跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-22AI 評分45

SCOPE:將自然語言政策編譯為神經符號謂詞程式

SCOPE: Compiling Natural-Language Policies into Neurosymbolic Predicate Programs

AI 導讀

SCOPE 將複合政策編譯成由小型模型、確定性提取器及程式碼組成的神經符號程式,用於執行政策檢查。程式透過針對偏離政策之處生成對抗性反例,與訓練資料共同最佳化,並在多項政策任務中取得最高平均準確率。它可轉移至其他模型而毋須再次最佳化,準確率媲美前沿推理模型,預測更穩定,亦可透過謂詞輸出解讀判定結果。

正文

Published on Oct 22

·

Submitted by

Levi

on Oct 23

Authors:

Abstract

SCOPE compiles compound policies into optimized neural-symbolic programs that achieve high accuracy, stability, and interpretability on inexpensive models.

Policy enforcement for LLM agents has shifted from single-turn content moderation to compound, application-specific policies evaluated over multi-turn transcripts and tool-call trajectories. Fine-tuned guardrail models are efficient but degrade on compound policies, and while LLM-as-a-judge approaches achieve higher accuracy, they incur high inference cost and tend to produce unstable predictions. Neurosymbolic methods offer a natural alternative, decomposing the policy into narrow neural decisions composed under explicit logic. However, existing symbolic layers lack the required expressiveness and are optimized against fixed data rather than the policy itself. To address this, we introduce SCOPE, which compiles a policy into an executable program of neural predicates executed by small models, deterministic extractors, and code that composes their outputs. The program is optimized jointly with its training data, using adversarial generation of counterexamples that target where the program deviates from the policy. We evaluate SCOPE on a benchmark of real-world policy tasks against prompt optimization, task decomposition, and workflow generation methods, achieving the highest average accuracy across tasks and models. Programs optimized with the weakest executor transfer to other models without further optimization. This allows them to be deployed in production on inexpensive models, where they reach accuracy comparable to frontier reasoning models. Unlike these monolithic models, SCOPE produces substantially more stable predictions, and each verdict is interpretable through the predicate outputs that produced it. Additionally, we validate the key components of our method through an ablation study. SCOPE thus enables reliable, interpretable, and efficient policy enforcement at production scale.

View arXiv page View PDF Project page Add to collection

Get this paper in your agent:

hf papers read 2610.31062

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.31062 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.31062 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.31062 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co