RL environments on the Hugging Face Hub
Explore reinforcement learning environments and tasks on the Hugging Face Hub. Browse OpenEnv, Harbor, MiMo, NeMo Gym and Verifiers, inspect rewards, and run supported agent rollouts.
- Agentic RL Environments (XiaomiMiMo/MiMo-V2.6-RL-oss, MiMo RL release)
- Agentic coding environments (harness-hub/harness-adapters, Harbor dataset) This private repository preserves the original write-42 pipeline pilot and adds six original coding environments in the separate synthetic gap v1 split. See…
- RepoFactory (IQuestLab/RepoFactory, Harbor dataset) 200 verifiable environments for full-repository generation. RepoFactory constructs training environments for long-horizon coding agents from real-world…
- Terminal-Bench 2.1 (Harbor git-repos dataset) (harborframework/terminal-bench-2.1, Harbor dataset)
- TermGrade Environments: 1,004 executable Linux tasks (ai-and/termgrade-environments, Harbor dataset) Part of TermGrade: graded environments and trajectories for terminal agents. Read the blog post. 1,004 executable environments · graded by 6 models · measured…
- Science Prediction Universe (SPU) (UnipatAI/SPU, Harbor dataset) Science Prediction Universe (SPU) is a benchmark of hidden wet-lab outcomes. Each task fixes the candidates, materials, conditions and measurement protocol of…
- Terminal-Bench (harborframework/terminal-bench, Harbor dataset)
- Terminal-Bench-Science (harborframework/terminal-bench-science, Harbor dataset)
- 📊 Data Agent — Harbor (train) (FineEnvs/data-agent-harbor-train, Harbor dataset) Teach an agent to actually do data science. This is a suite of 5,000 hands-on data-analysis tasks: each one drops your agent into a sandbox with a real…
- Long-Horizon Terminal-Bench (LHTB) (IntelligenceLab/Long-Horizon-Terminal-Bench, Harbor dataset) Leaderboard: the panel at the top of this page has two views. Use the Task menu in its top-right corner to switch between Lhtb2 Solved (LHTB 2.0, out of 77…
- Human Behavior Atlas (HumanBehaviorAtlas/human_behavior_atlas, RL dataset) A large-scale multimodal dataset for human behavior understanding, spanning emotion recognition, sentiment analysis, humor detection, mental health screening…
- ExtractBench (llamaindex/ExtractBench, Harbor dataset) Quick links: 🌐 Website 📜 Paper 💻 Code Given a document and a schema, a system returns structured data with evidence. The input is a full document…
- RL tasks generated with traj2envs (harness-hub/traj2envs-rl, Harbor dataset) 270 Harbor tasks under tasks/, each with its environment image pinned in task.toml ( environment .docker image, with opencode preinstalled), a top-level…
- SWE-rebench V2.1: Harbor (ibragim-bad/SWE-rebench-V2.1-harbor, Harbor dataset) 21,272 executable software-engineering tasks as ready-to-run Harbor task directories. Each task is a real GitHub issue: the agent edits the repository inside…
- Unslop (Harbor) (rawmodels/unslop-harbor, Harbor dataset) 200 Harbor tasks with the reward we trained AlexWortega/Qwen3.8-27B-antislop on. Your model finishes a tweet or writes a HumanEval function body. Claude Opus…
- FACET-Terminal-Tasks-6k (FACET-Terminal/FACET-Terminal-Tasks-6k, Harbor dataset) 6,020 execution-grounded tasks for terminal agents, coding agents, and executable workflow research
- nvidia/Nemotron-RL-Ultra-Training-Blends (nvidia/Nemotron-RL-Ultra-Training-Blends, NeMo Gym dataset) This dataset provides Reinforcement Learning (RL) and Multi-teacher On-Policy Distillation (MOPD) training-data blends used by the public Nemotron-3-Ultra…
- Scale-SWE-Verified (PrimeIntellect/Scale-SWE-Verified, Verifiers environment) Gold-patch-validated fork of AweAI-Team/Scale-SWE (paper): 17,202 / 20,181 Python issue-resolving tasks that produce a clean reward signal end-to-end. Default…
- OpenAI Math Lemmas (bkhtmm/openai-math-lemmas, Harbor dataset) From one formal-math problem to 47 independently checkable Lean proof tasks. We extracted 47 supporting lemmas from the reference proof of…
- nvidia/Nemotron-RL-ReasoningGym-v1 (nvidia/Nemotron-RL-ReasoningGym-v1, NeMo Gym dataset) The Nemotron-RL-ReasoningGym-v1 dataset is designed to improve reasoning capabilities across a broad range of domains, including algebra, arithmetic…
- SWE-rebench V2.1 (ibragim-bad/SWE-rebench-V2.1, Harbor dataset) 21,272 executable software-engineering tasks for training and evaluating coding agents. Each task is a real GitHub issue with the merged fix as the reference…
- nvidia/Nemotron-RL-Science-v1 (nvidia/Nemotron-RL-Science-v1, NeMo Gym dataset) Nemotron-RL-Science-v1 is a reinforcement learning (RL) dataset for science reasoning. Each example provides a problem, a reference answer, and a verifiable…
- earakely-scale/AirOpsEnv-AgentEnv (earakely-scale/AirOpsEnv-AgentEnv, RL dataset) Three GPT-6.1 Sol desks run JetBlue's network through the storm of Tuesday 8 July 2025 (b6-20250708-0400), shown at Kennedy: 637 flights from 04:00 with…
- Calendar-Scheduling-Dataset (nvidia/Nemotron-RL-agent-calendar_scheduling, NeMo Gym dataset) The Calendar-Scheduling-Dataset is a multi-turn conversation dataset that can understand natural language scheduling constraints, follow instructions across…
- oro-agents/smb-bench (oro-agents/smb-bench, Harbor dataset) By ORO AI (Shardul Bansal, Seth Schilbe, Jarrod Barnes) Placed in a long time horizon simulation, can AI learn from the delayed consequences of its own…
- Nemotron-RL-SysBench-v1 (nvidia/Nemotron-RL-SysBench-v1, NeMo Gym dataset) License: cc-by-4.0 Language: en Task Categories: reinforcement-learning, text-generation Tags: instruction-following, system-message-following, multi-turn…
- RuneBench skills-30m: tencent/hy4-flash on Harbor Pi (mariofilho/runebench-hy4flash-pi-traces, Harbor dataset) Sixteen raw event streams, one per RuneBench skill, 30-minute horizon. They are pi's session logs (--mode json --session-dir), written while Harbor drove the…
- Finance SignOff Bench (human-intelligence-ai/Finance-SignOff-Bench, Harbor dataset) English Finance SignOff Bench 是面向中文金融专业工作的智能体评测。每道题由金融从业者按真实工作场景编写,包括业务角色、一组工作材料和交付要求。模型需要独立完成 Word、Excel 等专业交付物,再由裁判模型对照出题专家写的评分细则逐条判定。…
- AgentGridWorld Hard (bytkim/AgentGridWorld-Hard, Harbor dataset) Nine small grid-world tasks for testing what an AI agent does when its target and its rules pull apart. Each task gives the agent a goal, rules it must keep…
- HallucinationGuard-Env (SamSankar/hallucination-guard-env, OpenEnv Space)
- Watercolour Environment Server (FineEnvs/watercolour-env, OpenEnv Space)
- Paygorn | HFT Auditor (SamaKool/Elite-Trade-Sentry, OpenEnv Space)
- Terminal-Bench 3.0 (harborframework/terminal-bench-3.0, Harbor dataset)
- 📈 SmolDataEnvs (FineEnvs/SmolDataEnvs, RL dataset) 5.5K+ RL tasks for hill-climbing small models in code and data science.
- Spreadsheet-RL Dataset (Spreadsheet-RL/Spreadsheet-RL, RL dataset) This dataset contains the training and evaluation data used by Spreadsheet-RL, a reinforcement learning framework for spreadsheet agents that edit Excel…
- harborframework/terminal-bench-2.0 (harborframework/terminal-bench-2.0, Harbor dataset)
- Zhanli-Li/DataWorld-Train-2k-part1 (Zhanli-Li/DataWorld-Train-2k-part1, Harbor dataset) Scaling Data Environments from Scratch Specify the world behind the files. Generate the data. Ground the supervision.
- Zhanli-Li/DataWorld-Train-2k-part2 (Zhanli-Li/DataWorld-Train-2k-part2, Harbor dataset) Scaling Data Environments from Scratch Specify the world behind the files. Generate the data. Ground the supervision.
- 📊 SmolDataEnvs: Harbor (train) (FineEnvs/SmolDataEnvs-harbor-train, Harbor dataset) 5.5K+ RL tasks for hill-climbing small models in code and data science.
- RTS-1K: offline rootless Apptainer release (laion/rts-1k-rootless-apptainer, Harbor dataset) This derived release contains 984 tasks from Recursive Task Synthesis. RTS-1K is the stable project label; the exact size is 984. The tasks are the strict…
- 🧩 ProgramGym-1648 (ProgramGym/programgym-1648, Harbor dataset) A dataset of 1,648 tasks for long-horizon program reproduction agents.
- SWE-Lego-RL-2699 (Lego-X/Lego-RL-2699, Harbor dataset) 2,699 executable, difficulty-filtered SWE tasks for agentic RL, shipped in two parallel views of the same instances:
- BlenderWorld (Qwen/BlenderWorld, Harbor dataset) BlenderWorld is the first comprehensive benchmark dedicated to evaluating frontier models on realistic 3D creation tasks. BlenderWorld comprises 223 tasks…
- openai/math as Harbor environments (FineEnvs/openai-math, Harbor dataset) Experimental. Built on a research release that is itself new and not yet independently reviewed. Expect rough edges, and read any proof that scores 1 before…
- Reverse-Text-RL (PrimeIntellect/Reverse-Text-RL, Verifiers environment) A small, scrappy RL dataset used in prime-rl's CI to debug RL training asking a model to reverse small sentences character-by-character. Follows the general…
- MiMo-V2.6-RL Terminal (Harbor) (FineEnvs/MiMo-V2.6-RL-harbor-terminal, Harbor dataset) Terminal-Bench style tasks. 64 Harbor tasks from the Terminal domain of Xiaomi's MiMo-V2.6-RL-oss, the RL environments MiMo-V2.6 was trained on, converted so…
- MiMo-V2.6-RL Code (Harbor) (FineEnvs/MiMo-V2.6-RL-harbor-code, Harbor dataset) Fix a real issue in a real repository. 2,698 Harbor tasks from the Code domain of Xiaomi's MiMo-V2.6-RL-oss, the RL environments MiMo-V2.6 was trained on…
- SimReadyBench A benchmark for simulation-ready asset reconstruction (hcltech-robotics/simreadybench, Harbor dataset) Chris von Csefalvay, Pranav Doma, Achyuthan Unni Krishnan and Tamas Foldi
- MiMo-V2.6-RL Cyber (Harbor) (FineEnvs/MiMo-V2.6-RL-harbor-cyber, Harbor dataset) Reproduce a real memory-safety crash (ARVO). 1,000 Harbor tasks from the Cyber domain of Xiaomi's MiMo-V2.6-RL-oss, the RL environments MiMo-V2.6 was trained…
- 🐚 Agent Harbor Tasks (efederici/agent-harbor-tasks, Harbor dataset) 400 original shell-agent tasks, Italian and English, from a 4-call chore to a 20-call investigation.
- Lego-X/LegoFlow-SWE (Lego-X/LegoFlow-SWE, Harbor dataset) LegoFlow-SWE · 5,000 verified Harbor SWE tasks and two GLM-5.2 trajectory releases
- Validated tasks (FWeindel/validated-tasks, Harbor dataset) Datasets repaired and filtered using the OT-next-data validation protocol.
- ExtractBench Pro (llamaindex/ExtractBenchPro, Harbor dataset) Quick links: 🌐 Website 💻 Code 📚 ExtractBench ExtractBench Pro is the hard companion to ExtractBench. The task is the same: given a full document and a…
- TerminalHorizon-Environment (shunzou05/TerminalHorizon-Environment, Harbor dataset) Scaling Agentic Data for Long-Horizon Terminal Intelligence Paper · Project Page · Citation TerminalHorizon is a fully automated data synthesis engine for…
- MiMo-V2.6-RL General (Harbor) (FineEnvs/MiMo-V2.6-RL-harbor-general, Harbor dataset) Work in a simulated company through its MCP systems. 925 Harbor tasks from the General domain of Xiaomi's MiMo-V2.6-RL-oss, the RL environments MiMo-V2.6 was…
- AgentTrove (open-thoughts/AgentTrove, Harbor dataset) AgentTrove is the largest open-source collection of agentic interaction traces to date, released by the OpenThoughts-Agent team. It contains 1,696,847 rows…
- dabstep-harbor (AdithyaSK/dabstep-harbor, Harbor dataset) A /workdir-native Harbor edition of DABstep. 450 financial-analytics factoid tasks over a single shared Adyen-payments corpus — every task's working…
- 📊 SmolDataEnvs: Harbor (test) (FineEnvs/SmolDataEnvs-harbor-test, Harbor dataset) 5.5K+ RL tasks for hill-climbing small models in code and data science.
- WildClawBench-Harbor (internlm/WildClawBench-Harbor, Harbor dataset) All 60 WildClawBench tasks as Harbor task directories. Point harbor run at this folder and any Harbor agent (Claude Code, Codex CLI, OpenHands, Gemini CLI or…
- MiMo-V2.6-RL Webdev (Harbor) (FineEnvs/MiMo-V2.6-RL-harbor-webdev, Harbor dataset) Build a website from a design brief. 2,093 Harbor tasks from the Webdev domain of Xiaomi's MiMo-V2.6-RL-oss, the RL environments MiMo-V2.6 was trained on…
- LHTB Leaderboard — Long-Horizon Terminal-Bench (IntelligenceLab/LHTB-leaderboard, Harbor dataset) This repository hosts submitted runs for Long-Horizon Terminal-Bench (LHTB), a 46-task benchmark measuring how well LLM agents sustain useful work in a…
- TaskTrove (open-thoughts/TaskTrove, Harbor dataset) v5.1 (current) — independent-review source retirement — moves 15 sources with majority or unanimous REJECT verdicts out of the default config and into…
- Environments (zero-trust-physics/zero-trust-physics-environments, Harbor dataset) Protocol Company · zerotrustphysics.com · Domain Packs for RL & SFT: 30 withheld calibrated tasks + 100,000 sealed runs + offline --network none verifier…
- 📊 SmolDataEnvs: Harbor (eval) (FineEnvs/SmolDataEnvs-harbor-eval, Harbor dataset) 5.5K+ RL tasks for hill-climbing small models in code and data science.
- AdithyaSK/data_agent_rl_environment_train_multireward (AdithyaSK/data_agent_rl_environment_train_multireward, Harbor dataset) Multi-reward variant of AdithyaSK/data agent rl environment train (2238 tasks, identical data/instructions). The only change: each task's verifier now emits a…
- 🗂️ Scrivania Harbor (efederici/scrivania-harbor, Harbor dataset) 3,360 everyday computer-use tasks for shell agents, Italian and English, 2–5 tool calls each, graded on the final state and on collateral damage.
- Repo2RLEnv TMax (FineEnvs/repo2rlenv-tmax, Harbor dataset) Sample the native TMax legacy taxonomy, create a template, initial-state tests and final completion tests in distinct stages, then build fixtures and a…
- Repo2RLEnv TerminalWorld (EuniAI) (FineEnvs/repo2rlenv-terminalworld, Harbor dataset) Screen original public terminal recordings, score feasibility and value, extract and refine a solution, write its instruction, reconstruct an offline…
- data_agent_rl_environment_train (AdithyaSK/data_agent_rl_environment_train, Harbor dataset) The official verified training suite for the data-agent RL pipeline. 2238 Harbor-format data-analysis tasks, each with:
- MESSIER (Andromede-AI/messier, Verifiers environment) A High-Resolution Corpus for Cross-Benchmark Agent Evaluation
- LoLBench (lolbench26/LoLBench, Harbor dataset) Software development often begins with user intent and high-level design rather than an implementation-ready specification. Developers must ground those goals…
- Agent World Model in the Wild (ChilleD/WildAWM, Harbor dataset) Agent World Model in the Wild (WildAWM) releases 341 accepted cross-interface (cli/mcp/web) tasks over frozen persona-day worlds in Harbor task format, split…
- 🎯 Data Agent — Harbor (test) (FineEnvs/data-agent-harbor-test, Harbor dataset) A held-out benchmark for data-analysis agents: 250 tasks, deliberately balanced across difficulty and leaning toward the harder end so it actually separates…
- CADForge CadQuery Agentic Traces (sanjuhs/cadforge-cadquery-agentic-traces, RL dataset) This dataset contains agentic CadQuery repair traces for CAD generation and RLVE/RLVR experiments. Each trace step has:
- Procedural Pile (reasoning-core/procedural-pile, Verifiers environment) Verifiable reasoning problems, generated by code, formatted as supervised training data. Procedural Pile contains 24,806,238 problems from 55 task families…
- nvidia/Nemotron-RL-agent-workplace_assistant (nvidia/Nemotron-RL-agent-workplace_assistant, NeMo Gym dataset) The Nemotron-RL-agent-workplace assistant is a tool use - multi step agentic environment that tests the agent’s ability to execute tasks in a workplace…
- ContractBench (micro1-inc/ContractBench, Harbor dataset) ContractBench measures how well an AI agent reviews and redlines a commercial contract the way an in-house attorney would: deciding where to intervene, what…
- 🧪 Data Agent — Harbor (eval) (FineEnvs/data-agent-harbor-eval, Harbor dataset) A small, difficulty-balanced validation split — 144 tasks — perfect for quick checkpoints while you train. Same idea as the rest of the family: your agent…
- PrimeIntellect/Terminal-Lego-15k (PrimeIntellect/Terminal-Lego-15k, Harbor dataset)
- 🛠️ smol-software-harbor (efederici/smol-software-harbor, Harbor dataset) 1,002 small, verifiable software-engineering tasks on 576 hand-written mini-codebases in 12 languages, for small coding agents: read, find the right place…
- MiMo-V2.6-RL Music (Harbor) (FineEnvs/MiMo-V2.6-RL-harbor-music, Harbor dataset) Compose a piece in ABC notation. 1,000 Harbor tasks from the Music domain of Xiaomi's MiMo-V2.6-RL-oss, the RL environments MiMo-V2.6 was trained on…
- GridSimEnv Desk (earakely-scale/GridSimEnv-AgentEnv, RL dataset) GridSimEnv hands an AI agent the trading desk of a real battery on the Texas grid. For three days at a time, while a real heat wave or winter storm sweeps…
- SWE-rebench-V2-Filtered-Verified (PrimeIntellect/SWE-rebench-V2-Filtered-Verified, Verifiers environment) Filtered and gold-patch-verified subset of Nebius's SWE-rebench-V2 (paper): 6,272 / 32,079 freshly-mined GitHub PR tasks across 17 languages. Default dataset…
- Repo2RLEnv SWE-gen (FineEnvs/repo2rlenv-swe-gen, Harbor dataset)
- DesignGym SFT (AdithyaSK/designgym-sft, RL dataset) Verified, natural trajectories that rebuild Crello train designs in DesignGym, one schema (cua-v1) across eight subsets. Every trajectory was replayed through…
- nvidia/Nemotron-RL-knowledge-mcqa (nvidia/Nemotron-RL-knowledge-mcqa, NeMo Gym dataset)
- Repo2RLEnv Endless Terminals (FineEnvs/repo2rlenv-endless-terminals, Harbor dataset) Sample native terminal categories, complexity and scenarios; author instructions and private expected behavior, initial-state tests, final tests, fixtures and…
- SkillFlow Test Tasks (zhang-ziao/SkillFlow-Task, Harbor dataset) SkillFlow Test Tasks is the task repository used in the SkillFlow benchmark for evaluating lifelong skill discovery, skill revision, and cross-task procedural…
- Terminal-Bench Hard (Zhongzhi1228/Terminal-Bench-Hard, Harbor dataset) Terminal-Bench Hard is a set of 100 challenging terminal-based agent tasks. The tasks cover software engineering, debugging, data processing, system…
- Repo2RLEnv SETA Evol (FineEnvs/repo2rlenv-seta-evol, Harbor dataset) Start with complete Harbor parents, apply one of six named evolution strategies, then author a complete child task with its own instruction, environment…
- Repo2RLEnv DataArc terminal synthesis (Envs-FORGE-linked code) (FineEnvs/repo2rlenv-dataarc, Harbor dataset) Read complete Harbor parent tasks and enumerate few-shot, self-instruct and evolution transformations. Author a complete child environment, instruction…
- WebsiteBench (TIGER-Lab/WebsiteBench, Harbor dataset) Given a production-level website they can explore through a browser, agents must reverse-engineer a full-stack version that matches its appearance and…
- Repo2RLEnv SETA Seed2Synth (FineEnvs/repo2rlenv-seta-seed2synth, Harbor dataset) Use attributed Unix Stack Exchange questions and accepted answers to design terminal tasks, then author self-contained offline environments, instructions…
- SWE-bench Science (OpenMOSS-Team/SWE-bench-Science, Harbor dataset) SWE-bench Science evaluates coding agents on software-engineering tasks drawn from scientific-computing repositories. The release contains 119 tasks across 20…
- APEX-Accounting — Harbor edition (10-task dev set) (mercor/apex-accounting-harbor, Harbor dataset) APEX-Accounting is a benchmark built by Mercor in partnership with Ramp to assess whether frontier models can do the real work of accountants: reconciling…
- 🔪 Bisturi Harbor (efederici/bisturi-harbor, Harbor dataset) 2,520 precise, fully specified multi-step file edits for agents, Italian and English: configs, simple code and everyday prose, each file full of near-matches.
- nvidia/Nemotron-RL-Agentic-Conversational-Tool-Use-Pivot-v1 (nvidia/Nemotron-RL-Agentic-Conversational-Tool-Use-Pivot-v1, NeMo Gym dataset) We created an RL dataset for conversational tool-use by utilizing existing expert tool-use trajectories. We pose each assistant step of the trajectory as a…
- HF ML Tasksmith (FineEnvs/HF_ML_Tasksmith, Harbor dataset) Fifty PR-derived Harbor tasks from Accelerate, Diffusers, PEFT, Transformers and TRL, including CPU and GPU tasks. Contains 50 Harbor tasks generated with the…
- repo2rlenv-pr-runtime (FineEnvs/repo2rlenv-pr-runtime, Harbor dataset) Generated by Repo2RLEnv — turning real GitHub repositories into verifiable RL environments.
- retail (leibler/retail, RL dataset) An executable Environment for tool-using agents, rebuilt from recorded traces. Release: 100.0% (223 of 223) of its Tasks replay as recorded.
- Endless Terminals 1K: rootless Apptainer release (laion/endless-terminals-rootless-apptainer, Harbor dataset) This release contains exactly 1,000 tasks from Endless Terminals, pinned to obiwan96/endless-terminals@26ecf78458e7f756e4d06780d5fbf3dd78e91815 and validated…
- 📊 SmolDataEnvs: Harbor (train) (ybelkada/SmolDataEnvs-harbor-train-sandbox, Harbor dataset) 5.5K+ RL tasks for hill-climbing small models in code and data science.
- Multi-SWE-bench (PrimeIntellect/Multi-SWE-bench, Verifiers environment) Re-upload of ByteDance's Multi-SWE-bench evaluation benchmark: 2,132 issue-resolving tasks across the seven Multi-SWE languages. This is the held-out eval…
- repo2rlenv-pr-diff (FineEnvs/repo2rlenv-pr-diff, Harbor dataset) Generated by Repo2RLEnv — turning real GitHub repositories into verifiable RL environments.
- Five Desks v12: SkillsBench siblings, light-touch run (rca-umb/five-desks-siblings, RL dataset) An OpenEnv environment for the OpenEnv Arena. Every task is a sibling of a named public SkillsBench v1.1 task. It does the same kind of work, uses the same…
- repo2rlenv-commit-runtime-v2 (FineEnvs/repo2rlenv-commit-runtime, Harbor dataset) Generated by Repo2RLEnv — turning real GitHub repositories into verifiable RL environments.
- Repo2RLEnv R2E (FineEnvs/repo2rlenv-r2e, Harbor dataset) Author equivalence tests around repository functions, measure their execution and coverage remotely, and export function-reconstruction tasks with the…
- Repo2RLEnv SWE-Next (FineEnvs/repo2rlenv-swe-next, Harbor dataset) Mine real repository history for supported code changes and associated tests, preserve regression behavior, and export the historical implementation change as…
- Nemotron-RL-Agentic-Indirect-Prompt-Injection-v1 (nvidia/Nemotron-RL-Agentic-Indirect-Prompt-Injection-v1, NeMo Gym dataset) Nemotron-RL-Agentic-Indirect-Prompt-Injection-v1 is an RL dataset for training and evaluating a tool-using agent's ability to resist Indirect Prompt Injection…
- OpenClaw EvalMix (zt1106/OpenClaw-EvalMix, Harbor dataset) OpenClaw EvalMix is a Harbor-format collection of 360 agent-evaluation tasks across four task families. Each task directory includes task.toml, an…
- airline (leibler/airline, Harbor dataset) An executable Environment for tool-using agents, rebuilt from recorded traces. Release: 100.0% (130 of 130) of its Tasks replay as recorded.
- TerminalWorld Seeds, oracle-validated (andylizf/TerminalWorld-Seeds-Clean, Harbor dataset) The current TW selection retains 405 tasks, excluding any original TW task excluded by either the preserved local quality curation or the upstream v3 training…
- repo2rlenv-code-instruct (FineEnvs/repo2rlenv-code-instruct, Harbor dataset) Generated by Repo2RLEnv — turning real GitHub repositories into verifiable RL environments.
- jupyter-agent-eval-v1 — Harbor task suite (AdithyaSK/jupyter-agent-eval-v1-harbor, Harbor dataset) 100 Harbor task(s) for the Jupyter data-analysis agent. Each task is one (question, gold answer) pair against a real Kaggle dataset.
- Harbor SWE-Smith 强化学习数据产物 (keryszhan/harbor-swesmith-rl-artifacts, Harbor dataset) 本数据集是 Harbor Qwen 工具调用代码智能体强化学习项目使用的冻结任务集,服务于 GRPO、原生价值模型/GAE PPO、训练过程诊断和统一协议评测。 项目已于 2026 年 8 月 30 日完成 P0…
- nvidia/Nemotron-RL-Instruction-Following-Structured-Outputs-v2 (nvidia/Nemotron-RL-Instruction-Following-Structured-Outputs-v2, NeMo Gym dataset) Split 1: Direct Generation tests the model’s ability to perform freeform text structured outputs on JSON, YAML, and XML data, varying the complexity and…
- HubBench 1.4.0 (SamuelChien821/hubbench, Harbor dataset) One Blobfish-authored, oracle-proven benchmark family per Harbor Hub professional-domain cluster. Every task is an employee decision worked over a dependent…
- Repo2RLEnv CLI-Gym (FineEnvs/repo2rlenv-cli-gym, Harbor dataset) Start with a healthy repository, synthesize a disruption and recovery, verify that damage breaks the original tests and recovery restores them, then export an…
- SOTOPIA-hard for Harbor (open-athena/sotopia-hard-harbor, Harbor dataset) This repository contains the 100-task SOTOPIA-hard split generated by the SOTOPIA adapter in marin-community/harbor at commit…
- ProgramDistill-Bench (microsoft/ProgramDistill, Harbor dataset) ProgramDistill is a dataset and executable benchmark for evaluating whether coding agents can restore missing behavior in interactive web applications. Each…