OdysseyArena: Benchmarking Large Language Models For Long-Horizon, Active and Inductive Interactions

TL;DR

OdysseyArena introduces a new benchmarking framework for evaluating large language models on long-horizon, active, and inductive interactions, highlighting current models' limitations in autonomous discovery within complex environments.

Contribution

The paper presents OdysseyArena, a comprehensive benchmark with environments and tasks designed to assess LLMs' inductive learning and long-term strategic capabilities.

Findings

Leading LLMs show limited inductive reasoning in complex tasks.

OdysseyArena-Lite provides 120 standardized tasks for benchmarking.

OdysseyArena-Challenge stresses models on extreme interaction horizons.

Abstract

The rapid advancement of Large Language Models (LLMs) has catalyzed the development of autonomous agents capable of navigating complex environments. However, existing evaluations primarily adopt a deductive paradigm, where agents execute tasks based on explicitly provided rules and static goals, often within limited planning horizons. Crucially, this neglects the inductive necessity for agents to discover latent transition laws from experience autonomously, which is the cornerstone for enabling agentic foresight and sustaining strategic coherence. To bridge this gap, we introduce OdysseyArena, which re-centers agent evaluation on long-horizon, active, and inductive interactions. We formalize and instantiate four primitives, translating abstract transition dynamics into concrete interactive environments. Building upon this, we establish OdysseyArena-Lite for standardized benchmarking, providing a set of 120 tasks to measure an agent's inductive efficiency and long-horizon discovery. Pushing further, we introduce OdysseyArena-Challenge to stress-test agent stability across extreme interaction horizons (e.g., > 200 steps). Extensive experiments on 15+ leading LLMs reveal that even frontier models exhibit a deficiency in inductive scenarios, identifying a critical bottleneck in the pursuit of autonomous discovery in complex environments. Our code and data are available at https://github.com/xufangzhi/Odyssey-Arena