[2602.09514] EcoGym: Evaluating LLMs for Long-Horizon Plan-and-Execute in Interactive Economies
Abstract:Long-horizon planning is widely recognized as a core capability of autonomous LLM-based agents; however, current evaluation frameworks suffer from being largely episodic, domain-specific, or insufficiently grounded in persistent economic dynamics. We introduce EcoGym, a generalizable benchmark for continuous plan-and-execute decision making in interactive economies. EcoGym comprises three diverse environments: Vending (adapted from the closed-source Vending-Bench, with full open-source release), Freelance (new), and Operation (new), implemented in a unified decision-making process with standardized interfaces, and budgeted actions over an effectively unbounded horizon (1000+ steps if 365 day-loops for evaluation). The evaluation of EcoGym is based on business-relevant outcomes (e.g., net worth, income, and DAU), targeting long-term strategic coherence and robustness under partial observability and stochasticity. Experiments across eleven leading LLMs expose a systematic tension: no single model dominates across all three scenarios. Critically, we find that models exhibit significant suboptimality in either high-level strategies or efficient actions executions. EcoGym is released as an open, extensible testbed for transparent long-horizon agent evaluation and for studying controllability utility trade-offs in economic settings.
Abstract:Long-horizon planning is widely recognized as a core capability of autonomous LLM-based agents; however, current evaluation frameworks suffer from being largely episodic, domain-specific, or insufficiently grounded in persistent economic dynamics. We introduce EcoGym, a generalizable benchmark for continuous plan-and-execute decision making in interactive economies. EcoGym comprises three diverse environments: Vending (adapted from the closed-source Vending-Bench, with full open-source release), Freelance (new), and Operation (new), implemented in a unified decision-making process wit
Explore this link on the map →saved by
related reading
- AI Benchmark Leaderboards & Model Evals | BenchmarkListbenchmarklist.com
- PostTrainBenchposttrainbench.com
- The bitter lesson of LLM evalsparsed.com
- Composer2.pdfcursor.com
- LLM Powered Autonomous Agents | Lil'Loglilianweng.github.io
- [2503.18825] EconEvals: Benchmarks and Litmus Tests for Economic Decision-Making by LLM Agentsarxiv.org
- Demystifying evals for AI agents \ Anthropicanthropic.com
- A Taxonomy of RL Environments for LLM Agentsleehanchung.github.io
- EconEvals: Benchmarks and Litmus Tests for LLM Agents in Unknown Environmentsarxiv.org
- Agent Evaluation: A Detailed Guidecameronrwolfe.substack.com
- Explore | alphaXivalphaxiv.org
- [2603.21972] Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipearxiv.org