research build log · ARC-AGI-3 · weekly snapshots

▣ code‑native/arc‑agi‑3 — archive

An agent that plays ARC‑AGI‑3 games by writing Python against the frame, with an execution-grounded “sleep” phase that mines skills and lets the game itself be the judge. Each card below is one week’s snapshot of the log — newest first.

experiment journal (2026-07-09): ▸ 무누수 파이프라인 플로우차트  ·  ▸ RQ 카드 저널

2026‑07‑09 latest

v3: 무누수 통합판 — fork=0으로 0 → 3 레벨, 위기 6장, 4-레인 비교

fork-검증을 하드 펜스로 금지하고 프롬프트 유출 3표면을 소거한 뒤의 첫 정직한 기록. 여섯 위기 카드(fault map), 파이프라인 노드별 이상/코드/실측, SkillOpt·baseline1·symbolica 4-레인 비교.

fork_dependence = 0 0→3 levels · RHAE 21.3 confirmed 7 / dropped 3
read the week →
2026‑07‑03 fork-시대 스냅샷

v2: sleep harness, escapes 0 → 4 levels, RHAE, trace explorer

A harness coordinate bug was silently eating every click. Eight fixes later, the agent clears level 4 on ft09 — with a data-driven run viewer over the real traces. 정정(07-09): 이 “WIN”은 이후 fork-브루트포스 아티팩트로 판정 — 역사 기록으로 보존.

level 4 cleared (fork-era) RHAE 17.9 21 runs · 8 fixes
read the week →
2026‑06‑30

v1: code-native baseline, failure ladder, first architecture

The first honest log: one autonomous CodeAct loop, an LLM-free skill gate, and the failure-mode chain — built and genuinely code-native, not yet solving a level from scratch.

0 levels from scratch failure-mode ladder LLM-free skill gate
read the week →