Metraipolis › archive › dc_0d910ad15474

FLEET: From Logits Entropy to Enhanced Trajectories in Text Generation — arXiv:2609.27657

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.27657
License (as archived)
CC0-1.0
Archived
2026-10-08T09:12:54.415Z
SHA-256 of the archived text
5e41d86c2eac8026a6d44eb6c3fa4544076964daf5674a4f2ec33595aafe0b91
Stable URL of this page
https://metraipolis.com/documento/dc_0d910ad15474

How to cite

FLEET: From Logits Entropy to Enhanced Trajectories in Text Generation — arXiv:2609.27657 — arXiv (en), https://arxiv.org/abs/2609.27657 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0d910ad15474 (Metraipolis archive dc_0d910ad15474, sha256 5e41d86c2eac8026a6d44eb6c3fa4544076964daf5674a4f2ec33595aafe0b91)
BibTeX
@misc{dc0d910ad15474,
  title = {FLEET: From Logits Entropy to Enhanced Trajectories in Text Generation — arXiv:2609.27657},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.27657},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0d910ad15474; sha256 5e41d86c2eac8026a6d44eb6c3fa4544076964daf5674a4f2ec33595aafe0b91},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27657. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Solutions based on large language models (LLMs) often rely on temperature sampling to improve accuracy and stability by aggregating multiple samples from the completion distribution. However, this memoryless approach is inherently suboptimal: because it lacks awareness of prior generations and their evaluations, it produces an increasing proportion of semantically duplicate answers as more samples are drawn, leading to diminishing returns. To address this limitation, we introduce FLEET, a novel method that integrates a memory mechanism into the generation process. FLEET represents each generation as a sparse trajectory through states whose entropy exceeds a predefined threshold and uses these trajectories to infer per-token utility scores that adjust the logits. Benchmark evaluations demonstrate that FLEET achieves the same accuracy as the repeated sampling baseline, with a 3x speedup, and substantially improves accuracy on complex coding tasks (LiveCodeBench Pass@32 increases from 59.9% to 66.2%) under the same budget. Furthermore, in the greedy-decoding configuration evaluated here, the approach is deterministic and uses a single calibration pass to derive its principal hyperparameters, requiring only minimal modifications to existing LLM pipelines.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-24 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.27657 — 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 2026-10-08T08:13:26.703Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).