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 • 3.63k • 96 -
nvidia/Nemotron-RL-instruction_following
Preview • Updated • 103 • 11 -
nvidia/Nemotron-RL-knowledge-web_search-mcqa
Viewer • Updated • 2.93k • 120 • 9 -
nvidia/Nemotron-RL-agent-workplace_assistant
Viewer • Updated • 1.8k • 188 • 15 -
nvidia/Nemotron-RL-instruction_following-structured_outputs
Viewer • Updated • 9.95k • 477 • 34 -
nvidia/Nemotron-RL-knowledge-mcqa
Viewer • Updated • 686k • 195 • 8 -
nvidia/Nemotron-RL-math-OpenMathReasoning
Viewer • Updated • 113k • 212 • 14 -
nvidia/Nemotron-RL-knowledge-openqa
Viewer • Updated • 136k • 74 • 8 -
nvidia/Nemotron-RL-math-advanced_calculations
Viewer • Updated • 6k • 59 • 9 -
nvidia/Nemotron-AIQ-Agentic-Safety-Dataset-1.0
Viewer • Updated • 10.8k • 1.24k • 14 -
nvidia/Nemotron-VLM-Dataset-v2
Viewer • Updated • 4.58M • 5.12k • 85 -
nvidia/ProfBench
Viewer • Updated • 40 • 578 • 20 -
google/code_x_glue_cc_code_completion_token
Viewer • Updated • 178k • 803 • 9 -
google/code_x_glue_cc_cloze_testing_all
Viewer • Updated • 176k • 141 • 6 -
google/code_x_glue_cc_clone_detection_big_clone_bench
Viewer • Updated • 1.73M • 687 • 20 -
google/code_x_glue_ct_code_to_text
Viewer • Updated • 1.01M • 2.2k • 79 -
google/code_x_glue_tc_nl_code_search_adv
Viewer • Updated • 281k • 250 • 11 -
TeichAI/claude-sonnet-4.5-high-reasoning-250x
Viewer • Updated • 247 • 442 • 34 -
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 • 9 -
Scientific Algorithm Discovery by Augmenting AlphaEvolve with Deep Research
Paper • 2510.06056 • Published • 6 -
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 • 18 -
Anthropic/hh-rlhf
Viewer • Updated • 169k • 17.5k • 1.66k -
open-thoughts/OpenThoughts3-1.2M
Viewer • Updated • 1.2M • 8.35k • 209 -
nex-agi/agent-sft
Preview • Updated • 259 • 105 -
Open-Bee/Honey-Data-15M
Viewer • Updated • 14.8M • 24.9k • 111 -
Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents
Paper • 2310.19923 • Published • 14 -
nvidia/Nemotron-PII
Viewer • Updated • 200k • 2.67k • 71 -
HuggingFaceFW/fineweb
Viewer • Updated • 52.5B • 163k • 2.68k -
rl-research/dr-tulu-sft-data
Viewer • Updated • 13.1k • 233 • 26 -
HuggingFaceFW/fineweb-2
Viewer • Updated • 4.48B • 73.4k • 760 -
miromind-ai/MiroVerse-v0.1
Viewer • Updated • 228k • 237 • 223 -
nvidia/Llama-Nemotron-Post-Training-Dataset
Viewer • Updated • 3.91M • 2.1k • 642 -
wikimedia/wikipedia
Viewer • Updated • 61.6M • 70.9k • 1.14k -
HuggingFaceH4/MATH-500
Viewer • Updated • 500 • 96k • 286 -
nick007x/github-code-2025
Viewer • Updated • 147M • 8.86k • 114 -
GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models
Paper • 2508.06471 • Published • 206 -
nvidia/ToolScale
Viewer • Updated • 4.06k • 392 • 188 -
natolambert/GeneralThought-430K-filtered
Viewer • Updated • 338k • 271 • 34 -
RJT1990/GeneralThoughtArchive
Viewer • Updated • 431k • 672 • 71 -
open-thoughts/OpenThoughts-114k
Viewer • Updated • 228k • 83.2k • 810 -
open-r1/OpenR1-Math-Raw
Viewer • Updated • 516k • 219 • 76 -
PrimeIntellect/SYNTHETIC-1
Viewer • Updated • 1.99M • 2.02k • 61 -
PrimeIntellect/synthetic-code-understanding
Viewer • Updated • 60.6k • 44 • 19 -
PrimeIntellect/INTELLECT-3-SFT
Viewer • Updated • 6.98M • 280 • 1 -
openbmb/InfLLM-V2-data-5B
Viewer • Updated • 7.19M • 322 • 32 -
kenhktsui/open-react-retrieval-multi-neg-result-new-kw
Viewer • Updated • 25.2k • 8 • 3 -
alwaysfurther/tiny-agent-with-tools
Viewer • Updated • 27 • 15 -
tiny-agents/tiny-agents
Viewer • Updated • 9 • 1.53k • 34 -
PleIAs/SYNTH
Viewer • Updated • 68M • 62.5k • 250 -
TuringEnterprises/Turing-Open-Reasoning
Viewer • Updated • 50 • 476 • 184 -
TeichAI/claude-4.5-opus-high-reasoning-250x
Viewer • Updated • 250 • 5.58k • 295 -
PrimeIntellect/INTELLECT-3-RL
Viewer • Updated • 70.7k • 9k • 6 -
PrimeIntellect/Reverse-Text-RL
Viewer • Updated • 1k • 6.75k • 2 -
PrimeIntellect/Reverse-Text-SFT
Viewer • Updated • 1k • 958 • 3 -
PrimeIntellect/SYNTHETIC-2-Base-Code
Viewer • Updated • 57.3k • 29 -
PrimeIntellect/SYNTHETIC-2-Base-Math
Viewer • Updated • 105k • 15 • 1 -
PrimeIntellect/SYNTHETIC-2-Base
Viewer • Updated • 465k • 17 • 9 -
PrimeIntellect/SYNTHETIC-2-Base-General-Reasoning
Viewer • Updated • 165k • 17 • 1 -
PrimeIntellect/SYNTHETIC-2-SFT-verified
Viewer • Updated • 105k • 581 • 8 -
PrimeIntellect/SYNTHETIC-2-Base-Answer-Critique
Viewer • Updated • 50k • 9 • 2 -
PrimeIntellect/SYNTHETIC-2-Base-Instruction-Following
Viewer • Updated • 87.5k • 11 -
PrimeIntellect/SYNTHETIC-2
Viewer • Updated • 51.6k • 1.16k • 13 -
PrimeIntellect/AIME-24
Viewer • Updated • 30 • 562 -
PrimeIntellect/AIME-25
Viewer • Updated • 30 • 655 -
PrimeIntellect/MATH-500
Viewer • Updated • 500 • 506 -
PrimeIntellect/LiveCodeBench-v5
Viewer • Updated • 279 • 143 -
arcee-ai/bfcl_v4_web_search
Viewer • Updated • 100 • 283 • 2 -
arcee-ai/EvolKit-75K
Viewer • Updated • 74.2k • 28 • 37 -
arcee-ai/general-dpo-datasets
Viewer • Updated • 91.6k • 454 -
arcee-ai/synthetic-data-gen
Viewer • Updated • 999k • 9 • 2 -
arcee-ai/DAM
Viewer • Updated • 10.4k • 39 -
arcee-ai/EvolKit-20k-vi
Viewer • Updated • 15.4k • 11 • 7 -
arcee-ai/reasoning-sharegpt
Viewer • Updated • 29.9k • 31 • 23 -
arcee-ai/agent-data
Viewer • Updated • 486k • 90 • 63 -
arcee-ai/infini-instruct-top-500k
Viewer • Updated • 500k • 35 • 6 -
arcee-ai/cleaned-mlabonne-distilabel-truthy-dpo-v0.1-filtered
Viewer • Updated • 663 • 6 -
Nanbeige/ToolMind
Updated • 1.76k • 133 -
Salesforce/APIGen-MT-5k
Viewer • Updated • 5k • 383 • 90 -
Team-ACE/ToolACE
Viewer • Updated • 11.3k • 876 • 166 -
glaiveai/glaive-function-calling-v2
Viewer • Updated • 113k • 5.48k • 489 -
nvidia/When2Call
Viewer • Updated • 28k • 490 • 44 -
Salesforce/xlam-function-calling-60k
Viewer • Updated • 60k • 5.76k • 575 -
HuggingFaceFW/fineweb-edu
Viewer • Updated • 3.5B • 224k • 964 -
Skywork-R1V4: Toward Agentic Multimodal Intelligence through Interleaved Thinking with Images and DeepResearch
Paper • 2512.02395 • Published • 49 -
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 • 10 -
ToolScope: An Agentic Framework for Vision-Guided and Long-Horizon Tool Use
Paper • 2510.27363 • Published • 23 -
Ariadne: A Controllable Framework for Probing and Extending VLM Reasoning Boundaries
Paper • 2511.00710 • Published • 5 -
VLA-R1: Enhancing Reasoning in Vision-Language-Action Models
Paper • 2510.01623 • Published • 12 -
DeepEyesV2: Toward Agentic Multimodal Model
Paper • 2511.05271 • Published • 45 -
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 • 101 -
Open Multimodal Retrieval-Augmented Factual Image Generation
Paper • 2510.22521 • Published • 31 -
smolagents/android-control
Viewer • Updated • 15.3k • 887 • 13 -
smolagents/guiact-web-single
Viewer • Updated • 13.3k • 45 • 1 -
smolagents/tool-scraping
Viewer • Updated • 1.89k • 21 • 5 -
smolagents/hermes-function-calling-v1-formatted-code-agent
Viewer • Updated • 9k • 25 • 1 -
smolagents/aguvis-stage-1
Viewer • Updated • 459k • 6.67k • 16 -
smolagents/aguvis-stage-2
Viewer • Updated • 784k • 3.92k • 26 -
beyoru/ToolCalll_fusion
Viewer • Updated • 10.5k • 6 • 1 -
beyoru/ToolCall_synthetic_qwen3
Viewer • Updated • 60k • 23 • 10 -
qualifire/mcp-tool-use-quality-benchmark
Viewer • Updated • 5k • 11 • 3 -
mlx-community/hermes-reasoning-tool-use
Viewer • Updated • 51k • 48 • 4 -
TeichAI/gemini-3-pro-preview-high-reasoning-1000x
Viewer • Updated • 1.02k • 707 • 72 -
openbmb/Ultra-FineWeb
Viewer • Updated • 1.29B • 53.5k • 328 -
allenai/Dolci-Instruct-SFT-Tool-Use
Viewer • Updated • 228k • 456 • 12 -
nvidia/Nemotron-Content-Safety-Reasoning-Dataset
Preview • Updated • 182 • 7 -
ai-safety-institute/AgentHarm
Viewer • Updated • 468 • 4.95k • 46 -
Voxel51/ScreenSpot-v2
Viewer • Updated • 1.27k • 2.5k • 1 -
rootsautomation/ScreenSpot
Viewer • Updated • 1.27k • 1.06k • 44 -
microsoft/WebTailBench
Preview • Updated • 144 • 16 -
DeepShop/DeepShop
Viewer • Updated • 150 • 16 • 3 -
osunlp/Online-Mind2Web
Viewer • Updated • 300 • 289 • 23 -
zai-org/T1
Preview • Updated • 96 • 10 -
zai-org/LongBench-v2
Viewer • Updated • 503 • 27.9k • 33