20 results for “evolving environments”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
This paper investigates whether LLMs explore new program forms or revisit existing ones when repeatedly mutating a program.
Jundong Xu, Qingchuan Li, Jiaying Wu, Yihuai Lan +10 more
This paper introduces EvoArena, a benchmark suite for evaluating large language model agents in dynamic environments, and EvoMem, a patch-based memory paradigm that improves performance in these envir…
A model-driven approach is proposed for generating families of reinforcement learning training environments using a hybrid genetic algorithm and model transformations.
This paper describes Gifbreeder, an animated evolutionary computation platform that generates 'Limbomorphs' - motile, lifelike creatures, and assesses their behavior.
The paper introduces EvoX Genesis, a system for long-horizon software development with a persistent project and finite-lived agents.
The paper introduces HORIZON, a self-evolving agent framework for hardware design using git operations.
This paper introduces analytical replay experiments to the evolutionary computing community, allowing quantification of how a population's potential for different evolutionary outcomes changed over ti…
This paper proposes Evolutionary Intelligence (EI) for scientific discovery, which links candidate refinement with experience retention across evolutionary cycles.
Xujun Li, Kehan Zheng, Mingyuan Zhao, Yize Geng +6 more
The paper proposes HiSME, a lightweight hierarchical skill meta-evolving solution that jointly optimizes skills and the skill evolving strategy by learning meta-skills from task execution traces, lead…
The authors introduce a new model to study the fitness progress of Evolution Strategies (ES) in generic problems and rigorously analyze the expected growth rate of the continuous steady-state (μ+1)-ES…
Minhua Lin, Juncheng Wu, Zijun Wang, Zhan Shi +13 more
The paper distinguishes between a model's ability to generate useful updates for external agent components (harness-updating) and its ability to benefit from those updates (harness-benefit), finding t…
Zhezheng Hao, Tianfu Wang, Huanshuo Dong, Ziyan Liu +6 more
The paper proposes Meta-Team, an experience-driven framework that enables multi-agent systems (MAS) to collaboratively self-evolve by transforming complex execution experiences into reusable improveme…
This paper presents a framework for automated design and artistic evaluation using an evolutionary system and AI.
The paper proposes a novel approach to automatically generating test inputs for games by combining a white-box testing approach with a model-based testing approach.
Zixuan Zhu, Yitong Hu, Yong Dai, Junfeng Fang +3 more
The paper introduces Unified Context Evolution (UCE), a gradient-free framework that externalizes and manages agent experience into a typed, evolving library, significantly improving performance on mu…
The authors study the (1+1)-EA in dynamic linear environments and prove sharp thresholds for mutation rates in two models.