Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments

ICLR 2026 Conference Submission17177 Authors

Keywords: benchmark, agents, rlvr, multi-agent systems, reasoning, large language models

TL;DR: Gaia2 evaluates LLM agents in asynchronous, dynamic environments with action-level verification, revealing fundamental trade-offs between reasoning, speed, and robustness.

Abstract: We introduce Gaia2, a benchmark for evaluating large language model agents in realistic, asynchronous environments. Unlike prior static or synchronous evaluations, Gaia2 introduces scenarios where environments evolve independently of agent actions, requiring agents to operate under temporal constraints, adapt to noisy and dynamic events, resolve ambiguity, and collaborate with other agents. Each scenario is paired with a write-action verifier, enabling fine-grained, action-level evaluation and making Gaia2 directly usable for reinforcement learning from verifiable rewards. Our evaluation of state-of-the-art proprietary and open-source models shows that no model dominates across capabilities: GPT-5 (high) reaches the strongest overall score of 42% pass@1 but fails on time-sensitive tasks, Claude-4 Sonnet trades accuracy and speed for cost, Kimi-K2 leads among open-source models with 21% pass@1. These results highlight fundamental trade-offs between reasoning, efficiency, robustness, and expose challenges in closing the “sim2real” gap. Gaia2 is built on the open-source Agents Research Environments platform and designed to be easy to extend. By releasing Gaia2, we aim to provide the community with a foundation for developing, benchmarking, and training the next generation of practical agent systems.

Primary Area: datasets and benchmarks

Submission Number: 17177