RHO: Evolving Agents in the Dark — Retrospective Harness Optimization via Self-Preference. Improving LLM agents from unlabeled past trajectories (arXiv:2606.05922).
☆69Oct 30, 2026Updated 2 weeks ago
Alternatives and similar repositories for retro-harness
Users that are interested in retro-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:
- Rethinking the Evaluation of Harness Evolution for Agents☆51Oct 15, 2026Updated 3 weeks ago
- On-policy distillation for visual token compression.☆17Oct 30, 2026Updated last week
- ☆16Updated this week
- A2Z GameSpec-Bench: How Faithfully Can Coding Agents Generate Games from Game Design Specifications?☆16Oct 8, 2026Updated last month
- Project page and release repository for PhysEditWorld, a dataset toward physics-editable world models.☆19Jul 2, 2026Updated 4 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Self-evolution for any agent harness. Plug in. Evolve. Measure.☆112Nov 3, 2026Updated last week
- [ICLR 2026] Training Visual Reasoners with Multimodal Verifiers☆15Jun 12, 2026Updated 5 months ago
- ☆14Mar 30, 2026Updated 7 months ago
- TRACE is an agentic jailbreaking framework that can reduce attack difficulty, induce the agent to execute end-to-end attack workflows thr…☆41Oct 1, 2026Updated last month
- [ACL 2024] Prompt Optimization via Adversarial In-Context Learning☆13Sep 4, 2024Updated 2 years ago
- Dataset of personal narratives with Advice Seeking Questions☆15May 10, 2019Updated 7 years ago
- ☆13Oct 7, 2025Updated last year
- ☆10May 23, 2025Updated last year
- [ECCV 2026] Dense Reward for Multi-View 3D Reasoning with Global Maps and Local Views☆15Sep 27, 2026Updated last month
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- mstar: Optimizing memory architecture for every LLM task as executable Python code.☆20Oct 30, 2026Updated 2 weeks ago
- Efficient multi-token attribution for reasoning language models — Python package, CLI, and HTML token traces☆44Oct 30, 2026Updated 2 weeks ago
- Self-evolve your LLM's capabilities with just a task and a success criterion.☆14Dec 31, 2025Updated 10 months ago
- Official code for Meta-Harness (2603.28052)☆1,777Nov 5, 2026Updated last week
- [AAAI 2025] Official Implementation of I-HallA v1.0☆16Feb 2, 2025Updated last year
- Pushing Test-Time Scaling Limits of Deep Search with Asymmetric Verification☆23Oct 8, 2025Updated last year
- [ACL 2026] PosterForest: Hierarchical Multi-Agent Collaboration for Scientific Poster Generation☆14Jun 12, 2026Updated 5 months ago
- Official repository of "Segment Anything with Motion, Geometry, and Semantic Adaptation for Complex Nonlinear Visual Object Tracking"☆11Sep 29, 2026Updated last month
- Real-Time Long Horizon Air Quality Forecasting via Group-Relative Policy Optimization☆16Sep 16, 2026Updated last month
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- Official Implementation for the paper "The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Co…☆15Apr 15, 2026Updated 6 months ago
- Official Implementation of EMNLP 2024 paper "Less is More: Making Smaller Language Models Competent Subgraph Retrievers for Multi-hop KGQ…☆13Aug 11, 2025Updated last year
- ☆12Apr 29, 2024Updated 2 years ago
- [NeurIPS 2026 Reviewed (5/5/4/3 - A/A/WA/WR)] MotionVLA: Vision-Language-Action Model for Humanoid Motion☆14Sep 25, 2026Updated last month
- [🏆CIKM'23] Official Repo for Uncertainty-aware Traffic Prediction under Missing Data☆10Dec 25, 2024Updated last year
- Artifacts for SoK: Can Trajectory Generation Combine Privacy and Utility?☆15Jun 27, 2024Updated 2 years ago
- A curated reading list on harness engineering for recursive self-improvement of LLM agents (EN/ZH).☆141Oct 23, 2026Updated 2 weeks ago
- triton ver of gqa flash attn, based on the tutorial☆12Aug 4, 2024Updated 2 years ago
- This is the office repository for ACL 2024 paper "Learning or Self-aligning? Rethinking Instruction Fine-tuning"☆11Aug 11, 2024Updated 2 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- MemAdapter: Counterfactual Adaptation Against Memory-induced Sycophancy☆34Oct 6, 2026Updated last month
- Self-Evolving Vision-Language Models for Image Quality Assessment via Voting and Ranking (ICLR 2026)☆27Jun 11, 2026Updated 5 months ago
- Official AHE code — Agentic Harness Engineering: observability-driven automatic evolution of coding-agent harnesses (concurrent w/ meta-h…☆969Oct 30, 2026Updated last week
- Code and Data for "GenAI Arena: An Open Evaluation Platform for Generative Models" [NeurIPS 2024]☆34Sep 8, 2024Updated 2 years ago
- Collection of papers, benchmarks and newest trends in the domain of End-to-end ToDs☆14Nov 18, 2023Updated 2 years ago
- ☆15Mar 12, 2026Updated 8 months ago
- A production-ready full-stack system that combines semantic search with spatial proximity to retrieve and reason over geospatial document…☆20Dec 2, 2025Updated 11 months ago
Are these results useful?