Back to AI News
arxiv

OutfitterBench Evaluates LLM Agents on Long-Horizon Resource Allocation

Researchers introduced OutfitterBench, a benchmark that asks LLM agents to manage an outdoor-equipment rental business for 200 days under a fixed capital ceiling. The environment includes a 46-product catalog and roughly 1,100 reservation requests, requiring agents to keep earlier commitments feasible while reallocating resources as demand changes. Experiments with seven frontier LLMs found that several agents performed worse than a simple rule-based baseline, while only one leading agent consistently surpassed it. The authors also released code and trajectory analyses highlighting weaknesses in constraint consistency, opportunity-cost comparison, and long-horizon plan maintenance.

AI Brief

It provides a concrete evaluation framework for understanding whether AI agents can sustain coherent, economically sound plans over extended operational horizons.

arXiv:2611.17933v1 Announce Type: new Abstract: In many long-horizon settings, an agent's own choices create future constraints: committing finite capacity establishes future obligations and forecloses later opportunities. Sustaining performance therefore requires both keeping evolving plans feasible and comparing the value of resource allocations with the alternatives they displace. Recent benchmarks increasingly evaluate LLM agents in continuing operations, but give less attention to how agents keep their own commitments feasible while reassessing resource allocations as opportunities change. We introduce OutfitterBench, where agents manage an outdoor-equipment rental business for 200 days, purchasing from a 46-product catalog and handling roughly 1,100 reservation requests. Under a fixed capital ceiling, reservations and uncertain walk-in demand compete for reusable equipment whose availability changes over time. Experiments with seven frontier LLMs show that several agents underperform a simple rule-based baseline, while only the leading agent consistently surpasses it. Trajectory analysis shows that some agents apply known constraints inconsistently and make new decisions that conflict with existing commitments. Agents with more reliable fulfillment can still secure low returns from comparable commitments or delay resource reallocation. The leading agent better connects preparation with economic choices but also misses opportunities for more profitable asset use. These findings highlight limitations in sustaining coherent resource plans and reassessing their value over time. The benchmark code is publicly available at https://github.com/adminblackjack/OutfitterBench.
Be the first to rate this article.

Comments & Questions (0)

Captcha
Please be respectful — let's keep the conversation friendly.

No comments yet

Be the first to comment!