IntentTwin: Deconfounding Candidate Support and the Oracle-to-Deployment Gap in Offline Web Behavior Prediction
cs.CL, cs.IR, cs.LG
Submitted: 2026-10-27
Updated: 2026-10-27
Terminology
Sources
- Mind2Web: Towards a Generalist Agent for the Web
- D4RL: Datasets for Deep Data-Driven Reinforcement Learning
- Planning with Diffusion for Flexible Behavior Synthesis
- Offline Reinforcement Learning with Implicit Q-Learning
- Conservative Q-Learning for Offline Reinforcement Learning
- Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems
- AgentBench: Evaluating LLMs as Agents
- Training language models to follow instructions with human feedback
- Toolformer: Language Models Can Teach Themselves to Use Tools
- Reflexion: Language Agents with Verbal Reinforcement Learning
- Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- OPeRA: A Dataset of Observation, Persona, Rationale, and Action for Evaluating LLMs on Human Online Shopping Behavior Simulation
- ReAct: Synergizing Reasoning and Acting in Language Models
- WebArena: A Realistic Web Environment for Building Autonomous Agents
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data