# CREST 论文提出多轮智能体的验证器约束信用分配方法

- 来源：Rohan Paul (@rohanpaul_ai)
- 发布时间：2026-09-01 02:12
- AIHOT 分数：39
- AIHOT 链接：https://aihot.virxact.com/items/cmthkafsw03flro1pgr1pk9gx
- 原文链接：https://x.com/rohanpaul_ai/status/2094488388816499099

## AI 摘要

论文《Teach the Magnitude, Not the Direction》提出 CREST 框架，为多轮多步 LLM 智能体做分层信用分配：每轮单独获得验证的信用，再由同一模型充当自教师，对轮内不确定决策加大学习权重，但教师只能调节更新幅度、不能推翻验证器的判断。

## 正文

This paper shows a better way to train multi-turn agents:

score each turn separately, then use a self-teacher to focus learning without letting it override the reward.

Standard RL has a basic problem.

A long agent session can contain successful and failed turns, yet 1 overall reward can blur them together.

CREST fixes that by giving each turn its own verified credit, then using the same model as a teacher to put more learning weight on uncertain decisions inside that turn.

The teacher can strengthen an update, but it cannot reverse the verifier's judgment.

On Qwen3-4B-Instruct, it reaches 52.0% average BFCL V3 accuracy versus 49.25% for the strongest RL baseline.

– arxiv. org/abs/2608.13179

Title: "Teach the Magnitude, Not the Direction: Verifier-Bounded Credit Assignment for Multi-Turn Multi-step LLM Agents"