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)
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…
📈 SmolDataEnvs (FineEnvs/SmolDataEnvs, RL dataset) 5.5K+ RL tasks for hill-climbing small models in code and data science.
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…
harborframework/terminal-bench-2.0 (harborframework/terminal-bench-2.0, Harbor dataset)
Terminal-Bench 3.0 (harborframework/terminal-bench-3.0, Harbor dataset)
Terminal-Bench-Science (harborframework/terminal-bench-science, Harbor dataset)
TerminalHorizon-Environment (shunzou05/TerminalHorizon-Environment, Harbor dataset) Scaling Agentic Data for Long-Horizon Terminal Intelligence Paper · Citation TerminalHorizon is a fully automated data synthesis engine for long-horizon…
PrimeIntellect/Terminal-Lego-15k (PrimeIntellect/Terminal-Lego-15k, Harbor dataset)
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…
TermGrade Band-Central: the 151-task selection and its splits (ai-and/termgrade-bandcentral-gemma4-31b-bash, Harbor dataset) Part of TermGrade: graded environments and trajectories for terminal agents. Read the blog post. 271 executable environments · every task carries a measured…
🧩 ProgramGym-1648 (ProgramGym/programgym-1648, Harbor dataset) A dataset of 1,648 tasks for long-horizon program reproduction agents.
SystemVerilog RL (HPAI-BSC/SystemVerilog-RL-12k, RL dataset) An RL dataset for SystemVerilog verification tasks. For each row, we ask the model to produce a self-checking testbench; a good testbench must pass on the…
Terminal-Bench (harborframework/terminal-bench, Harbor dataset)
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…
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…
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…
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…
Quant Desk — OpenEnv Arena dataset (Akahsizrr/quant-desk, RL dataset) Data for the Quant Desk OpenEnv environment: 36 deterministic, self-contained single-answer tasks spanning all eight Arena domains (software engineering…
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…
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…
📊 SmolDataEnvs: Harbor (train) (FineEnvs/SmolDataEnvs-harbor-train, 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…
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…
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…
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…
nvidia/Nemotron-RL-knowledge-mcqa (nvidia/Nemotron-RL-knowledge-mcqa, NeMo Gym dataset)
nvidia/Nemotron-RL-instruction_following (nvidia/Nemotron-RL-instruction_following, NeMo Gym dataset) The Nemotron-RL-instruction following is a dataset created by combining prompts from the WildChat-1M dataset (made available under the ODC Attribution…
SkillNet-Gym (zjunlp/SkillNet-Gym, Harbor dataset) SkillNet-Gym is a benchmark of 159 terminal-based tasks for evaluating agents in skill-rich, reproducible environments. This repository uses the native Harbor…
nvidia/Nemotron-RL-Instruction-Following-MultiTurnChat-v1 (nvidia/Nemotron-RL-Instruction-Following-MultiTurnChat-v1, NeMo Gym dataset) The MultiChallenge Dataset is a rigorous benchmark designed to improve large language models in complex multi-turn conversations by explicitly targeting…
nvidia/Nemotron-RL-instruction_following-structured_outputs (nvidia/Nemotron-RL-instruction_following-structured_outputs, NeMo Gym dataset) The Nemotron-RL-instruction following-structured outputs dataset tests the ability of the model to follow output formatting instructions under schema…
nvidia/Nemotron-3-Nano-RL-Training-Blend (nvidia/Nemotron-3-Nano-RL-Training-Blend, NeMo Gym dataset) Nemotron-3-Nano-RL-Training-Blend is a curated dataset blend used to train the Nemotron-3-Nano-30B-A3B model. The blend consists of the following component…
ORO Bench Agent Trajectories (oro-ai/orobench-trajectories, Harbor dataset) ORO runs an open competition for shopping agents. Participants submit agent implementations, independent validators execute submitted versions in shopping…
bpHigh/railsim-arena (bpHigh/railsim-arena, RL dataset) An OpenEnv environment for OpenEnv Arena in industrial and physical systems. The agent is the train dispatcher for Arriva's line between Leeuwarden and…
Fixed workspace reasoning and original MiMo repairs (akseljoonas/mimo-openenv-workspace-v5, RL dataset) A candidate curriculum of 32 public procedural data-workflow cases and two original MiMo code repairs. This is a preparation artifact, not evidence of a…
OpenEnv QE Arena tasks (Profa-QE/openenv-qe-arena-tasks, RL dataset) Public task instances for the openenv-qe-arena training environment (OpenEnv Arena, software-engineering domain).
RetroEnv-Curated (LiteFold/RetroEnv-Curated, RL dataset) Four splits for training and evaluating retrosynthesis agents, cut from LiteFold/RetroEnv. Each task gives a target molecule, a depth budget and optionally a…
Five Desks v5: a collapse test (positive control) (rca-umb/five-desks-control, RL dataset) This is a deliberate diagnostic, not an attempt to improve the model. It asks one question: does training in the arena reach the private-task score at all?…
Environments (spiderpilot89/zero-trust-physics-environments, Harbor dataset) Give an agent one question about a real thing and one tool. Is its answer the right one, and is everything it says the tool told it true? Zero-Trust Physics…
Mixed Skills OpenEnv Environment (cmunley/mixed-skills-env, RL dataset) One OpenEnv server with 50 deterministic, procedurally generated tasks in five families, 10 tasks each:
TraceLite EnvBench (OpenEnv) (TraceLite-AI/envbench-openenv, RL dataset) Five realistic ops and data jobs from TraceLite AI's EnvBench. Each task reads like an ordinary ticket ("add a hall column to the sensor statistics", "put the…
APIShift Env (yaswanth169/apishift-env, OpenEnv Space) OpenEnv where LLM agents learn API migration
Geoguesser Environment (FineEnvs/geoguesser-env, OpenEnv Space)
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…
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…
Repo2RLEnv SWE-Flow (FineEnvs/repo2rlenv-swe-flow, Harbor dataset) Trace passing repository tests, select exercised source functions, remove their implementations and generate a reconstruction instruction. Restore the…
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…
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…
skilltrainbench training tasks (armin-aptura/skilltrainbench-public, Harbor dataset) The training half of the skilltrainbench benchmark suite: for each of the four datasets, the dev task names of its pinned train/test split, in Harbor task…
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…
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
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…
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…
R2E-Gym-Subset-Verified (PrimeIntellect/R2E-Gym-Subset-Verified, Verifiers environment) Gold-patch-validated subset of R2E-Gym/R2E-Gym-Subset (paper). The train split contains 4,522 / 4,578 rows (98.78%) verified scoreable end-to-end: apply the…
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…
📊 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…
WildClawBench-Harbor (internlm/WildClawBench-Harbor, Harbor dataset) This repository is the WildClawBench benchmark converted to the Harbor task format, so that all 60 tasks can be run directly with harbor run against any…
Monthly-SWEBench 2026-05 (UnipatAI/Monthly-SWEBench-2026-05, Harbor dataset) This package contains the 2026-05 Monthly-SWEBench final release set. It includes 100 Harbor-format software engineering tasks selected from closed GitHub PRs…
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…
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…
Multi-SWE-RL-Verified (PrimeIntellect/Multi-SWE-RL-Verified, Verifiers environment) Gold-patch-validated subset of PrimeIntellect/Multi-SWE-RL-Reupload (ByteDance's Multi-SWE-RL): 2,232 / 4,703 rows across C, Go, Java, JavaScript, Rust, and…
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…
Monthly-SWEBench-2026-04 (UnipatAI/Monthly-SWEBench-2026-04, Harbor dataset) 90 tasks — 43 bugfix + 47 non-bugfix Tasks span diverse open-source repositories Each task includes a runnable environment, test suite, and reference solution
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…
Repo2RLEnv SWE-smith (FineEnvs/repo2rlenv-swe-smith, Harbor dataset) Apply owned procedural mutations to real repository functions, require an executable test contrast, and author a natural issue from bounded evidence. Contains…
Monthly-SWEBench-2026-03 (UnipatAI/Monthly-SWEBench-2026-03, Harbor dataset) 112 tasks — 68 bugfix + 44 non-bugfix Tasks span diverse open-source repositories Each task includes a runnable environment, test suite, and reference solution
TaskTrove Clean (open-athena/task-trove, Harbor dataset) All 12,720 tasks in laion swesmith-oracle-filtered-v2 now install the verifyit grading package at Marin commit a9adee624d703250556f8078b3d5beb18b4b57ab. This…
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…
📊 SmolDataEnvs: Harbor (test) (FineEnvs/SmolDataEnvs-harbor-test, Harbor dataset) 5.5K+ RL tasks for hill-climbing small models in code and data science.
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-gen (FineEnvs/repo2rlenv-swe-gen, Harbor dataset)
repo2rlenv-commit-runtime-v2 (FineEnvs/repo2rlenv-commit-runtime, Harbor dataset) Generated by Repo2RLEnv — turning real GitHub repositories into verifiable RL environments.
PortSimEnv on AgentEnv (earakely-scale/PortSimEnv-AgentEnv, RL dataset) GPT-6 Astra plays the lines week dock-24B-w07x1-busy-0-e09, APM Terminals Barcelona's busy week of 12 February 2024 in the wind of the storm week of 11…
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…
Repo2RLEnv R2E-Gym / SWEGEN (FineEnvs/repo2rlenv-r2e-gym, Harbor dataset) Mine supported bug-fix commits, measure failing-to-passing and regression tests across revisions, and export the buggy starting state and deterministic…
repo2rlenv-pr-runtime (FineEnvs/repo2rlenv-pr-runtime, Harbor dataset) Generated by Repo2RLEnv — turning real GitHub repositories into verifiable RL environments.
Repo2RLEnv SCALER (FineEnvs/repo2rlenv-scaler, Harbor dataset) Generate instances from owned reasoning families with seeded procedural samplers, deterministic references and family-specific answer verification; generation…
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…
🧪 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…
📊 SmolDataEnvs: Harbor (eval) (FineEnvs/SmolDataEnvs-harbor-eval, Harbor dataset) 5.5K+ RL tasks for hill-climbing small models in code and data science.
PatchRecoveryGym for Laguna (poolside-laguna-hackathon/patchrecoverygym-laguna, Verifiers environment) Submitted by: Kannappan Sirchabesan (@kannappans) · Poolside Research Hackathon (Foundations track) A reproducible eval + RL environment that tests whether a…
🎯 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…
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…
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…
SWE-Lego-Real-Data-Verified (PrimeIntellect/SWE-Lego-Real-Data-Verified, Verifiers environment) Gold-patch-validated subset of PrimeIntellect/SWE-Lego-Real-Data (itself a fixed fork of SWE-Lego's real-data split). The resolved split contains 4,323 /…
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…
repo2rlenv-pr-diff (FineEnvs/repo2rlenv-pr-diff, Harbor dataset) Generated by Repo2RLEnv — turning real GitHub repositories into verifiable RL environments.
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:
repo2rlenv-code-instruct (FineEnvs/repo2rlenv-code-instruct, Harbor dataset) Generated by Repo2RLEnv — turning real GitHub repositories into verifiable RL environments.
repo2rlenv-equivalence-tests (FineEnvs/repo2rlenv-equivalence-tests, Harbor dataset) Generated by Repo2RLEnv — turning real GitHub repositories into verifiable RL environments.
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…
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…
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
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…
MegaTerminal (di-zhang-fdu/MegaTerminal, Harbor dataset) MegaTerminal is a Harbor-style terminal task-folder dataset assembled from the terminal task sources collected for task matching experiments. The task folders…
Monkey Business (ScalingIntelligence/monkey_business, Verifiers environment) Monkey Business is a dataset of samples from large language models. It contains both correct and incorrect samples from a variety of models (the Llama-3…
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…
repo2rlenv-cve-patches (FineEnvs/repo2rlenv-cve-patches, Harbor dataset) Generated by Repo2RLEnv — turning real GitHub repositories into verifiable RL environments.
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…
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…
Terminal-Bench 2.1 (offline Apptainer, v1) (laion/terminal-bench-2-1-apptainer-v1, Harbor dataset) A validated subset of Terminal-Bench 2.1 (revision 7131e4375048a0e408a8fb404b5f499d726b695b, Apache-2.0) for running on HPC clusters without Docker 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…
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…
🐚 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.
Keep the failed attempts. Check the artifact. (glayguo/noteflow-research-pilots, Harbor dataset) Versioned public development evidence from Robot Reel × Skills Anywhere × EvalArc, recorded 14 September 2026 on an NVIDIA L40S, with separate scripted Harbor…
Watercolour reference pool (FineEnvs/watercolour-reference-pool, RL dataset) The reference paintings that define the reward in the watercolour RL environment: an agent writes a p5.brush sketch, the sketch is rendered, and a vision…
Multilingual Multimodal RL runs (FineEnvs/multilingual-multimodal-rl-runs, RL dataset) The evidence behind the two Kannada GRPO runs in the Multilingual Multimodal Envs collection: what the model wrote for every held-out item at every…
nvidia/Nemotron-RL-Agentic-Function-Calling-Pivot-v1 (nvidia/Nemotron-RL-Agentic-Function-Calling-Pivot-v1, NeMo Gym dataset) This is a RL dataset for general function-calling by utilizing existing expert tool-use trajectories. We pose each assistant step of the trajectory as a…
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…
AACR-Bench Harbor (osolmaz/aacr-bench-harbor, Harbor dataset)
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…
Watercolour rollouts, judge-led run (FineEnvs/watercolour-rollouts-judge-led, RL dataset) Browse these paintings in the gallery Space, by step and by reward, with the sketch that made each one.
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…
TaskCompendium spike examples (open-athena/taskcompendium-spike, Harbor dataset) Schema 0.9 contains 63 semantic TaskSpec records and 164 Harbor lowerings. A TaskSpec defines the problem, semantic requirements, provenance, and private…
Nemotron Terminal easy clean-1K: rootless Apptainer release (laion/nemotron-terminal-easy-clean1k-rootless-apptainer, Harbor dataset) This derived release contains exactly 1,000 balanced easy tasks from four Nemotron Terminal domains. It is pinned to…
MegaTerminal-Hard-1K (jwu323/MegaTerminal-Hard-1K, Harbor dataset) The 1,000 highest-quality, hardest terminal-agent tasks selected from the 11,599 tasks in di-zhang-fdu/MegaTerminal. Every task is a complete, self-contained…
openai/math as Harbor environments (raising-heart/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…
nvidia/Nemotron-RL-coding-competitive_coding (nvidia/Nemotron-RL-coding-competitive_coding, NeMo Gym dataset) The Nemotron-RL-coding-competitive coding dataset is a python-only, reasoning-based, synthetic dataset. It contains competitive coding style problems and…
nvidia/Nemotron-RL-Agentic-SWE-Pivot-v1 (nvidia/Nemotron-RL-Agentic-SWE-Pivot-v1, NeMo Gym dataset) The SWE-RL dataset provides GitHub issues for training and validating real-world software engineering agents using the OpenHands environment in NeMo Gym. The…

Community rollouts · MiMo-V2.6 RL