AI Paper Atlas

Research map / Multi-agent systems and games / LLM agents

Orion: Steering Personalized Web Agents via Global-Micro Profiling and Adaptive Intent Tracking

Die Hu, Jingguo Ge, Weitao Tang, He Kong, Liangxiong Li, Bingzhen Wu

AAAI 2026 · Multi-agent systems and games › LLM agents · approach: Agentic benchmarks and orchestration · 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.

Proposes Orion, a personalized LLM-based web agent that models user intent via global-micro profiling and adaptive intent tracking.

Problem

LLM-based web agents have limited personalization because user intent is ambiguous and dynamic, making it hard to model diverse interests and track intent changes over time.

Approach

Orion combines global-micro user profiling with adaptive intent tracking so that a web agent can model diverse user interests and follow evolving intent. Details beyond the abstract are not available.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add online GRPO RL after SFT (ablation)Orion · Ablation avg over three tasksresult accuracy (%): 34.7 -> 44.3Improved
add global-micro profile instead of single profile (ablation)Orion · Ablation avg over three tasksresult accuracy (%): 30.8 -> 44.3Improved
add dynamic profile update during interaction (ablation)Orion · Ablation avg over three tasksresult accuracy (%): 31.6 -> 44.3Improved
add proactive disambiguation action (ablation)Orion · Ablation avg over three tasksresult accuracy (%): 32.1 -> 44.3Improved
add proactive disambiguation action (ablation)Orion · Ablation avg over three tasksaverage steps: 6.4 -> 3.83Improved
use GRPO instead of PPO for online RLQwen2.5-7B-Instruct SFT · Personalized Recommendationresult accuracy (%): 10.3 -> 19.8Improved
add online RL (PPO) after SFT (ablation)Qwen2.5-7B-Instruct SFT · Personalized Recommendationresult accuracy (%): 8.2 -> 10.3Improved
use PUMA profile prompting vs ChatShop on GPT-4.1GPT-4.1 · Product Searchresult accuracy (%): 38.0 -> 42.8Improved
increase clustering threshold alpha away from 15 (ablation)Orion · sensitivity analysisresult accuracyMixed
increase context size lc beyond 6 (ablation)Orion · sensitivity analysisresult accuracyNo clear effect

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