Newest papers

Environment Duels: A Microcosm of LLM Co-Evolution

Shibo Jin, Zhiqiu Xu, Yiling Zou, Shangyu Gong, Naik Mayur · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.30116 · cited by 0 works (OpenAlex) · open-access PDF

Korean

다우크는 합성 훈련 파이프라인에서 오픈 웹에서 공유 된 데이터를 통해 실제 상호 작용의 에이전트를 통해, 국경 LLM은 이전과 경쟁자가 만드는 것을 흡수합니다. 각 모델은이 생태계에서 창조자와 솔버로서 자신의 역할을 얼마나 잘합니다? 우리는 합성 훈련 파이프라인, 대화 환경에서 두 가지 능력을 평가하는 역동적 인 에이전트 벤치마크를 소개합니다. 각 모델은 다른 사람들로부터 더 많이 배우고 가장 어려운 환경과 가장 유용한 힌트를 작성하면서이 생태계에서 실패 할 수있는 솔버가 실패 할 수있는 작업을 목표로합니다. 9 개 국경 LLM을 통해, 해결 및 저자들은 외부 환경에 대한 솔버링 기술을 구별 할 수 있습니다 : 가장 강한 솔

Machine translation (Meta M2M100); the English original follows.

Abstract

Through a tangle of real-world interactions, from synthetic training pipelines to data shared on the open web, frontier LLMs absorb what their predecessors and competitors create. How well does each model play its role in this ecosystem, as a creator and as a solver? We introduce Environment Duels, a dynamic agentic benchmark that evaluates both capabilities on interactive environments. Each model writes environments, each with a privileged hint, aiming for tasks that capable solvers fail without the hint and pass with it. Across nine frontier LLMs, solving and authoring prove to be distinct skills: the strongest solvers are not the strongest authors, while smaller models learn more from how others played and write the hardest environments and the most useful hints. Beyond the scores, the pairwise interactions form a microcosm of how models affect one another. Head-to-head outcomes are transitive and so yield a stable ranking; independent authors converge on the same designs; and in a reinforcement-learning study with Qwen3.8-27B, the learner's hint lift on an author's environments tracks how much training on those environments improves it on held-out reasoning and agentic benchmarks, whether the environments are its own or another model's. Each of these patterns has a counterpart in how models shape one another outside the duel. By staging these interactions under controlled conditions, Environment Duels offers a window onto how LLMs teach, challenge and learn from one another. Code is available at https://github.com/LLM-Duels/EnvDuels.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Microcosm, Computer science, Transitive relation, Frontier, Competitor analysis, Lift (data mining)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange