AnyAct: Universal Action for Self-Evolving Agents

arXiv:2609.37025 · cs.AI · Submitted 2026-09-29 · Read on arXiv

cs.AI

Submitted: 2026-09-29

Updated: 2026-09-29

Code: https://github.com/HKUDS/AnyTool

Project page: https://www.uipath.com/ai/research

Terminology

• Self-Evolving Agents — 1× in this paper · explained in 2 episodes

Sources

• A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems
• MCP-Zero: Active Tool Discovery for Autonomous LLM Agents
• Mano Technical Report
• RAG-MCP: Mitigating Prompt Bloat in LLM Tool Selection via Retrieval-Augmented Generation
• Scaling Agents for Computer Use
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• Agentic Lybic: Multi-Agent Execution System with Tiered Reasoning and Orchestration
• API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs
• Search-o1: Agentic Search-Enhanced Large Reasoning Models
• SE-Agent: Self-Evolution Trajectory Optimization in Multi-Step Reasoning with LLM-Based Agents
• DeepSeek-V3 Technical Report
• Build the web for agents, not agents for the web
• OmniParser for Pure Vision Based GUI Agent
• LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?
• UI-TARS: Pioneering Automated GUI Interaction with Native Agents
• Aime: Towards Fully-Autonomous Multi-Agent Framework
• Retrieval Models Aren't Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models
• CoAct-1: Computer-using Multi-Agent System with Coding Actions
• Multi-Agent Collaboration Mechanisms: A Survey of LLMs
• UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning

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