Two Minds Better Than One: Collaborative Reward Modeling for LLM Alignment
Paper
•
2505.10597
•
Published
Finetune data
-
-
COIG-P: A High-Quality and Large-Scale Chinese Preference Dataset for Alignment with Human Values
Paper • 2504.05535 • Published • 44 -
nvidia/HelpSteer3
Viewer • Updated • 133k • 2.67k • 93 -
nvidia/Nemotron-RL-instruction_following
Preview • Updated • 157 • 7 -
nvidia/Nemotron-RL-knowledge-web_search-mcqa
Viewer • Updated • 2.93k • 479 • 5 -
nvidia/Nemotron-RL-agent-workplace_assistant
Viewer • Updated • 1.8k • 393 • 9 -
nvidia/Nemotron-RL-instruction_following-structured_outputs
Viewer • Updated • 9.95k • 374 • 25 -
nvidia/Nemotron-RL-knowledge-mcqa
Viewer • Updated • 686k • 392 • 7 -
nvidia/Nemotron-RL-math-OpenMathReasoning
Updated • 214 • 10 -
nvidia/Nemotron-RL-knowledge-openqa
Viewer • Updated • 136k • 188 • 7 -
nvidia/Nemotron-RL-math-advanced_calculations
Viewer • Updated • 6k • 123 • 8 -
nvidia/Nemotron-AIQ-Agentic-Safety-Dataset-1.0
Viewer • Updated • 10.8k • 5.75k • 10 -
nvidia/Nemotron-VLM-Dataset-v2
Viewer • Updated • 4.58M • 13.2k • 76 -
nvidia/ProfBench
Viewer • Updated • 40 • 313 • 19 -
google/code_x_glue_cc_code_completion_token
Viewer • Updated • 178k • 430 • 8 -
google/code_x_glue_cc_cloze_testing_all
Viewer • Updated • 176k • 312 • 5 -
google/code_x_glue_cc_clone_detection_big_clone_bench
Viewer • Updated • 1.73M • 600 • 20 -
google/code_x_glue_ct_code_to_text
Viewer • Updated • 1.01M • 4.59k • 77 -
google/code_x_glue_tc_nl_code_search_adv
Viewer • Updated • 281k • 697 • 10 -
TeichAI/claude-sonnet-4.5-high-reasoning-250x
Viewer • Updated • 247 • 415 • 28 -
Idea2Plan: Exploring AI-Powered Research Planning
Paper • 2510.24891 • Published -
TGPR: Tree-Guided Policy Refinement for Robust Self-Debugging of LLMs
Paper • 2510.06878 • Published • 1 -
FML-bench: A Benchmark for Automatic ML Research Agents Highlighting the Importance of Exploration Breadth
Paper • 2510.10472 • Published • 8 -
Scientific Algorithm Discovery by Augmenting AlphaEvolve with Deep Research
Paper • 2510.06056 • Published • 5 -
RECODE-H: A Benchmark for Research Code Development with Interactive Human Feedback
Paper • 2510.06186 • Published -
AlphaResearch: Accelerating New Algorithm Discovery with Language Models
Paper • 2511.08522 • Published • 17 -
Anthropic/hh-rlhf
Viewer • Updated • 169k • 23.7k • 1.61k -
open-thoughts/OpenThoughts3-1.2M
Viewer • Updated • 1.2M • 11.2k • 197 -
nex-agi/agent-sft
Preview • Updated • 420 • 102 -
Open-Bee/Honey-Data-15M
Viewer • Updated • 14.8M • 27.3k • 104 -
Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents
Paper • 2310.19923 • Published • 14 -
nvidia/Nemotron-PII
Viewer • Updated • 200k • 1.95k • 49 -
HuggingFaceFW/fineweb
Viewer • Updated • 52.5B • 187k • 2.59k -
rl-research/dr-tulu-sft-data
Viewer • Updated • 13.1k • 492 • 25 -
HuggingFaceFW/fineweb-2
Viewer • Updated • 4.48B • 61.5k • 710 -
miromind-ai/MiroVerse-v0.1
Viewer • Updated • 228k • 714 • 101 -
nvidia/Llama-Nemotron-Post-Training-Dataset
Viewer • Updated • 3.91M • 5.36k • 637 -
wikimedia/wikipedia
Viewer • Updated • 61.6M • 72.2k • 1.1k -
HuggingFaceH4/MATH-500
Benchmark • Updated • 500 • 97.7k • 272 -
nick007x/github-code-2025
Viewer • Updated • 147M • 4.83k • 112 -
GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models
Paper • 2508.06471 • Published • 195 -
nvidia/ToolScale
Viewer • Updated • 4.06k • 1.66k • 166 -
natolambert/GeneralThought-430K-filtered
Viewer • Updated • 338k • 835 • 29 -
RJT1990/GeneralThoughtArchive
Viewer • Updated • 431k • 2.63k • 70 -
open-thoughts/OpenThoughts-114k
Viewer • Updated • 228k • 101k • 782 -
open-r1/OpenR1-Math-Raw
Viewer • Updated • 516k • 435 • 76 -
PrimeIntellect/SYNTHETIC-1
Viewer • Updated • 1.99M • 1.08k • 60 -
PrimeIntellect/synthetic-code-understanding
Viewer • Updated • 60.6k • 79 • 19 -
PrimeIntellect/INTELLECT-3-SFT
Viewer • Updated • 6.98M • 1.22k • 1 -
openbmb/InfLLM-V2-data-5B
Viewer • Updated • 7.19M • 336 • 30 -
kenhktsui/open-react-retrieval-multi-neg-result-new-kw
Viewer • Updated • 25.2k • 37 • 3 -
alwaysfurther/tiny-agent-with-tools
Viewer • Updated • 27 • 20 -
tiny-agents/tiny-agents
Viewer • Updated • 9 • 475 • 33 -
PleIAs/SYNTH
Viewer • Updated • 68M • 23.2k • 216 -
TuringEnterprises/Turing-Open-Reasoning
Viewer • Updated • 50 • 19.2k • 182 -
TeichAI/claude-4.5-opus-high-reasoning-250x
Viewer • Updated • 250 • 2.73k • 143 -
PrimeIntellect/INTELLECT-3-RL
Viewer • Updated • 70.7k • 22.6k • 5 -
PrimeIntellect/Reverse-Text-RL
Viewer • Updated • 1k • 2.99k • 2 -
PrimeIntellect/Reverse-Text-SFT
Viewer • Updated • 1k • 609 • 2 -
PrimeIntellect/SYNTHETIC-2-Base-Code
Viewer • Updated • 57.3k • 128 -
PrimeIntellect/SYNTHETIC-2-Base-Math
Viewer • Updated • 105k • 18 • 1 -
PrimeIntellect/SYNTHETIC-2-Base
Viewer • Updated • 465k • 45 • 9 -
PrimeIntellect/SYNTHETIC-2-Base-General-Reasoning
Viewer • Updated • 165k • 23 • 1 -
PrimeIntellect/SYNTHETIC-2-SFT-verified
Viewer • Updated • 105k • 257 • 6 -
PrimeIntellect/SYNTHETIC-2-Base-Answer-Critique
Viewer • Updated • 50k • 13 • 2 -
PrimeIntellect/SYNTHETIC-2-Base-Instruction-Following
Viewer • Updated • 87.5k • 31 -
PrimeIntellect/SYNTHETIC-2
Viewer • Updated • 51.6k • 352 • 10 -
PrimeIntellect/AIME-24
Viewer • Updated • 30 • 64 -
PrimeIntellect/AIME-25
Viewer • Updated • 30 • 112 -
PrimeIntellect/MATH-500
Viewer • Updated • 500 • 71 -
PrimeIntellect/LiveCodeBench-v5
Viewer • Updated • 279 • 171 -
arcee-ai/bfcl_v4_web_search
Viewer • Updated • 100 • 23 -
arcee-ai/EvolKit-75K
Viewer • Updated • 74.2k • 32 • 36 -
arcee-ai/general-dpo-datasets
Viewer • Updated • 91.6k • 252 -
arcee-ai/synthetic-data-gen
Viewer • Updated • 999k • 51 • 2 -
arcee-ai/DAM
Viewer • Updated • 10.4k • 97 -
arcee-ai/EvolKit-20k-vi
Viewer • Updated • 15.4k • 57 • 7 -
arcee-ai/reasoning-sharegpt
Viewer • Updated • 29.9k • 34 • 23 -
arcee-ai/agent-data
Viewer • Updated • 486k • 54 • 63 -
arcee-ai/infini-instruct-top-500k
Viewer • Updated • 500k • 32 • 6 -
arcee-ai/cleaned-mlabonne-distilabel-truthy-dpo-v0.1-filtered
Viewer • Updated • 663 • 20 -
Nanbeige/ToolMind
Updated • 2.27k • 61 -
Salesforce/APIGen-MT-5k
Viewer • Updated • 5k • 542 • 88 -
Team-ACE/ToolACE
Viewer • Updated • 11.3k • 1.02k • 158 -
glaiveai/glaive-function-calling-v2
Viewer • Updated • 113k • 2.26k • 480 -
nvidia/When2Call
Viewer • Updated • 28k • 410 • 42 -
Salesforce/xlam-function-calling-60k
Viewer • Updated • 60k • 3.49k • 561 -
HuggingFaceFW/fineweb-edu
Viewer • Updated • 3.5B • 309k • 895 -
Skywork-R1V4: Toward Agentic Multimodal Intelligence through Interleaved Thinking with Images and DeepResearch
Paper • 2512.02395 • Published • 47 -
MATRIX: Multimodal Agent Tuning for Robust Tool-Use Reasoning
Paper • 2510.08567 • Published -
Scaling Agentic Reinforcement Learning for Tool-Integrated Reasoning in VLMs
Paper • 2511.19773 • Published • 9 -
ToolScope: An Agentic Framework for Vision-Guided and Long-Horizon Tool Use
Paper • 2510.27363 • Published • 22 -
Ariadne: A Controllable Framework for Probing and Extending VLM Reasoning Boundaries
Paper • 2511.00710 • Published • 4 -
VLA-R1: Enhancing Reasoning in Vision-Language-Action Models
Paper • 2510.01623 • Published • 10 -
DeepEyesV2: Toward Agentic Multimodal Model
Paper • 2511.05271 • Published • 42 -
DeepMMSearch-R1: Empowering Multimodal LLMs in Multimodal Web Search
Paper • 2510.12801 • Published • 13 -
DeepAgent: A General Reasoning Agent with Scalable Toolsets
Paper • 2510.21618 • Published • 99 -
Open Multimodal Retrieval-Augmented Factual Image Generation
Paper • 2510.22521 • Published • 30 -
smolagents/android-control
Viewer • Updated • 15.3k • 1.86k • 12 -
smolagents/guiact-web-single
Viewer • Updated • 13.3k • 40 • 1 -
smolagents/tool-scraping
Viewer • Updated • 1.89k • 18 • 5 -
smolagents/hermes-function-calling-v1-formatted-code-agent
Viewer • Updated • 9k • 26 • 1 -
smolagents/aguvis-stage-1
Viewer • Updated • 459k • 4.17k • 16 -
smolagents/aguvis-stage-2
Viewer • Updated • 784k • 4.4k • 25 -
beyoru/ToolCalll_fusion
Viewer • Updated • 10.5k • 6 • 1 -
beyoru/ToolCall_synthetic_qwen3
Viewer • Updated • 60k • 22 • 9 -
qualifire/mcp-tool-use-quality-benchmark
Viewer • Updated • 5k • 16 • 3 -
mlx-community/hermes-reasoning-tool-use
Viewer • Updated • 51k • 75 • 4 -
TeichAI/gemini-3-pro-preview-high-reasoning-1000x
Viewer • Updated • 1.02k • 1.48k • 56 -
openbmb/Ultra-FineWeb
Viewer • Updated • 1.29B • 54.5k • 290 -
allenai/Dolci-Instruct-SFT-Tool-Use
Viewer • Updated • 228k • 889 • 10 -
nvidia/Nemotron-Content-Safety-Reasoning-Dataset
Preview • Updated • 67 • 4 -
ai-safety-institute/AgentHarm
Viewer • Updated • 468 • 6.9k • 45 -
Voxel51/ScreenSpot-v2
Viewer • Updated • 1.27k • 3.17k • 1 -
rootsautomation/ScreenSpot
Viewer • Updated • 1.27k • 1.87k • 43 -
microsoft/WebTailBench
Preview • Updated • 169 • 14 -
DeepShop/DeepShop
Viewer • Updated • 150 • 24 • 3 -
osunlp/Online-Mind2Web
Viewer • Updated • 300 • 909 • 19 -
zai-org/T1
Preview • Updated • 59 • 9 -
zai-org/LongBench-v2
Viewer • Updated • 503 • 26.1k • 28