# PRO-LONG: Programmatic Memory Enables Long-Horizon Reasoning

arXiv: https://arxiv.org/abs/2607.20064 · HTML: https://mlsanity.com/paper/2607.20064/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 22 of its 30 references that are in the map.
- First posted on arXiv 22 Jul 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/)

## Builds on (most cited first, 22 of 22)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [Show Your Work: Scratchpads for Intermediate Computation with Language Models](https://mlsanity.com/paper/2112.00114/) (2021)
- [Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory](https://mlsanity.com/paper/2504.19413/) (2025)
- [A Survey on the Memory Mechanism of Large Language Model based Agents](https://mlsanity.com/paper/2404.13501/) (2024)
- [ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory](https://mlsanity.com/paper/2509.25140/) (2025)
- [SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning](https://mlsanity.com/paper/2602.08234/) (2026)
- [ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems](https://mlsanity.com/paper/2505.11831/) (2025)
- [Hierarchical Reasoning Model](https://mlsanity.com/paper/2506.21734/) (2025)
- [On the Measure of Intelligence](https://mlsanity.com/paper/1911.01547/) (2019)
- [A Survey of Context Engineering for Large Language Models](https://mlsanity.com/paper/2507.13334/) (2025)
- [From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMs](https://mlsanity.com/paper/2504.15965/) (2025)
- [Recursive Language Models](https://mlsanity.com/paper/2512.24601/) (2025)
- [Less is More: Recursive Reasoning with Tiny Networks](https://mlsanity.com/paper/2510.04871/) (2025)
- [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)
- [ArcMemo: Abstract Reasoning Composition with Lifelong LLM Memory](https://mlsanity.com/paper/2509.04439/) (2025)
- [Executable World Models for ARC-AGI-3 in the Era of Coding Agents](https://mlsanity.com/paper/2605.05138/) (2026)
- [Coding Agents are Effective Long-Context Processors](https://mlsanity.com/paper/2603.20432/) (2026)
- [ARC-AGI Without Pretraining](https://mlsanity.com/paper/2512.06104/) (2025)

## Built on by (most cited first, 10 of 10)

- [Prime Agent: A Self-Improving RLM Harness](https://mlsanity.com/paper/2608.23552/) (2026)
- [Tycho: Active Abstraction with Programmatic World Models for ARC-AGI-3](https://mlsanity.com/paper/2607.28287/) (2026)
- [Twin: Playing an Unknown Game with a Test-Time Digital Twin](https://mlsanity.com/paper/2608.14490/) (2026)
- [DiG-bench: Discovery in Games](https://mlsanity.com/paper/2608.12593/) (2026)
- [Thinking Before Thinking: Scaling Agentic Inference Through Meta-Reasoning](https://mlsanity.com/paper/2609.38147/) (2026)
- [Agents Can Use Base Models to Evade AI Detection](https://mlsanity.com/paper/2609.31876/) (2026)
- [Coding Agent Memory Post-training: Unlocking the Memory Potential of Pre-trained File Operations for Long-Horizon Tasks via Reinforcement Learning](https://mlsanity.com/paper/2609.34422/) (2026)
- [Schema: Discovering Unknown Environments via Agentic Program Induction](https://mlsanity.com/paper/2609.39140/) (2026)
- [Tracing the Thoughts of a Coding Agent Playing ARC-AGI-3: Lessons for Continual Learning](https://mlsanity.com/paper/2610.11450/) (2026)
- [DeLoop: Repeated Actions as Self-Supervision for Long-Horizon Agents](https://mlsanity.com/paper/2610.19376/) (2026)

## Abstract (arXiv)

Long-horizon tasks require sustained perception, reasoning, and exploration, and are a persistent challenge for large language model (LLM) agents. This gap is reflected in their limited performance on continual learning benchmarks such as ARC-AGI-3 and NetHack, especially when evaluated without specialized harnesses. Various agent harnesses have been proposed to close the gap, and each commits to a strategy for handling long sequences of observations, i.e., what information to save from the environment and how to load it into model context, a choice we argue is particularly consequential. Existing methods for context management have typically been designed around a tradeoff, where preserving more information makes relevant details harder to retrieve. Recent progress in coding agents, however, makes new approaches to memory viable. We propose PRO-LONG, a minimal context management framework built around programmatic memory for LLM agents in long-horizon, exploratory settings. PRO-LONG addresses the tradeoff by keeping a complete, structured interaction log and using programmatic tools to search this history efficiently. On NetHack, we find increasing gains from using PRO-LONG for cross-episodic memory, with scores reaching up to 2.2x those of a base coding agent. On the full ARC-AGI-3 public game set, PRO-LONG improves over this baseline agent by an average of 18.0 percentage points across frontier models, and matches or exceeds state-of-the-art specialized harnesses (up to 97.4% best@2) while using 4.2-5.8x fewer tokens. Relevant code and logs are available at https://github.com/alexisfox7/PRO-LONG.