Agent-Environment Alignment via Automated Interface Generation

arXiv:2505.21055 · cs.AI · Submitted 2025-05-27 · Read on arXiv

cs.AI

Submitted: 2025-05-27

Updated: 2026-10-13

Code: https://github.com/THUNLP-MT/ALIGN

Terminology

• Alignment — 2× in this paper · explained in 1 episode
• Action Space — 1× in this paper · explained in 1 episode
• Agent Architectures — 1× in this paper · explained in 1 episode
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes

Sources

• Agent S: An Open Agentic Framework that Uses Computers Like a Human
• OpenAI Gym
• SeaView: Software Engineering Agent Visual Interface for Enhanced Workflow
• FireAct: Toward Language Agent Fine-tuning
• ATLaS: Agent Tuning via Learning Critical Steps
• AgentRefine: Enhancing Agent Generalization through Refinement Tuning
• Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents
• IDEA: Enhancing the Rule Learning Ability of Large Language Model Agent through Induction, Deduction, and Abduction
• AI2-THOR: An Interactive 3D Environment for Visual AI
• OmniParser for Pure Vision Based GUI Agent
• ART: Automatic multi-step reasoning and tool-use for large language models
• WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning
• UI-TARS: Pioneering Automated GUI Interaction with Native Agents
• AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents
• OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis
• Gymnasium: A Standard Interface for Reinforcement Learning Environments
• EscapeCraft: A 3D Room Escape Environment for Benchmarking Complex Multimodal Reasoning Ability
• RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning
• BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents
• Hallucination is Inevitable: An Innate Limitation of Large Language Models

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems