AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

Proposer-Agent-Evaluator (PAE): Autonomous Skill Discovery For Foundation Model Internet Agents

Yifei Zhou, Qianlan Yang, Kaixiang Lin, Min Bai, Xiong Zhou, Yu-Xiong Wang, Sergey Levine, Li Erran Li

ICML 2025 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: World-model-based agents · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

placeholder

Problem

placeholder

Approach

placeholder

Measured effects reported in the paper

What was changedWhereMeasuredEffect
apply PAE instead of SFT fine-tuningLLaVa-7B · WebVoyagersuccess rate (average): 14.9% to 22.3%Improved
apply PAE instead of SFT fine-tuningLLaVa-7B · WebArena Easysuccess rate (average): 18.0% to 24.6%Improved
apply PAE instead of SFT fine-tuningLLaVa-34B · WebVoyagersuccess rate (average): 22.2 to 33.0Improved
apply PAE instead of SFT fine-tuningLLaVa-7B · WebVoyager unseen websitessuccess rate: 9.1 to 16.3Improved
use Qwen2VL-7B instead of Claude as proposer and evaluator (ablation)LLaVa-7B PAE · WebArena Easysuccess rate (average): 18.0% to 23.1%Improved
use Qwen2VL-7B instead of Claude as proposer and evaluator (ablation)LLaVa-7B PAE · WebVoyager unseen websitessuccess rate: 9.1% to 13.7%Improved
add 10 user-demo screenshots as task-proposer context (ablation)LLaVa-7B PAE · WebArena Easy OpenStreetMapsuccess rate: 19.5% to 21.7%Improved
add 10 user-demo screenshots as task-proposer context (ablation)LLaVa-7B PAE · WebArena Easy PostMill and OneStopMarketsuccess rate: PostMill: 21.1 to 21.5; OneStopMarket: 42.3 to 42.1No clear effect
include a reasoning step before web operations (ablation)PAE agent policy · unseen human-written evaluation setperformanceImproved
replace outcome-based evaluation with step-based evaluation (ablation)PAE · evaluation task setperformanceHurt
replace outcome-based evaluation with function-based evaluation (ablation)PAE · evaluation task setperformanceHurt
apply PAE instead of SFT fine-tuningLLaVa-34B · WebVoyager unseen websitessuccess rate: 16.1 to 21.4Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy