研究库 论文知识库

内容库 / 论文

arXiv:2610.12341 · Agent 智能体

Can AI Agents Learn Their Way to the Top? Evaluating Heuristic Learning in a Long-Running Game Agent Competition

Can AI Agents Learn Their Way to the Top? Evaluating Heuristic Learning in a Long-Running Game Agent Competition

类型：arxiv
标识：2610.12341
链接：https://arxiv.org/abs/2610.12341
主分类：agent
形态：benchmark
TLDR：Adversarial games have driven advances from heuristic search to reinforcement learning, yet learning and adapting strategies from limited samples remain challenging. AI agents offer an alternative by turning game experience into revisions of executable policies. Building on heuristic learning (HL), we formalize Adversarial Heuristic Learning (AHL), a paradigm that uses AI agents as learning engines to refine game policies and supporting software while keeping model weights fixed. We introduce AAArena, a benchmark comprising 12 authentic adversarial games and 1,920 archived human programs, with
副分类：evaluation
待LLM分类：否
来源文件：
/inbox/tom/_candidates/2026-10-12-agent-rag-longcontext-candidates.json

相关 · 按语义匹配

笔记 Cameron R. Wolfe (Deep Learning Focus) · RSS 摘要

笔记 flyP 精读 · Agentic RL 与长视野 LLM Agent 训练

笔记 flyP 夜间轻量精读 · 2026-06-23（cron 3d8f503a · 22:50 CST）

笔记 flyP 精读与反方审稿 · Agentic RL 综述 + GLM-5.2 开放 Agent 路线 · 2026-07-15 22:50

笔记 Agent-STAR / arXiv:2603.21972 · "Demystifying RL for Long-Horizon Tool-Using Agents: A Comprehensive Recipe" · flyP 精读与批判

笔记 flyP 精读与批判 · VLA-Precision / ACoB（在线 RL for VLA 高精度操作）

arXiv

2610.12341

TLDR

Adversarial games have driven advances from heuristic search to reinforcement learning, yet learning and adapting strategies from limited samples remain challenging. AI agents offer an alternative by turning game experience into revisions of executable policies. Building on heuristic learning (HL), we formalize Adversarial Heuristic Learning (AHL), a paradigm that uses AI agents as learning engines to refine game policies and supporting software while keeping model weights fixed. We introduce AAArena, a benchmark comprising 12 authentic adversarial games and 1,920 archived human programs, with

arXiv ↗ 中文全文