Tycho通过动态构建游戏模型，让AI在限时挑战中高效推理规则并通关。
Tycho: Active Abstraction with Programmatic World Models for ARC-AGI-3
- 用可执行的程序化世界模型分离观察与动画，实现结构化交互
- 使用该模型后GPT-5.6和Opus 5达100.00分人类行动效率，完成183关
- 提出'主动抽象'概念：决定何时建模、修复或跳过模型最具价值
ARC-AGI-3将抽象转化为技能习得的交互问题：玩家需在每一步都精准行动的前提下，推断未知游戏的规则、隐藏状态和目标。我们将其形式化为参数化的渲染确定性莫尔机，并提出Tycho——一个在互动中构建与使用特定游戏模型的编码代理系统。Tycho将可行动观察与中间动画、关卡完成及游戏结束帧分离。基于此结构化历史，代理可建模、测试、规划、修复或绕过自由形式的可执行假设。在每策略单次匹配公开集运行中，我们在25个公开游戏中对比四种编排策略，使用Claude Opus 4.8且推理预算一致。由代理请求调用模型构建者获得最高平均相对人类行动效率（RHAE）88.49。采用该策略后，GPT-5.6 Sol与Opus 5均达100.00 RHAE并完成全部183关。其游戏平衡首跑人类回放中位排名分别为98.5和100.0。Opus 5所用计分动作比综合官方人类基线少61%。自动修复验证失败后的模型能更准确复现转移行为，但仅达83.07 RHAE。转移匹配反映模拟器是否复现观测动态，而非是否识别目标或提升下一步动作。强表现还需判断何时构建、修复、使用或跳过模型。我们称此联合问题为‘主动抽象’：从高成本交互中生成可检验模型，并决定获取或使用它的代价是否值得。
原文摘要 · Abstract (English)
ARC-AGI-3 turns abstraction into an interactive problem of skill acquisition. A player must infer an unfamiliar game's rules, hidden state, and goal while maintaining action efficiency because every move counts. We formalize these environments as parameterized rendered deterministic Moore machines and introduce Tycho, a coding-agent system that constructs and uses game-specific models during interaction. Tycho separates actionable observations from intermediate animation, level-completion, and game-over frames. From this structured history, an agent can model, test, plan with, repair, or bypass a free-form executable hypothesis. In one matched public-set run per policy, we compare four orchestration policies on all 25 public games using Claude Opus 4.8 under matched inference budgets. Actor-requested delegation to a model builder obtains the highest observed mean Relative Human Action Efficiency (RHAE), 88.49. With this selected policy, GPT-5.6 Sol and Opus 5 both reach 100.00 RHAE and complete all 183 levels. Their game-balanced first-run human-replay midranks are 98.5 and 100.0. Opus 5 uses 61% fewer scored actions than the aggregate official human baselines. Automatic repair after verification failures produces models that reproduce observed transitions much more accurately, yet reaches only 83.07 RHAE. Transition match indicates whether a simulator reproduces observed dynamics, not whether it has identified the objective or improves the next action. Strong play also requires deciding when to construct, repair, use, or bypass a model. We call this joint problem active abstraction: generating a testable model from costly interaction and deciding when acquiring or using it is worth its cost.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。