Meta Agents Research Environments is a comprehensive platform designed to evaluate AI agents in dynamic, realistic scenarios. Unlike static benchmarks, this platform introduces evolving environments where agents must adapt their strategies as new information becomes available, mirroring real-world challenges.
☆581Sep 30, 2026Updated last month
Alternatives and similar repositories for meta-agents-research-environments
Users that are interested in meta-agents-research-environments are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A Gym for Agentic LLMs☆519Jan 21, 2026Updated 9 months ago
- SkyRL: A Modular Full-stack RL Library for LLMs☆2,541Updated this week
- MCP Atlas☆164Updated this week
- The raw UserRL repo under construction☆128Jun 2, 2026Updated 5 months ago
- Our library for RL environments + evals☆4,793Updated this week
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- ☆308Jul 1, 2026Updated 4 months ago
- [ICLR 2026] The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution☆516Aug 18, 2026Updated 3 months ago
- An interface library for RL post training with environments.☆2,869Updated this week
- Research code artifacts for Code World Model (CWM) including inference tools, reproducibility, and documentation.☆922Jul 17, 2026Updated 4 months ago
- Democratizing Reinforcement Learning for LLMs☆5,926Oct 16, 2026Updated last month
- MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering☆1,802Apr 24, 2026Updated 6 months ago
- Resources and paper list for 'Scaling Environments for Agents'. This repository accompanies our survey on how environments contribute to …☆75Jan 28, 2026Updated 9 months ago
- slime is an LLM training framework for RL Scaling.☆8,849Nov 5, 2026Updated 2 weeks ago
- Framework for evaluating and improving agents☆7,205Updated this week
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- A version of verl to support diverse tool use [TMLR 2026]☆1,056Jul 15, 2026Updated 4 months ago
- (ACL 2026 Findings) The Agent’s First Day: Benchmarking Learning, Exploration, and Scheduling in the Workplace Scenarios☆12Jan 19, 2026Updated 10 months ago
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆24,283Updated this week
- The Automated LLM Speedrunning Benchmark measures how well LLM agents can reproduce previous innovations and discover new ones in languag…☆148May 6, 2026Updated 6 months ago
- Measuring how well CLI agents like Claude Code or Codex CLI can post-train base LLMs on a single H100 GPU in 10 hours☆626Updated this week
- Agent RL framework for LLM agents: multi-turn reinforcement learning with StarPO and reasoning-collapse diagnostics☆2,846Oct 28, 2026Updated 3 weeks ago
- [NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards☆1,555Nov 9, 2026Updated last week
- DAEDALUS: Bootstrapping Agent Memory from Self-Generated Tasks. Code, paper and blog post.☆13Oct 19, 2026Updated last month
- [COLM 2025] Official repository for R2E-Gym: Procedural Environment Generation and Hybrid Verifiers for Scaling Open-Weights SWE Agents☆353Jul 13, 2025Updated last year
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- ☆1,207Jan 10, 2026Updated 10 months ago
- A benchmark for LLMs on complicated tasks in the terminal☆2,623Jul 11, 2026Updated 4 months ago
- MCP-Universe is a comprehensive framework designed for RL training, benchmarking, and developing AI agents for general tool-use.☆606Oct 8, 2026Updated last month
- τ-Bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains☆2,484Nov 10, 2026Updated last week
- The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.☆5,921Updated this week
- Post-training with Tinker☆4,272Updated this week
- Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.☆3,366Updated this week
- AllenAI's post-training codebase☆3,940Updated this week
- Harness for running and evaluating AI agents against RL environments☆305Updated this week
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- An agent benchmark with tasks in a simulated software company.☆822Nov 17, 2025Updated last year
- Search, understand, reproduce, and improve an idea with ease☆1,248Updated this week
- Code for Paper: Training Software Engineering Agents and Verifiers with SWE-Gym [ICML 2025]☆764Nov 1, 2026Updated 2 weeks 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…☆2,454Jun 9, 2026Updated 5 months ago
- Official eval scripts for JobBench☆74Oct 6, 2026Updated last month
- Agentic RL Training at Scale☆2,262Updated this week
- 🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.☆678Jan 29, 2026Updated 9 months ago
Are these results useful?