PRO-LONG: Programmatic Memory Enables Long-Horizon Reasoning

arXiv:2607.20064 · cs.AI · Submitted 2026-07-22 · Read on arXiv

cs.AI

Submitted: 2026-07-22

Updated: 2026-10-12

Code: https://github.com/alexisfox7/PRO-LONG

Terminology

• Benchmark — 1× in this paper · explained in 2 episodes
• Continual Learning — 1× in this paper · explained in 2 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes

Sources

• Coding Agents are Effective Long-Context Processors
• Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
• ARC-AGI-3: A New Challenge for Frontier Agentic Intelligence
• ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems
• On the Measure of Intelligence
• ArcMemo: Abstract Reasoning Composition with Lifelong LLM Memory
• Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
• ARC-AGI Without Pretraining
• Lost in the Middle: How Language Models Use Long Contexts
• A Survey of Context Engineering for Large Language Models
• ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory
• MemGPT: Towards LLMs as Operating Systems
• Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI
• Executable World Models for ARC-AGI-3 in the Era of Coding Agents
• Hierarchical Reasoning Model
• From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMs
• SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems