arXiv:2607. 28956v1 Announce Type: new Abstract: Large language model agents are increasingly evaluated as autonomous tool users, yet most benchmarks focus on bounded tasks with immediate success criteria.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
E-Commerce Bench is an open‑source benchmark that simulates a year‑long e‑commerce operation, requiring LLM agents to manage multiple online stores, negotiate with suppliers, optimize sales, fulfill orders, handle returns, and manage cash flow. The environment uses real product and supplier data, a calendar of promotions and shocks, and deterministic customer and negotiation models to enable reproducible evaluation. The study evaluates 18 state‑of‑the‑art models across seven metrics, finding no single model dominates, with GPT‑5.6 Sol achieving the highest year‑end assets but lagging in fraud avoidance and operational efficiency.
arXiv:2606. 15862v1 Announce Type: new Abstract: Large language model (LLM) agents have made rapid progress on short-horizon, well-scoped tasks, yet their ability to sustain coherent decisions in dynamic long-horizon environments remains uncertain.
arXiv:2603. 16453v3 Announce Type: replace Abstract: Large language model (LLM) agents have made rapid progress on short-horizon, well-scoped tasks, yet their ability to sustain coherent decisions in dynamic long-horizon environments remains uncertain.
arXiv:2606. 16613v1 Announce Type: new Abstract: As LLM agents become capable of increasingly long-horizon tasks, evaluating their performance in economic systems is becoming increasingly important.
The paper introduces a deterministic, reproducible e‑commerce environment that pre‑commits customer and trajectory parameters, enabling a simulated consumer to attempt purchasing a target cart with the help of an evaluated model. The environment records every assistant action and state, allowing post‑trial evaluation of specific conversation components and applying penalties based on tool‑call accuracy. Using this setup, the authors benchmark eight open‑weight agents (20B–35B parameters) across 160 trials and 44 metrics, revealing nuanced performance issues such as under‑action, over‑purchase, unsupported product attributes, and poor search that are hidden by overall success rates.
arXiv:2608. 08621v1 Announce Type: new Abstract: Running a business is a challenging form of intelligent work.