gkroiz/agent-interp-envs

Research infra for creating RL environments, post-training, and evals.

Creating realistic RL environments requires collaboration between researchers, engineers, and domain experts across many dimensions: artifacts, environments tools, dynamism of the environment, reproducibility, and more. There is no open source framework for building these environments effectively. Until now.

Evaluate and improve models and agents using environments

The universal bridge between agents and environments — evaluate, RL-train, and trace any agent, in any sandbox, on any model.

General agent evaluation framework

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.

AIRA-dojo: a framework for developing and evaluating AI research agents

A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)

OpenART is an open-source framework designed to evaluate the safety and robustness of autonomous AI agents in dynamic, long-horizon, and stateful environments. It stress-tests agent runtimes against multi-step state poisoning, privilege escalation, and tool-use vulnerabilities across 10,000+ benchmark scenarios.