Multi-agent synthetic data generation pipeline capable of generating and validating long horizon terminal/coding tasks for RL training
☆76Jul 28, 2025Updated last year
Alternatives and similar repositories for tbench-agentic-data-pipeline
Users that are interested in tbench-agentic-data-pipeline are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- GRPO training code which scales to 32xH100s for long horizon terminal/coding tasks. Base agent is now the top Qwen3 agent on Stanford's T…☆419Aug 24, 2025Updated last year
- Convert GitHub PRs into Harbor tasks☆90Jul 13, 2026Updated 3 months ago
- ☆128Apr 1, 2026Updated 7 months ago
- 💻 SETA: Scaling Environments for Terminal Agents☆197Sep 30, 2026Updated last month
- TerminalWorld: Benchmarking Agents on Real-World Terminal Tasks (NeurIPS 2026 Evaluations and Datasets Track)☆54Updated this week
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- ☆148Mar 31, 2026Updated 7 months ago
- 💻 SETA: Scaling Environments for Terminal Agents - Environments☆152Feb 16, 2026Updated 8 months ago
- Measuring and evolving with the frontier of agent work☆1,018Updated this week
- ☆18Mar 28, 2026Updated 7 months ago
- [ICLR 2024] This is the official implementation for the paper: "Beyond imitation: Leveraging fine-grained quality signals for alignment"☆11May 5, 2024Updated 2 years ago
- A benchmark for LLMs on complicated tasks in the terminal☆2,614Jul 11, 2026Updated 3 months ago
- This is the office repository for ACL 2024 paper "Learning or Self-aligning? Rethinking Instruction Fine-tuning"☆11Aug 11, 2024Updated 2 years ago
- Terminal-Lego: What Makes Interaction Trajectories Effective for Training Terminal Agents?☆13Jun 4, 2026Updated 5 months ago
- ☆26Updated 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.
- Based on the R1-Zero method, using rule-based rewards and GRPO on the Code Contests dataset.☆18Apr 22, 2025Updated last year
- Advancing Small and Medium-sized Code Agents.☆17May 29, 2026Updated 5 months ago
- 🔱 Sailor2: Sailing in South-East Asia with Inclusive Multilingual LLMs☆74Mar 21, 2025Updated last year
- Data recipes and robust infrastructure for training AI agents☆309Oct 23, 2026Updated 2 weeks ago
- ☆15Oct 13, 2025Updated last year
- Terminal-Bench 2.1☆136Updated this week
- ☆193May 13, 2026Updated 5 months ago
- ☆46May 16, 2026Updated 5 months ago
- [ICLR 2025] Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates (Oral)☆85Oct 23, 2024Updated 2 years ago
- 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.
- [ICLR 2025] 🧬 RegMix: Data Mixture as Regression for Language Model Pre-training (Spotlight)☆219Feb 17, 2025Updated last year
- An open-source framework to benchmark and assess safety specifications of Reinforcement Learning problems.☆14Aug 25, 2023Updated 3 years ago
- ☆14Jul 31, 2025Updated last year
- ReasoningLens: a user-friendly toolkit to visualize, understand, and debug model reasoning chains.☆27Jul 7, 2026Updated 4 months ago
- Code for Paper: Training Software Engineering Agents and Verifiers with SWE-Gym [ICML 2025]☆758Updated this week
- [NeurIPS 2025 D&B] 🚀 SWE-bench Goes Live!☆262Updated this week
- [COLM 2025] Official repository for R2E-Gym: Procedural Environment Generation and Hybrid Verifiers for Scaling Open-Weights SWE Agents☆347Jul 13, 2025Updated last year
- Run SWE-bench evaluations remotely☆84Aug 14, 2025Updated last year
- Official implementation of "MoDoMoDo: Multi-Domain Data Mixtures for Multimodal LLM Reinforcement Learning"☆11Aug 23, 2025Updated last year
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- ☆441Apr 30, 2026Updated 6 months ago
- SWE-Flow: Synthesizing Software Engineering Data in a Test-Driven Manner☆40Jun 29, 2025Updated last year
- [DL4C @ NeurIPS 2025] On-Device Environment Setup via Online Reinforcement Learning☆13Dec 2, 2025Updated 11 months ago
- ☆41Apr 2, 2026Updated 7 months ago
- ☆11Sep 24, 2026Updated last month
- [NeurIPS 2025 D&B Spotlight] Scaling Data for SWE-agents☆825Updated this week
- Framework for evaluating and improving agents☆6,876Updated this week