain composition of the stream. Over these scenarios, we combinatorially evaluate five representative self-evolving methods across three frontier foundation models, disentangling how model capability, method architecture, and streaming scenario jointly shape self-evolution. Our results show that self-evolution reliability varies across streaming scenarios, the benefit of self-evolution is gated by model capability and is non-monotonic in model strength, and no single method dominates across models and scenarios. These findings offer concrete guidance for selecting self-evolving methods across models and streaming scenarios. Overall, we advocate that self-evolving agents should be evaluated under realistic task streams rather than isolated single-task settings.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.LG).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.00155 — 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 2026-10-31T12:31:30.387Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).