Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning
☆448May 28, 2026Updated 3 months ago
Alternatives and similar repositories for agent-world-model
Users that are interested in agent-world-model are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- The official implementation of "EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis".☆191Updated this week
- GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulators☆65Dec 23, 2025Updated 8 months ago
- [ACL 2026 Oral] From Word to World: Can Large Language Models be Implicit Text-based World Models?☆72Apr 13, 2026Updated 4 months ago
- The official paper for EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL.☆95Aug 28, 2026Updated last week
- RLAnything (ICML 2026) & AutoTool (ICML 2026), DemyAgent: Open-Source RL for LLMs and Agentic Scenarios☆634Jun 12, 2026Updated 2 months ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Official Implementation of "Simulating Environments with Reasoning Models for Agent Training"☆68Feb 18, 2026Updated 6 months ago
- When and How Much to Imagine: Adaptive Test-Time Scaling with World Models for Visual Spatial Reasoning☆19Jun 2, 2026Updated 3 months ago
- verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in…☆2,282Jun 9, 2026Updated 2 months ago
- Agent RL framework for LLM agents: multi-turn reinforcement learning with StarPO and reasoning-collapse diagnostics☆2,794Aug 23, 2026Updated 2 weeks ago
- Training and evaluating with OpenReward☆33Apr 28, 2026Updated 4 months ago
- [ICLR 2026] The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution☆479Aug 18, 2026Updated 2 weeks ago
- OpenClaw-RL: Train any agent simply by talking☆5,670May 23, 2026Updated 3 months ago
- SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning☆964May 17, 2026Updated 3 months ago
- SkyRL: A Modular Full-stack RL Library for LLMs☆2,259Updated this week
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Reinforcement Learning via Self-Distillation (SDPO)☆1,090Jul 1, 2026Updated 2 months ago
- Code for "CREAM: Consistency Regularized Self-Rewarding Language Models", ICLR 2025.☆30Feb 17, 2025Updated last year
- DIVE: Scaling Diversity in Agentic Task Synthesis for Generalizable Tool Use☆29Mar 13, 2026Updated 5 months ago
- Computer Environments Elicit General Agentic Intelligence in LLMs☆243Aug 22, 2026Updated 2 weeks ago
- A version of verl to support diverse tool use [TMLR 2026]☆1,037Jul 15, 2026Updated last month
- [ICML 2026] RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments☆231Apr 30, 2026Updated 4 months ago
- slime is an LLM post-training framework for RL Scaling.☆8,404Updated this week
- [ICLR 2026] Agentic Reinforced Policy Optimization (ARPO)☆1,114Aug 20, 2026Updated 2 weeks ago
- ☆65Jul 1, 2026Updated 2 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Benchmark and research code for the paper SWEET-RL Training Multi-Turn LLM Agents onCollaborative Reasoning Tasks☆271May 5, 2025Updated last year
- ☆144Mar 31, 2026Updated 5 months ago
- An interface library for RL post training with environments.☆2,552Updated this week
- Toolathlon-Gym for testing AI agents real-world tool-use capabilities across diverse MCP servers.☆147Jul 22, 2026Updated last month
- Agentic RL on Any Harness at Scale☆830Aug 13, 2026Updated 3 weeks ago
- ☆32Feb 11, 2026Updated 6 months ago
- τ-Bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains☆1,969Updated this week
- Dr. MAS is an end-to-end RL training framework for multi-agent LLM systems, supporting the co-training of multiple (heterogeneous) LLMs.☆159Jul 27, 2026Updated last month
- [EMNLP 2026] Aligning Agentic World Models via Knowledgeable Experience Learning☆40May 15, 2026Updated 3 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Gym-Anything: Turn any Software into an Agent Environment☆280Aug 24, 2026Updated 2 weeks ago
- Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning☆1,654Updated this week
- [ACL 2026 Main] MCP-Flow: Facilitating LLM Agents to Master Real-World, Diverse and Scaling MCP Tools.☆25Apr 8, 2026Updated 5 months ago
- Code for Paper: Training Software Engineering Agents and Verifiers with SWE-Gym [ICML 2025]☆732Jul 29, 2025Updated last year
- Official repo of Toucan: Synthesizing 1.5M Tool-Agentic Data from Real-World MCP Environments☆267Dec 16, 2025Updated 8 months ago
- SkillsBench evaluates how well skills work and how effective agents are at using them.☆1,753Jul 23, 2026Updated last month
- The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.☆5,733Updated this week