# Explore Before You Solve: The Speed--Depth Trade-off in Epistemic Agents for ARC-AGI-3

arXiv: https://arxiv.org/abs/2605.25931 · HTML: https://mlsanity.com/paper/2605.25931/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 32 references that are in the map.
- First posted on arXiv 25 May 2026.

## Builds on (most cited first, 7 of 7)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [ARC-AGI-3: A New Challenge for Frontier Agentic Intelligence](https://mlsanity.com/paper/2603.24621/) (2026)
- [Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI](https://mlsanity.com/paper/2507.14172/) (2025)
- [ARC Prize 2025: Technical Report](https://mlsanity.com/paper/2601.10904/) (2026)

## Built on by (most cited first, 2 of 2)

- [Tycho: Active Abstraction with Programmatic World Models for ARC-AGI-3](https://mlsanity.com/paper/2607.28287/) (2026)
- [The LLM Proposes, the Executive Disposes: A Self-Verifying Agent Instrument that Dissociates Commitment Drift from Binding Drift in Long-Horizon Agents](https://mlsanity.com/paper/2608.04066/) (2026)

## Abstract (arXiv)

We systematically investigate all 25 public ARC-AGI-3 games and find that every one is reachable through non-intelligent strategies: 10 in a single blind step, 5 after one probing action, 1 via repeated ACTION1 presses, 1 via diverse exploration, and 8 via single repeated actions with sufficient budget (50-200 steps). A library-level null-coordinate vulnerability additionally bypasses 18 games in 1 step. This benchmark critique implies the public evaluation set cannot discriminate intelligent exploration from trivial heuristics - the private 55-game evaluation is the only genuine intelligence test. Against this backdrop, we present AERA (Adaptive Epistemic Reasoning Agent), a three-phase (EXPLORE / VERIFY / PLAN) agent achieving RHAE=0.2116 (4/25 solved) on these 25 games with Qwen2.5-0.5B, while random and no-explore baselines score 0.0000. We formalise AERA through a Speed--Depth trade-off framework: under a convexity assumption (proved for a class of environments in the Appendix), RHAE's quadratic form emerges as a second-order penalty for deviating from the Pareto frontier between action efficiency and information gain. Contributions: (i) a benchmark validity analysis showing that current interactive reasoning benchmarks fail to measure the exploration they claim to require, and (ii) the EXPLORE-before-PLAN framework and model-capability x exploration interaction. The linked code track entry achieves RHAE=0.30 on the full 55-game private evaluation. Code: CC0.