Learning to Formalize：用候选形式化器衔接开放式任务与快速决策模型
Learning to Formalize: Bridging Open-Ended Workloads and Fast Decision Models
AI 导读
该 arXiv 论文提出用一个由离线教师生成候选列表训练的小型形式化器，将开放式任务转化为显式候选选项，再由冻结的决策模型快速选择，弥合生成式 LLM 与快速决策模型之间的接口鸿沟。
正文 · 原文
Abstract:Decision models offer fast choices over sup- plied alternatives, while general-purpose large language models interpret open-ended tasks through flexible generation and reasoning at the cost of sequential decoding. Many work- loads expect a generative backend to determine what can be done and therefore provide no well-defined candidate list. We bridge this in- terface gap with a small candidate formalizer trained on offline teacher-generated lists. The formalizer constructs explicit, validated alter- natives from task context, and a frozen deci- sion model selects an entry. A motivating com- parison with official TypeSafe Jev-1.13.0 on 200 CALVIN-D test episodes reports 11% suc- cess with generic motions versus 46.5% with DeepSeek V4 Flash pose candidates. Sepa- rately, a six-arm privileged-state evaluation on 1,011 CALVIN-D validation annotations finds that a locally deployed decision model can achieve at most 52.6% task success rate with the fine-tuned formalizer, compared with 11.8% without it, and the end-to-end latency is kept to 2.09 s, whereas Qwen3.5-27B is 3.67 s with the exact experiment setting.
| Comments: | 10 pages, 2 figures, only for concept verification now |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.36595 [cs.AI] |
| (or arXiv:2610.36595v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.36595 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Chengxuan Pei [view email]
[v1]
Tue, 27 Oct 2026 03:56:32 UTC (131 KB)
来源：arXiv cs.AI · arxiv.org