Programmatic memory for long-horizon LLM agents: the harness appends everything to one log, and the agent searches it with code. 97.4% on ARC-AGI-3 (arXiv:2607.20064)
☆457Aug 21, 2026Updated last month
Alternatives and similar repositories for PRO-LONG
Users that are interested in PRO-LONG are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- An ARC-AGI solution using Agentica from Symbolica☆311Feb 12, 2026Updated 7 months ago
- ☆175Mar 26, 2026Updated 5 months ago
- ☆47Jul 30, 2026Updated last month
- Technical Appendices☆20Sep 3, 2026Updated 3 weeks ago
- The Duck: ARC-AGI-3 inference harness -- winning solution to ARC-AGI-3 Milestone 1.☆87Jul 1, 2026Updated 2 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- RLM for coding agent☆103Feb 19, 2026Updated 7 months ago
- A Difficulty-Calibrated Benchmark for Building Terminal Agents☆30Feb 20, 2026Updated 7 months ago
- Latent Embedding Operating System☆25Apr 30, 2026Updated 4 months ago
- ☆18Mar 10, 2026Updated 6 months ago
- A plugin for your agentic framework that optimizes code using the GEPA algorithm (Genetic-Pareto LLM-driven search).☆99Apr 28, 2026Updated 4 months ago
- ☆36Apr 25, 2026Updated 4 months ago
- 3rd-place solution to the ARC-AGI-3 Preview Challenge — Explore It Till You Solve It☆22Jan 7, 2026Updated 8 months ago
- Framework for evolving code and prompts inspired by Darwinian evolution☆520Jun 1, 2026Updated 3 months ago
- A local-first evidence layer for agent work, capturing what the agent sees, does, and changes.☆99Updated this week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Experiments Notebook of "Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism"☆17Apr 30, 2025Updated last year
- Code repo for paper: Effective Strategies for Asynchronous Software Engineering Agents☆72Apr 2, 2026Updated 5 months ago
- Official implementation of the ΔBelief-RL method.☆31Feb 28, 2026Updated 6 months ago
- Repository for "Training Language Models To Explain Their Own Computations"☆37Jul 7, 2026Updated 2 months ago
- ☆16Sep 8, 2025Updated last year
- [ACL'26 Oral, SAC Highlight] Schoenfeld’s Anatomy of Mathematical Reasoning by Language Models☆28Sep 7, 2026Updated 2 weeks ago
- Automatic textbook formalization of Grinberg Algebraic Combinatorics☆18Jul 28, 2026Updated last month
- Method for Long Context RLMs using verifiable Lambda Calculus☆308Apr 24, 2026Updated 5 months ago
- New state-of-the-art bounds for open problems☆125Apr 12, 2026Updated 5 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- ☆102Jun 10, 2026Updated 3 months ago
- Forging interactive reasoning environments from The Witness puzzle mechanics — for ARC-AGI-3☆22Jul 25, 2026Updated last month
- FOND4LTLf translates an LTLf/PLTLf-FOND to standard FOND planning problems☆17Nov 3, 2024Updated last year
- This Guidance helps organizations provide their data scientists with external package repository access while maintaining information sec…☆23Oct 20, 2024Updated last year
- Training GPTs to solve interaction nets☆18Aug 14, 2024Updated 2 years ago
- Compiles AI agent traces and truns them into reusable context.☆97Sep 16, 2026Updated last week
- Reference code for the Meta-Harness paper.☆1,608Sep 11, 2026Updated last week
- [ICML 2026] Official implementation for paper: Learning Self-Correction in Vision–Language Models via Rollout Augmentation☆16Jun 4, 2026Updated 3 months ago
- A type of cellular automaton with the intent of simulating autopoiesis☆19Dec 13, 2024Updated last year
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- LLM-as-a-Verifier is a general-purpose framework that provides fine-grained feedback for any agent without requiring additional training.…☆3,261Aug 20, 2026Updated last month
- experiment loop for ai agents and swarms☆173Mar 29, 2026Updated 5 months ago
- Official implementation of Continual Harness (arxiv.org/abs/2605.09998) on ARC-AGI-3☆40Jul 3, 2026Updated 2 months ago
- Symbol-Equivariant Recurrent Reasoning Model☆18Mar 4, 2026Updated 6 months ago
- ☆47Nov 6, 2025Updated 10 months ago
- Instant Neural Graphics Primitives from scratch, zero dependencies. Learning by doing.☆10Aug 18, 2023Updated 3 years ago
- Recursive Coding Agents — AI Engineer World's Fair 2026 talk + website (SvelteKit, Cloudflare Workers)☆22Jun 30, 2026Updated 2 months ago