PRO-LONG: Programmatic Memory Enables Long-Horizon Reasoning
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, especially when models are evaluated out of the box. Various agent harnesses have been proposed to close this gap, and each commits to a strategy for handling long sequences of observations, i.e., what information to save from the environment and how
Record details
Published: 22 July 2026
Source: arXiv cs.AI
Category: Research
Topics: Agents & autonomy · Environment
Retrieved: 23 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Coordinating from Memory: Graph-Structured Experience Reuse for Multi-Agent Adaptation in Dynamic Manufacturing
arXiv cs.AI · 22 July 2026
Courteous Anticipation: Improving Long-Lived Task Planning in Persistent Shared Environments
arXiv cs.AI · 22 July 2026
Closing the Lab-to-Store Gap: A Data-Efficient Post-Training and Experience-Driven Learning VLA Framework for Retail Humanoids
arXiv · 22 July 2026
Towards Miniature Humanoid Tele-Loco-Manipulation Using Virtual Reality and Reinforcement Learning
arXiv cs.HC · 22 July 2026
Is Deep Research Reliable? Misleading Knowledge Induces False Conclusions
HuggingFace Daily Papers · 22 July 2026
TableVerse: A Large-scale Tabletop Dataset with Real-world Grounded Layouts for Generalizable Manipulation
HuggingFace Daily Papers · 22 July 2026
How to cite this record
ethics.ai (22 July 2026), “PRO-LONG: Programmatic Memory Enables Long-Horizon Reasoning,” evidence record 12966, https://ethics.ai/record/12966 (originally published by arXiv cs.AI).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.