跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 27 天前AI 評分46

Thinking-in-Bets 如何減少 LLM 智能體迎合用戶而修改答案

Thinking-in-Bets at Test Time Reduces Sycophantic Revisions in LLM Agents

AI 導讀

Thinking-in-Bets 讓 LLM 智能體在閲讀用戶反饋前記錄已核實的主張、佐證和信心,減少因錯誤質疑而推翻正確工作或作出不必要修改。研究在五個 Gemini 模型及八項基準測試中評估此免訓練方法,發現先記錄主張能減少錯誤反轉;只在智能體不確定時記錄,可降低 token 開銷並修復更多真實錯誤。

正文

Published on Oct 26

Authors:

Abstract

Thinking-in-Bets improves agent reliability by having models record verified claims before receiving user feedback, reducing false reversals and unnecessary edits while maintaining accuracy.

Language model agents often abandon correct work when a user challenges it, yet simply telling them to stand firm makes them ignore real mistakes. Once an agent reads a complaint, it tends to discount its own earlier checks in order to agree with the user. We introduce Thinking-in-Bets, a training-free method in which an agent writes a short private record of its main claims, the checks supporting them, and its confidence before reading user feedback. When challenged, the agent consults this Claim Checklist to keep verified work intact while investigating uncertain or newly challenged parts. We evaluate five Gemini models (3.5 Flash-Lite, 3.5 Flash, 3.6 Flash, 3.8 Flash, and 4.0 Argon) across eight benchmarks: SWE-Together, SWE-Interact, and DeepSWE for software engineering, Agents' Last Exam for professional reports, Humanity's Last Exam and SycEval for academic reasoning, Vals Finance for financial analysis, and Terminal-Bench for command-line tasks. Recording claims before criticism nearly eliminates false reversals in patch review and protects passing report drafts under mistaken pushback, whereas writing the same record after reading the complaint recovers very little of the gain. In multi-turn coding, pre-reply claim records substantially reduce unnecessary file edits after mistaken complaints, and gating the record so it is written only when the agent is uncertain lowers token overhead while fixing more real bugs than the baseline. Even in non-interactive tasks without user feedback, listing the key claims in a draft and re-checking the weakest one before submission improves both answer accuracy and confidence estimates across all tested models.

View arXiv page View PDF Project page Add to collection

Get this paper in your agent:

hf papers read 2610.34654

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/2610.34654 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/2610.34654 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/2610.34654 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