Official repository of the paper: Continual Harness: Online Adaptation for Self-Improving Foundation Agents and PokeAgent Speedrun Track 2
☆349May 13, 2026Updated 6 months ago
Alternatives and similar repositories for continual-harness
Users that are interested in continual-harness are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆22Mar 11, 2026Updated 8 months ago
- Official implementation of Continual Harness (arxiv.org/abs/2605.09998) on ARC-AGI-3☆42Jul 3, 2026Updated 4 months ago
- Official repository of the spotlight ICML 2025 paper, PokeChamp: an Expert-level Minimax Language Agent.☆191Mar 11, 2026Updated 8 months ago
- ☆38Updated this week
- Official code for Meta-Harness (2603.28052)☆1,789Nov 5, 2026Updated last week
- 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.
- ☆208Apr 3, 2025Updated last year
- Meta-Harness: 76.4% on Terminal-Bench 2.0 (Claude Opus 4.6)☆1,255Mar 26, 2026Updated 7 months ago
- ☆52Nov 1, 2026Updated 2 weeks ago
- Codex plugin that injects the ultrawork orchestration directive when the user prompt contains 'ultrawork' or 'ulw'.☆16May 24, 2026Updated 5 months ago
- The official repository of "Position: Agentic Evolution is the Path to Evolving LLMs".☆856Nov 6, 2026Updated last week
- LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric Rewards☆41Jun 1, 2026Updated 5 months ago
- Value model for block-wise search☆14Jul 1, 2025Updated last year
- The code for paper "MemGym: a Long-Horizon Memory Environment for LLM Agents".☆23Jun 2, 2026Updated 5 months ago
- Self-HPO: self-improving harness + policy co-optimization for agentic SWE☆67Oct 19, 2026Updated 3 weeks ago
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- RHO: Evolving Agents in the Dark — Retrospective Harness Optimization via Self-Preference. Improving LLM agents from unlabeled past traje…☆69Oct 30, 2026Updated 2 weeks ago
- ☆145Jul 2, 2026Updated 4 months ago
- ☆102Jun 30, 2025Updated last year
- CHARGE: A Benchmark for Multimodal RAG via Chart-based Document Question-Answering Generation Framework☆10Apr 18, 2025Updated last year
- The first benchmark that asks code agents to build agents.☆25Jun 4, 2026Updated 5 months ago
- Code and implementations for the paper "AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcemen…☆892Feb 15, 2026Updated 9 months ago
- mstar: Optimizing memory architecture for every LLM task as executable Python code.☆20Updated this week
- Playing Pokemon Red with Reinforcement Learning☆22Jul 28, 2025Updated last year
- World Model Self-Distillation project website☆19Jun 15, 2026Updated 5 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Code for "Meta^n: Recursive Self-Improvement through Emergent Depth"☆89Aug 26, 2026Updated 2 months ago
- [arXiv:2603.18859] "RewardFlow: Topology-Aware Reward Propagation on State Graphs for Agentic RL with Large Language Models"☆13Jun 5, 2026Updated 5 months ago
- [ICML25] Official repo for "Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond…☆26Sep 27, 2025Updated last year
- ☆29Mar 10, 2026Updated 8 months ago
- [EMNLP 2026] Official code for "SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization"☆390Aug 12, 2026Updated 3 months ago
- A curated list for Self-Improvement in Foundation Model Based Agentic Systems.☆637Updated this week
- DAEDALUS: Bootstrapping Agent Memory from Self-Generated Tasks. Code, paper and blog post.☆13Oct 19, 2026Updated 3 weeks ago
- [ICML'26] MemEvolve & EvolveLab☆288May 5, 2026Updated 6 months ago
- Self-referential self-improving agents that can optimize for any computable task☆2,912Jul 31, 2026Updated 3 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- RSI-Exam: Measuring Recursive Self-Improvement on Long-Horizon, Executable Research Tasks · Discord https://discord.gg/FBzhepyE☆202Nov 6, 2026Updated last week
- ☆18Feb 28, 2026Updated 8 months ago
- Modified version of the LeagueSandbox project which relies on a Redis server to accept actions and send observations. Intended for reinfo…☆14Feb 23, 2025Updated last year
- Rethinking the Evaluation of Harness Evolution for Agents☆52Oct 15, 2026Updated last month
- Agentic RL on Any Harness at Scale☆878Updated this week
- SafePyramid: A Hierarchical Benchmark for In-context Policy Guardrailing☆15Sep 23, 2026Updated last month
- Repo for "AlphaResearch: Accelerating New Algorithm Discovery with Language Models"☆61Nov 12, 2025Updated last year
Are these results useful?