---
title: "PRIME: Predictive Routing of Interventions by Modeling Effects for Scientific Ideation"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.03055v1"
permalink: "https://feed.astralor.com/items/itm_1308aa4f4f298bc1a1fdde06"
published: "2026-11-02T12:49:33.000Z"
score: 60
channel: "ai"
tags: ["LLM","多模态","PRIME","Predictive Routing","Interventions","Modeling Effects","Scientific Ideation Feedback-driven","LLM-generated"]
---

# PRIME: Predictive Routing of Interventions by Modeling Effects for Scientific Ideation

## 速览

Feedback-driven iteration is widely used to improve LLM-generated scientific ideas, but existing systems either leave revision decisions implicit in generation, align revisions with feedback-localized weaknesses, or res…

## 关键点

- Feedback-driven iteration is widely used to improve LLM-generated scientific ideas, but existing systems either leave revision decisions implicit in generation, align revisions with feedback-localized weaknesses, or res…
- This is problematic because problems, hypotheses, and solutions are interdependent: the location where a weakness manifests does not itself determine the revision scope that will produce a better successor.
- We term this phenomenon diagnosis-intervention mismatch.

## 全文

Feedback-driven iteration is widely used to improve LLM-generated scientific ideas, but existing systems either leave revision decisions implicit in generation, align revisions with feedback-localized weaknesses, or restrict action selection to system-specific operations. This is problematic because problems, hypotheses, and solutions are interdependent: the location where a weakness manifests does not itself determine the revision scope that will produce a better successor. We term this phenomenon diagnosis-intervention mismatch. We introduce Predictive Routing of Interventions by Modeling Effects (PRIME), a plug-and-play feedback-to-revision decision layer for existing scientific ideators. PRIME operates in three stages: (1) Structural Attribution interprets feedback over the problem-hypothesis-solution structure without fixing a revision target; (2) Counterfactual Routing constructs alternative scope-conditioned interventions and compares their projected successor utility and risks through lightweight rollouts; and (3) Intervention Execution compiles the selected intervention into an ordered generator-facing plan with semantic actions, preservation constraints, and dependency requirements for successor generation. We validate diagnosis intervention mismatch on 112 human-annotated idea-feedback pairs. Across four benchmarks, two ideators, and fixed- and open-problem settings, PRIME improves successor quality and routing reliability over strong baselines; removing counterfactual routing reduces quality from 3.463 to 1.960 and increases route regret from 0.426 to 1.929, confirming cross-scope effect modeling as the primary source of its gains.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_1308aa4f4f298bc1a1fdde06