Forethought：用神经符号原语编程实现可验证推理
Forethought: Verifiable Reasoning from Neurosymbolic Primitive Programming
AI 导读
arXiv 论文 Forethought 提出用类型化 DSL 组合符号与神经原语的神经符号推理系统，将模型推理表示为逐步带输出契约、设计时校验并执行时强制的推理程序。作为工具调用执行内核在四个工具调用基准上评测，相对直接提示同一基座模型，端到端准确率中位数提升 32%，聚合准确率达到评测配置中最高，但对前沿模型的领先幅度在单次运行噪声内；移除契约与控制层后大部分收益消失。
正文 · 原文
Abstract:Modern agentic workflows decompose user requests into sequences of tool calls with correctly resolved parameters, the results of which are processed through reasoning traces in the language model's context window. The prevailing route to improving such reasoning is test-time scaling, which trains models to search over long chains of thought; but the resulting capability is entangled in model weights, cannot be checked step by step, and is costly at inference. We present Forethought, a neurosymbolic reasoning system built from a library of symbolic and neural primitives composed through a typed domain-specific language. The results are reasoning programs: concrete representations of the model's work, in which every step carries an output contract that is checked at design time and enforced at execution time. Symbolic steps hold by construction, while learned steps are contract-checked and empirically validated, giving an explicit boundary between what is guaranteed and what is measured. Instantiated as a tool-calling execution kernel and evaluated on four standard tool-calling benchmark suites, Forethought improves end-to-end accuracy by a median of 32% relative to prompting the same base model directly, and reaches the highest aggregate accuracy among the evaluated configurations, though only by a margin within single-run noise over a frontier model. Systems pairing small open models with Forethought's fixed small-model layer match that frontier model, and a pipeline with a non-reasoning responder outperforms its reasoning sibling while requiring only a single fine-tuning stage. Removing the contract-and-control layer erases most of these gains, showing that checked structure, not decomposition alone, drives the improvement. Our results show the potential of rich symbolic orchestrators for building language-model agents that are more accurate, reliable, and auditable.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2607.04096 [cs.AI] |
| (or arXiv:2607.04096v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2607.04096 arXiv-issued DOI via DataCite |
Submission history
From: Asad Aali [view email]
[v1]
Sun, 5 Jul 2026 03:20:23 UTC (58 KB)
[v2]
Tue, 10 Nov 2026 00:16:50 UTC (54 KB)
来源：arXiv cs.AI · arxiv.org