# MDA让LLM提假设，8次实验追平Opus 4.7

- 来源：Rohan Paul (@rohanpaul_ai)
- 发布时间：2026-08-16 19:15
- AIHOT 分数：35
- AIHOT 链接：https://aihot.virxact.com/items/cmsvpvalq0658rovmdnx49y1s
- 原文链接：https://x.com/rohanpaul_ai/status/2088947644689477948

## AI 摘要

新方法MDA将LLM限定为假设生成器，用贝叶斯推理评分机制、信息价值选择实验，避免让模型自行判断证据含义。在FORCEBENCH上，MDA用8次实验达到未限流Opus 4.7智能体约41次实验的准确率，数值通过率93%对31%。

## 正文

LLMs can suggest scientific mechanisms, but this paper finds that letting the agent choose experiments and fit the mechanism is far less data-efficient.

So scientific agents may work better when the LLM proposes hypotheses but does not decide what the evidence means.

MDA turns the LLM into the hypothesis generator. Bayesian inference scores the candidate mechanisms, and value-of-information chooses the next experiment where those mechanisms disagree most.

That changes the experiment budget dramatically.

On FORCEBENCH, MDA reaches roughly the accuracy of an unthrottled Opus 4.7 agent using 8 experiments instead of about 41, while reaching a 93% numeric pass rate versus 31% for the budget-matched Opus 4.7 LLM agent.

The mechanism is easy to see in the examples: for Yukawa forces, it probes long range because the competing laws look identical nearby; for Coulomb, it changes source charge because moving the probe alone cannot separate the true law from a charge-blind fit.

When predictions still fail, MDA asks the LLM for new mechanisms and repeats the loop.

Let LLMs propose scientific ideas, but let explicit uncertainty and designed experiments decide what survives.