Metraipolis › archive › dc_804255136f57

TTSE: A Two-Track Online Self-Evolution Framework — arXiv:2609.24289

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.24289
License (as archived)
CC0-1.0
Archived
2026-10-09T07:07:38.823Z
SHA-256 of the archived text
e0298ab6aa5710681bbd93364f28f18cbe16e22f4a361f60d66f88cf9979677b
Stable URL of this page
https://metraipolis.com/documento/dc_804255136f57

How to cite

TTSE: A Two-Track Online Self-Evolution Framework — arXiv:2609.24289 — arXiv (en), https://arxiv.org/abs/2609.24289 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_804255136f57 (Metraipolis archive dc_804255136f57, sha256 e0298ab6aa5710681bbd93364f28f18cbe16e22f4a361f60d66f88cf9979677b)
BibTeX
@misc{dc804255136f57,
  title = {TTSE: A Two-Track Online Self-Evolution Framework — arXiv:2609.24289},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.24289},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_804255136f57; sha256 e0298ab6aa5710681bbd93364f28f18cbe16e22f4a361f60d66f88cf9979677b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.24289. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

As Large Language Model (LLM) agents are applied in continuously interactive environments, driving the evolution of their own capabilities becomes a core problem for achieving long-term autonomy. Currently, environmental knowledge is typically treated as an external fixed input rather than as part of the agent's ongoing evolution. Reinforcement learning methods usually optimize policies through environmental interaction but tend to adapt only to fixed task distributions or single environments. This paper proposes TTSE (Two-Track Self-Evolution), a dual-track online self-evolution framework that separates evolving knowledge into FACT (environmental facts, whose reliability is continuously verified through interaction evidence) and TIP (task-conditioned implementation procedures). From a decision-theoretic perspective, we decompose the agent's excess risk into environment-representation regret and conditional-execution regret, characterize the conditions under which environment-conditioned policies strictly outperform condition-agnostic policies, and bound the downstream risk in terms of FACT identification error and cross-condition mismatch cost. In practice, TTSE's ablation experiments on GDPevo validate the advantage of dual-track evolution. On the classic agent task benchmarks ALFWorld and ScienceWorld, TTSE further demonstrates superior task adaptation. Moreover, TTSE is broadly compatible with existing skill self-evolution methods; combined with the Bayesian-Agent algorithm, a single-track ablation validates the dual-track advantage, substantially improving the aggregate score across the five major domains of SOPBench over three independent repetitions. Finally, on the real end-to-end task benchmark PinchBench, TTSE is integrated into a general agent framework via retrieval-based injection and stably outperforms the baseline across three independent runs.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.24289 — 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 2026-10-09T06:58:09.391Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).