Tycho:ARC-AGI-3的程序化世界模型主动抽象

Tycho: Active Abstraction with Programmatic World Models for ARC-AGI-3

精选理由

Tycho让AI在ARC-AGI-3里边玩边建模,GPT-5.6和Opus 5都满分通关,动作效率还胜过人类基线。

AI 摘要

论文提出Tycho编码代理系统,在ARC-AGI-3的25个公开游戏中用Claude Opus 4.8测试四种编排策略,Actor请求委托策略获得最高平均RHAE 88.49。GPT-5.6 Sol和Opus 5在该策略下均达到100.00 RHAE,并完成全部183个关卡。Opus 5比官方人类基线少用61%的计分动作,游戏均衡首轮人类重播中位排名为100.0。自动修复策略虽能更准确复现观察转移,但RHAE仅83.07,说明还需决定何时构建、修复或绕过模型。

原文 · arXiv cs.AI

Tycho: Active Abstraction with Programmatic World Models for ARC-AGI-3

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.