Libra
NetX Lab
NetX Lab
When LLM Agents Meet Reinforcement Learning
Awesome List for Agentic RL
This page lists names, links and short descriptions. The original list on GitHub is the source and belongs to its authors.
Base Framework
Molt
NVIDIA (NeMo Labs)
In 2 lists
Orchard
Microsoft
AgentJet
ModelScope (Alibaba)
HarnessX
Darwin-Agent
Dressage
Accio-Lab
AReno
Ant Group (inclusionAI)
Polar
NVIDIA (NeMo)
uni-agent
verl-project
VeRL-Omni
verl-project
OpenClaw-RL
Gen-Verse
Claw-R1
USTC
Open-AgentRL
Gen-Verse
NeMo-RL
NVIDIA
In 3 lists
RLinf
Tsinghua/Infinigence AI/PKU
In 3 lists
siiRL
Shanghai Innovation Institute
agent-lightning
Microsoft Research
In 3 lists
AReaL
AntGroup/Tsinghua
In 2 lists
ROLL
Alibaba
In 2 lists
MARTI
Tsinghua
Tunix
RL2
Accio
In 2 lists
verifiers
Individual
prime-rl
Prime Intellect
In 3 lists
oat
NUS/Sea AI
veRL
ByteDance
In 3 lists
Click to view technical details
Libra
NetX Lab
Orchard
Microsoft
AReno
Ant Group (inclusionAI)
Molt
NVIDIA (NeMo Labs)
In 2 lists
AgentJet
ModelScope (Alibaba)
HarnessX
Darwin-Agent
Dressage
Accio-Lab
Polar
NVIDIA (NeMo)
uni-agent
verl-project
VeRL-Omni
verl-project
OpenClaw-RL
Gen-Verse
Claw-R1
USTC
Open-AgentRL
Gen-Verse
NeMo-RL
NVIDIA
In 3 lists
RLinf
Tsinghua/Infinigence AI/PKU
In 3 lists
siiRL
Shanghai Innovation Institute
agent-lightning
Microsoft Research
In 3 lists
AReaL
AntGroup/Tsinghua
In 2 lists
ROLL
Alibaba
In 2 lists
MARTI
Tsinghua
Tunix
RL2
Accio
In 2 lists
verifiers
Individual
prime-rl
Prime Intellect
In 3 lists
oat
NUS/Sea AI
veRL
ByteDance
In 3 lists
General/MultiTask
T2PO
Academic (ICML 2026 Spotlight)
StraTA
Shanghai AI Lab / Oxford / Multi-institution
SDAR
Zhejiang University (ZJU-REAL)
SkillZero
Zhejiang University (ZJU-REAL)
MetaClaw
UNC-Chapel Hill (AIMING Lab)
In 2 lists
SkillRL
UNC-Chapel Hill (AIMING Lab)
LLM-in-Sandbox
RUC/MSRA/THU
youtu-agent
Tencent Youtu Lab
In 4 listsDetails
DEPO
HKUST/SJTU
SPEAR
Tencent Youtu Lab
DeepAgent
RUC/Xiaohongshu
AgentRL
Tsinghua
AgentGym-RL
Fudan University
Agent_Foundation_Models
OPPO Personal AI Lab
Trinity-RFT
Alibaba
SPA-RL-Agent
PolyU
verl-agent
NTU/Skywork
SkyRL
UC Berkeley / NovaSky-AI
In 2 lists
VAGEN
Northwestern University (mll-lab-nu)
ART
OpenPipe
In 3 lists
OpenManus-RL
UIUC/MetaGPT
In 2 lists
Click to view technical details
T2PO
Academic (ICML 2026 Spotlight)
StraTA
Shanghai AI Lab / Oxford / Multi-institution
SDAR
Zhejiang University (ZJU-REAL)
SkillZero
Zhejiang University (ZJU-REAL)
MetaClaw
UNC-Chapel Hill (AIMING Lab)
In 2 lists
SkillRL
UNC-Chapel Hill (AIMING Lab)
LLM-in-Sandbox
RUC/MSRA/THU
youtu-agent
Tencent Youtu Lab
In 4 listsDetails
DEPO
HKUST/SJTU
SPEAR
Tencent Youtu Lab
DeepAgent
RUC/Xiaohongshu
AgentRL
Tsinghua
AgentGym-RL
Fudan University
Agent_Foundation_Models
OPPO Personal AI Lab
Trinity-RFT
Alibaba
SPA-RL-Agent
PolyU
verl-agent
NTU/Skywork
SkyRL
UC Berkeley / NovaSky-AI
In 2 lists
VAGEN
Northwestern University (mll-lab-nu)
ART
OpenPipe
In 3 lists
OpenManus-RL
UIUC/MetaGPT
In 2 lists
Search & RAG Agent
EviSD
Academic
GTA-RAG
Academic (EMNLP'26 Findings)
LAPO
Academic
Harness-1
UIUC
SlimSearcher
Ant Group / ZJU
DeepRubric
Shandong University
SAAS
Xiamen University
CuSearch
Academic
GrepSeek
UMass Amherst (CIIR)
PyRAG
Academic
ORBIT
University of Waterloo
LiteResearcher
Simplex AI / ZJU / PolyU
DR-Venus
Ant Group (inclusionAI)
MR-Search
Academic
ProRAG
RUC
O-Researcher
OPPO PersonalAI Lab
In 2 lists
MemSearcher
CAS
DR Tulu
AI2 / UW / CMU / MIT
IGPO
Ant Group
ReSeek
Tencent PCG BAC/Tsinghua University
AutoGraph-R1
HKUST KnowComp
WebSeer
Individual
HiPRAG
Individual
Tree-GRPO
AMAP
DeepResearch
Alibaba/Tongyi Lab
In 2 lists
DeepDive
Tsinghua/THUDM
ASearcher
Ant Research RL Lab Tsinghua University & UW
SSRL
Tsinghua
Research-Venus
Ant Group
Graph-R1
BUPT/NTU/NUS
Kimi-Researcher
Moonshot AI
R-Search
Individual
StepSearch
SenseTime
AutoRefine
USTC
ZeroSearch
Alibaba
ReasonRAG
CityU HK / Huawei
VRAG
USTC / Tongyi Lab, Alibaba
MaskSearch
Tongyi Lab, Alibaba
R3-RAG
Fudan NLP
O2-Searcher
KnowledgeXLab
s3
UIUC
knowledge-r1
CAS / UCAS
WebThinker
RUC
DeepResearcher
SJTU
Search-R1
UIUC/Google
In 2 lists
R1-Searcher
RUC
C-3PO
Alibaba
DeepRetrieval
UIUC
Click to view technical details
PyRAG
Academic
GrepSeek
UMass Amherst (CIIR)
LAPO
Academic
GTA-RAG
Academic (EMNLP'26 Findings)
EviSD
Academic
Harness-1
UIUC
SlimSearcher
Ant Group / ZJU
DeepRubric
Shandong University
SAAS
Xiamen University
CuSearch
Academic
ORBIT
University of Waterloo
LiteResearcher
Simplex AI / ZJU / PolyU
DR-Venus
Ant Group (inclusionAI)
MR-Search
Academic
ProRAG
RUC
O-Researcher
OPPO PersonalAI Lab
In 2 lists
MemSearcher
CAS
DR Tulu
AI2 / UW / CMU / MIT
IGPO
Ant Group
ReSeek
Tencent PCG BAC/Tsinghua University
AutoGraph-R1
HKUST KnowComp
WebSeer
Individual
HiPRAG
Individual
Tree-GRPO
AMAP
DeepResearch
Alibaba/Tongyi Lab
In 2 lists
DeepDive
Tsinghua/THUDM
ASearcher
Ant Research RL Lab Tsinghua University & UW
SSRL
Tsinghua
Research-Venus
Ant Group
Graph-R1
BUPT/NTU/NUS
Kimi-Researcher
Moonshot AI
R-Search
Individual
StepSearch
SenseTime
AutoRefine
USTC
ZeroSearch
Alibaba
ReasonRAG
CityU HK / Huawei
VRAG
USTC / Tongyi Lab, Alibaba
MaskSearch
Tongyi Lab, Alibaba
R3-RAG
Fudan NLP
O2-Searcher
KnowledgeXLab
s3
UIUC
knowledge-r1
CAS / UCAS
WebThinker
RUC
DeepResearcher
SJTU
Search-R1
UIUC/Google
In 2 lists
R1-Searcher
RUC
C-3PO
Alibaba
DeepRetrieval
UIUC
Web & GUI Agent
SCALE-CUA
Tsinghua (THUDM)
OpenWebRL
UIUC / Microsoft Research
ToolCUA
Alibaba Tongyi Lab (X-PLUG)
ClawGUI
Zhejiang University (ZJU-REAL)
In 2 lists
OpAgent
Codefuse AI (Ant Group)
GUI-Libra
GUI-Libra (MS-affiliated)
MobileAgent
X-PLUG (TongyiQwen)
In 4 listsDetails
UI-TARS
ByteDance Seed
In 3 lists
MobileRL
Tsinghua / Zhipu AI (THUDM)
DART-GUI
Computer-use-agents
Mano-P
Mininglamp AI
InfiGUI-G1
InfiX AI
gui-rcpo
Zhejiang University
UI-AGILE
Xiamen University
GUI-G2
Zhejiang University (ZJU-REAL)
MagicGUI
Honor (MagicAgent-GUI)
Grounding-R1
Salesforce
AgentCPM-GUI
OpenBMB/Tsinghua/RUC
TTI
CMU
GTA1
Salesforce / ANU
SE-GUI
Nankai University/vivo
ARPO
CUHK/HKUST
GUI-G1
RUC
WebAgent-R1
Amazon/UVA
ZeroGUI
Shanghai AI Lab
GUI-R1
CAS/NUS
InfiGUI-R1
Zhejiang University
UI-R1
vivo/CUHK
CollabUIAgents
Tsinghua/Alibaba/HKUST
DigiQ
UC Berkeley/CMU/Amazon
GUI-Agent-RL
Microsoft
WebAgent
Alibaba
In 2 lists
Click to view technical details
SCALE-CUA
Tsinghua (THUDM)
OpenWebRL
UIUC / Microsoft Research
ToolCUA
Alibaba Tongyi Lab (X-PLUG)
ClawGUI
Zhejiang University (ZJU-REAL)
In 2 lists
OpAgent
Codefuse AI (Ant Group)
GUI-Libra
GUI-Libra (MS-affiliated)
MobileAgent
X-PLUG (TongyiQwen)
In 4 listsDetails
UI-TARS
ByteDance Seed
In 3 lists
MobileRL
Tsinghua / Zhipu AI (THUDM)
DART-GUI
Computer-use-agents
Mano-P
Mininglamp AI
InfiGUI-G1
InfiX AI
gui-rcpo
Zhejiang University
UI-AGILE
Xiamen University
GUI-G2
Zhejiang University (ZJU-REAL)
MagicGUI
Honor (MagicAgent-GUI)
Grounding-R1
Salesforce
AgentCPM-GUI
OpenBMB/Tsinghua/RUC
TTI
CMU
GTA1
Salesforce / ANU
SE-GUI
Nankai University/vivo
ARPO
CUHK/HKUST
GUI-G1
RUC
WebAgent-R1
Amazon/UVA
ZeroGUI
Shanghai AI Lab
GUI-R1
CAS/NUS
InfiGUI-R1
Zhejiang University
UI-R1
vivo/CUHK
CollabUIAgents
Tsinghua/Alibaba/HKUST
DigiQ
UC Berkeley/CMU/Amazon
GUI-Agent-RL
Microsoft
WebAgent
Alibaba
In 2 lists
Tool-Use Agent
Tool-RL-Box
Harbin Institute of Technology
SPADER
Zhejiang University
APPO
Alibaba AMAP (AMAP-ML)
AgenticQwen
Alibaba PAI
Agent-STAR
CUHK
ToolOrchestra
NVIDIA / HKU
ToolMaster
Northeastern University (NEUIR)
MATPO
MiroMind AI
AWorld-RL
Ant Group (inclusionAI)
CodeGym
Academic
UserRL
Salesforce AI Research
ToolBrain
ToolBrain (AAMAS 2026)
Tool-R1
Individual (YBYBZhang)
MiroRL
MiroMindAI
MUA-RL
Alibaba (Tongyi)
verl-tool
TIGER-Lab
Multi-Turn-RL-Agent
University of Minnesota
Tool-N1
NVIDIA
Tool-Star
RUC
RL-Factory
Simple-Efficient
In 2 lists
calculator_agent_rl
Individual (Danau5tin)
ReTool
ByteDance
ToolRL
UIUC
AWorld
Ant Group (inclusionAI)
In 2 lists
Agent-R1
USTC
In 2 lists
ReCall
BaiChuan
Click to view technical details
Tool-RL-Box
Harbin Institute of Technology
SPADER
Zhejiang University
APPO
Alibaba AMAP (AMAP-ML)
AgenticQwen
Alibaba PAI
Agent-STAR
CUHK
ToolOrchestra
NVIDIA / HKU
ToolMaster
Northeastern University (NEUIR)
MATPO
MiroMind AI
AWorld-RL
Ant Group (inclusionAI)
CodeGym
Academic
UserRL
Salesforce AI Research
ToolBrain
ToolBrain (AAMAS 2026)
Tool-R1
Individual (YBYBZhang)
MiroRL
MiroMindAI
verl-tool
TIGER-Lab
Multi-Turn-RL-Agent
University of Minnesota
Tool-N1
NVIDIA
Tool-Star
RUC
RL-Factory
Simple-Efficient
In 2 lists
calculator_agent_rl
Individual (Danau5tin)
ReTool
ByteDance
ToolRL
UIUC
AWorld
Ant Group (inclusionAI)
In 2 lists
Agent-R1
USTC
In 2 lists
ReCall
BaiChuan
Code & SWE Agent
Lego-RL
LegoX
FastContext
Microsoft
SWE-Edit
Microsoft Research
CodeScout
OpenHands
CUDA-Agent
ByteDance/Tsinghua
SWE-World
RUC (RUCAIBox)
LLM-in-Sandbox
RUC/MSRA/THU
CUDA-L2
DeepReinforce AI
PPP-Agent
CMU/OpenHands
DeepAnalyze
RUC/Tsinghua
In 8 listsDetails
RepoDeepSearch
PKU, Bytedance, BIT
CUDA-L1
DeepReinforce AI
SWE-Swiss
Tsinghua / ByteDance
MedAgentGym
Emory/Georgia Tech
In 2 lists
CURE
University of Chicago Princeton/ByteDance
Time-R1
UIUC
ML-Agent
MASWorks
In 2 lists
digitalhuman
Tencent
Skywork-OR1
Skywork AI
In 2 lists
sweet_rl
Meta/UCB
swe-rl
Meta/UIUC/CMU
In 2 lists
CTRL
HKU/ByteDance
AceCoder
Waterloo (TIGER-Lab)
rllm
Berkeley Sky Computing Lab BAIR / Together AI
open-r1
HuggingFace
In 3 lists
Click to view technical details
Lego-RL
LegoX
FastContext
Microsoft
SWE-Edit
Microsoft Research
CodeScout
OpenHands
CUDA-Agent
ByteDance/Tsinghua
SWE-World
RUC (RUCAIBox)
LLM-in-Sandbox
RUC/MSRA/THU
CUDA-L2
DeepReinforce AI
PPP-Agent
CMU/OpenHands
DeepAnalyze
RUC/Tsinghua
In 8 listsDetails
RepoDeepSearch
PKU, Bytedance, BIT
CUDA-L1
DeepReinforce AI
SWE-Swiss
Tsinghua / ByteDance
MedAgentGym
Emory/Georgia Tech
In 2 lists
CURE
University of Chicago Princeton/ByteDance
Time-R1
UIUC
ML-Agent
MASWorks
In 2 lists
digitalhuman
Tencent
Skywork-OR1
Skywork AI
In 2 lists
sweet_rl
Meta/UCB
swe-rl
Meta/UIUC/CMU
In 2 lists
CTRL
HKU/ByteDance
AceCoder
Waterloo (TIGER-Lab)
rllm
Berkeley Sky Computing Lab BAIR / Together AI
open-r1
HuggingFace
In 3 lists
Reasoning Agent
Agent0
UNC‑Chapel Hill / Salesforce Research / Stanford University
KG-R1
UIUC/Google
AgentFlow
Stanford University
In 2 lists
THOR
USTC / iFLYTEK
Tool-Light
RUC (RUC-NLPIR)
ARPO
RUC, Kuaishou
terminal-bench-rl
Individual (Danau5tin)
AutoTIR
Beihang University / BAAI
MOTIF
University of Maryland
cmriat/l0
CMRIAT
agent-distillation
KAIST
EasyR1
Individual
In 3 lists
AutoCoA
BJTU
ToRL
SJTU
ReMA
SJTU, UCL
Agentic-Reasoning
Oxford
SimpleTIR
NTU, Bytedance
openrlhf_async_pipline
OpenRLHF
Click to view technical details
Agent0
UNC‑Chapel Hill / Salesforce Research / Stanford University
KG-R1
UIUC/Google
AgentFlow
Stanford University
In 2 lists
THOR
USTC / iFLYTEK
Tool-Light
RUC (RUC-NLPIR)
ARPO
RUC, Kuaishou
terminal-bench-rl
Individual (Danau5tin)
AutoTIR
Beihang University / BAAI
MOTIF
University of Maryland
cmriat/l0
CMRIAT
agent-distillation
KAIST
EasyR1
Individual
In 3 lists
AutoCoA
BJTU
ToRL
SJTU
ReMA
SJTU, UCL
Agentic-Reasoning
Oxford
SimpleTIR
NTU, Bytedance
openrlhf_async_pipline
OpenRLHF
Multi-Agent RL
Maestro
Tsinghua / Multi-institution
DrMAS
NTU
MarsRL
Academic
PettingLLMs
Intel / UCSD
MASPRM
UBC / Huawei
MrlX
Ant Group (AQ-MedAI)
CoMAS
Shanghai AI Lab / CUHK / Oxford / NUS
MAPoRL
Academic
CoMLRL
OpenMLRL
ARIA
Fudan University
SPIRAL
NUS / A*STAR / Sea AI Lab
AMPO
Tongyi Lab, Alibaba
FlowReasoner
Sea AI Lab / NUS
MARFT
SII / SJTU
Click to view technical details
Maestro
Tsinghua / Multi-institution
DrMAS
NTU
MarsRL
Academic
PettingLLMs
Intel / UCSD
MASPRM
UBC / Huawei
MrlX
Ant Group (AQ-MedAI)
CoMAS
Shanghai AI Lab / CUHK / Oxford / NUS
MAPoRL
Academic
CoMLRL
OpenMLRL
ARIA
Fudan University
SPIRAL
NUS / A*STAR / Sea AI Lab
AMPO
Tongyi Lab, Alibaba
FlowReasoner
Sea AI Lab / NUS
MARFT
SII / SJTU
Memory
Click to view technical details
Embodied
REAL
InternRobotics
Embodied-R1.5
Tianjin University
AVA-VLA
UCAS
WorldVLN
Tsinghua (EmbodiedCity)
Embodied-R1
Tianjing University
VIKI-R
MARS-EAI (NeurIPS 2025 D&B)
STeCa
The Hong Kong Polytechnic University
Click to view technical details
REAL
InternRobotics
Embodied-R1.5
Tianjin University
AVA-VLA
UCAS
WorldVLN
Tsinghua (EmbodiedCity)
Embodied-R1
Tianjing University
VIKI-R
MARS-EAI (NeurIPS 2025 D&B)
STeCa
The Hong Kong Polytechnic University
Domain-Specific
FaithMed
CMU
Gene-Disease-Curation
Academic
MedSAM-Agent
CUHK/Tencent
ChemCraft
Peking University / IDEA
Doctor-R1
Tsinghua (thu-unicorn)
Alpha-R1
SJTU / FinStep.AI / StepFun
OS-R1
ISCAS
MMedAgent-RL
Unknown
MedResearcher-R1
Ant Group (AQ-MedAI)
LegalDelta
Northeastern University (NEUIR)
DoctorAgent-RL
UCAS/CAS/USTC
Biomni
Stanford University (SNAP)
In 2 lists
Click to view technical details
FaithMed
CMU
Gene-Disease-Curation
Academic
MedSAM-Agent
CUHK/Tencent
ChemCraft
Peking University / IDEA
Doctor-R1
Tsinghua (thu-unicorn)
Alpha-R1
SJTU / FinStep.AI / StepFun
OS-R1
ISCAS
MMedAgent-RL
Unknown
MedResearcher-R1
Ant Group (AQ-MedAI)
LegalDelta
Northeastern University (NEUIR)
DoctorAgent-RL
UCAS/CAS/USTC
Biomni
Stanford University (SNAP)
In 2 lists
Reward & Training Methodology
DRACO
CMU / IBM Research
Agent-G²
Zhejiang University / Baidu (EMNLP'26)
AgentV-RL
Academic
DataMind
Zhejiang University (ZJUNLP)
ARLArena
UCLA
Agent-RRM
Academic
ToolPRMBench
Arizona State University
RLVR-World
THU ML Group
AgentProg
MobileLLM
AgentPRM
Cornell
Agentic-Reward-Modeling
THU-KEG
AgentRM
THUNLP/Tsinghua
Click to view technical details
DRACO
CMU / IBM Research
Agent-G²
Zhejiang University / Baidu (EMNLP'26)
AgentV-RL
Academic
DataMind
Zhejiang University (ZJUNLP)
ARLArena
UCLA
Agent-RRM
Academic
ToolPRMBench
Arizona State University
RLVR-World
THU ML Group
AgentProg
MobileLLM
AgentPRM
Cornell
Agentic-Reward-Modeling
THU-KEG
AgentRM
THUNLP/Tsinghua
Safety
ToolSafe
Academic (MurrayTom)
TROJail
Academic (ACL 2026)
SafeSearch
Amazon Science
Jailbreak-R1
Academic (yuki-younai)
GuardReasoner-VL
NUS (yueliu1999)
xJailbreak
Academic
Auto-RT
ICIP-CAS
RLbreaker
Purdue
Click to view technical details
ToolSafe
Academic (MurrayTom)
TROJail
Academic (ACL 2026)
SafeSearch
Amazon Science
Jailbreak-R1
Academic (yuki-younai)
GuardReasoner-VL
NUS (yueliu1999)
xJailbreak
Academic
Auto-RT
ICIP-CAS
RLbreaker
Purdue
VLM Agent
InSight-doc
Academic (EMNLP'26)
VTS
UNC Chapel Hill / Sony
VSeek
UT Austin (SwarmLab)
HyperEyes
DeepExperience
ODE
HKUST / CUHK / PKU
ParaVT
NTU / HKU / Tsinghua / MiroMind (LMMs-Lab)
OpenSearch-VL
CUHK / NTU / HKU / Multi-institution
MTA-Agent
Salesforce AI Research
Gen-Searcher
Academic
MM-DeepResearch
Academic
PyVision-RL
agents-x-project
Vision-DeepResearch
Academic (ICML 2026)
ARM-Thinker
Shanghai AI Lab / InternLM
CodeDance
ByteDance
DeepEyesV2
Xiaohongshu
Mini-o3
Mini-o3 team
VisionThink
CUHK (dvlab-research)
multimodal-search-r1
ByteDance/NTU
AutoVLA
UCLA Mobility Lab
VDeepEyes
Xiaohongshu/XJTU
CoSo
NTU/Alibaba
Pixel-Reasoner
University of Waterloo (TIGER-AI-Lab)
Visual-ARFT
Shanghai AI Lab / SJTU
In 2 lists
VTool-R1
UIUC
OpenThinkIMG
Academic (zhaochen0110)
Chain-of-Focus
Multi-institution
GRIT
UC Santa Cruz (eric-ai-lab)
AlphaDrive
HUST/Horizon Robotics
VSC-RL
Liverpool/Huawei/Tianjin/UCL
RL4VLM
UC Berkeley
Click to view technical details
InSight-doc
Academic (EMNLP'26)
VTS
UNC Chapel Hill / Sony
VSeek
UT Austin (SwarmLab)
HyperEyes
DeepExperience
ODE
HKUST / CUHK / PKU
ParaVT
NTU / HKU / Tsinghua / MiroMind (LMMs-Lab)
OpenSearch-VL
CUHK / NTU / HKU / Multi-institution
MTA-Agent
Salesforce AI Research
Gen-Searcher
Academic
MM-DeepResearch
Academic
PyVision-RL
agents-x-project
Vision-DeepResearch
Academic (ICML 2026)
ARM-Thinker
Shanghai AI Lab / InternLM
CodeDance
ByteDance
DeepEyesV2
Xiaohongshu
Mini-o3
Mini-o3 team
VisionThink
CUHK (dvlab-research)
multimodal-search-r1
ByteDance/NTU
AutoVLA
UCLA Mobility Lab
VDeepEyes
Xiaohongshu/XJTU
CoSo
NTU/Alibaba
Pixel-Reasoner
University of Waterloo (TIGER-AI-Lab)
Visual-ARFT
Shanghai AI Lab / SJTU
In 2 lists
VTool-R1
UIUC
OpenThinkIMG
Academic (zhaochen0110)
Chain-of-Focus
Multi-institution
GRIT
UC Santa Cruz (eric-ai-lab)
AlphaDrive
HUST/Horizon Robotics
VSC-RL
Liverpool/Huawei/Tianjin/UCL
RL4VLM
UC Berkeley
Self-Evolution
AgentOPSD
Academic
BaT
NVIDIA (MONAI)
SEED
Academic (jinyangwu)
OPID
Academic (jinyangwu)
UCOB
Academic (TU2021)
SIRI
Academic
world-knowledge
HKUST / Tencent
ARISE
George Washington University
Tool-R0
UIUC / ETH Zurich
MemSkill
NTU/UIUC/UIC/Tsinghua
MemRL
SJTU/Xidian/NUS/USTC/MemTensor
AgentEvolver
Alibaba/Tongyi Lab
EvolveR
KnowledgeXLab / Shanghai AI Lab
SEAgent
Shanghai AI Lab / CUHK
R-Zero
Tencent AI Seattle Lab / WashU / UMD
Absolute-Zero-Reasoner
Tsinghua (LeapLabTHU) / BIGAI / PSU
RAGEN
RAGEN-AI
In 2 lists
WebRL
Tsinghua/Zhipu AI
Click to view technical details
BaT
NVIDIA (MONAI)
AgentOPSD
Academic
SEED
Academic (jinyangwu)
OPID
Academic (jinyangwu)
UCOB
Academic (TU2021)
SIRI
Academic
world-knowledge
HKUST / Tencent
ARISE
George Washington University
Tool-R0
UIUC / ETH Zurich
MemSkill
NTU/UIUC/UIC/Tsinghua
MemRL
SJTU/Xidian/NUS/USTC/MemTensor
AgentEvolver
Alibaba/Tongyi Lab
EvolveR
KnowledgeXLab / Shanghai AI Lab
SEAgent
Shanghai AI Lab / CUHK
R-Zero
Tencent AI Seattle Lab / WashU / UMD
Absolute-Zero-Reasoner
Tsinghua (LeapLabTHU) / BIGAI / PSU
RAGEN
RAGEN-AI
In 2 lists
WebRL
Tsinghua/Zhipu AI
Environment
PAST-Bench
Gen-Verse (NUS/Stanford/Oxford/Princeton)
DigiWorld
Meta (FAIR)
Evo-Bench
Renmin University (RUCAIBox)
ScrambleToolBench
NTU DeCLaRe Lab / A*STAR
SETA
CAMEL-AI.org
OpenAgent
Nanjing University (LAMDA-NeSy)
Echoverse
Microsoft Research
DocOps
Chinese Academy of Sciences (ICT)
PatientAgentBench
Amazon Science
LegalWorld
SII / Fudan DISC
MobileGym
Academic
AEnvironment
Ant Group (inclusionAI)
Gym-Anything
CMU L3 Lab
ClawBench
TIGER-AI Lab / NAIL Group
In 2 lists
OpenSandbox
Alibaba
In 2 lists
OpenEnv
Meta (PyTorch)
In 2 lists
open-trajectory-gym
Individual
Agent-World-Model
Snowflake AI Research
TermiGen
UCSB
VisGym
UC Berkeley
NeMo-Gym
NVIDIA
In 2 lists
VISTA-Gym
Texas A&M / Emory / KAUST
LoCoBench-Agent
Salesforce AI Research
Simia-Agent-Training
Microsoft
PaperArena
University of Science and Technology of China
enterprise-deep-research
Salesforce AI Research
In 2 lists
meta-agents-research-environments
Meta (FAIR)
BrowseComp-Plus
University of Waterloo
MCP-Bench
Accenture
MCPVerse
Individual
CompassVerifier
Shanghai AI Lab
tau2-bench
Sierra Research
Mind2Web-2
Ohio State University
MCP-Universe
Salesforce AI Research
gem
Sea AI Lab
MLE-Dojo
GIT, Stanford
R2E-Gym
UC Berkeley/ANU
SWE-smith
Princeton/Stanford/SWE-bench
atropos
Nous Research
InternBootcamp
InternBootcamp
loong
CAMEL-AI.org
DataSciBench
Tsinghua
reasoning-gym
open-thought
llmgym
tensorzero
SWE-Gym
UC Berkeley/UIUC/CMU/Apple
debug-gym
Microsoft Research
gym-llm
Rodrigo Sánchez Molina
AgentGym
Fudan
tau-bench
Sierra
In 2 lists
appworld
Stony Brook University
In 2 lists
android_world
Google Research
TheAgentCompany
CMU, Duke
In 2 lists
LlamaGym
Rohan Pandey
In 2 lists
In 2 lists
LMRL-Gym
UC Berkeley
OSWorld
HKU, CMU, Salesforce, Waterloo
In 3 lists
webarena
CMU
In 2 lists
AgentBench
Tsinghua University
In 7 listsDetails
WebShop
Princeton-NLP
ScienceWorld
AllenAI
factorio-learning-environment
JackHopkins
alfworld
Microsoft, CMU, UW
jericho
Microsoft, GIT
TextWorld
Microsoft Research
In 2 lists
Under Review/Waiting for Open Source
Qwen-UI-Agent: Towards Next-Generation Real-World Centric Foundation GUI Agent
(Tongyi-MAI — repo released, but no RL training code)
Qwen-CUA
(xlang-ai — technical report + demo only, weights hosted separately)
UI-Mate
(Tencent — inference/eval code only)
SearchMaster
(training code marked "planned for release")
RoMeRL
(training code "being organized"; eval checkpoints only)
GroundCUA
(ServiceNow — training/ marked "Coming Soon")
CoEvolve: Training LLM Agents via Agent-Data Mutual Evolution
(ACL 2026, AMAP/Alibaba — repo created but code not yet released)
Related lists in Computer Science
See category94
Table of Contents
hesreallyhim/awesome-claude-code
A hand-picked collection of the finest of resources for the most awesome of agents, Claude Code, the undisputed champion of coding companions, from the unstoppable team…
94
Awesome Agent Skills
VoltAgent/awesome-agent-skills
A curated collection of 1000+ agent skills from official dev teams and the community, compatible with Claude Code, Codex, Gemini CLI, Cursor, and more.
93
Awesome Machine Learning
josephmisiti/awesome-machine-learning
A curated list of awesome Machine Learning frameworks, libraries and software.
92
Awesome Production Machine Learning
EthicalML/awesome-production-machine-learning
A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning
92
AWESOME DATA SCIENCE
academic/awesome-datascience
:memo: An awesome Data Science repository to learn and apply for real world problems.
91
Static Analysis
analysis-tools-dev/static-analysis
⚙️ A curated list of static analysis (SAST) tools and linters for all programming languages, config files, build tools, and more. The focus is on tools which improve…