-
Multi-Agent Computer Use
Paper • 2606.01533 • Published • 5 -
OpenSkill: Open-World Self-Evolution for LLM Agents
Paper • 2606.06741 • Published • 29 -
Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills
Paper • 2606.07412 • Published • 13 -
Bayesian-Agent: Posterior-Guided Skill Evolution for LLM Agent Harnesses
Paper • 2606.08348 • Published • 16
Collections
Discover the best community collections!
Collections including paper arxiv:2610.18773
-
Harness^2: Recursive Agent Harnessing for an Open World
Paper • 2610.14224 • Published • 69 -
ClawLoop: Self-Improving Agents via Harness-Native Training Loop
Paper • 2610.14118 • Published • 27 -
Latent World Action Model for GUI Agents
Paper • 2610.14228 • Published • 10 -
Jeva: System One Models from First Principles
Paper • 2610.18773 • Published • 129
-
Why Fine-Tuning Encourages Hallucinations and How to Fix It
Paper • 2604.15574 • Published • 25 -
Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation
Paper • 2604.24763 • Published • 69 -
Programming with Data: Test-Driven Data Engineering for Self-Improving LLMs from Raw Corpora
Paper • 2604.24819 • Published • 84 -
GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents
Paper • 2604.26752 • Published • 114
-
LTX-2: Efficient Joint Audio-Visual Foundation Model
Paper • 2601.03233 • Published • 203 -
MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head
Paper • 2601.07832 • Published • 53 -
Motion Attribution for Video Generation
Paper • 2601.08828 • Published • 71 -
Post-LayerNorm Is Back: Stable, ExpressivE, and Deep
Paper • 2601.19895 • Published • 27
-
VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training
Paper • 2602.10693 • Published • 38 -
Flash-KMeans: Fast and Memory-Efficient Exact K-Means
Paper • 2603.09229 • Published • 82 -
DIVE: Scaling Diversity in Agentic Task Synthesis for Generalizable Tool Use
Paper • 2603.11076 • Published • 5 -
LongCat-Flash-Prover: Advancing Native Formal Reasoning via Agentic Tool-Integrated Reinforcement Learning
Paper • 2603.21065 • Published • 80
-
Towards Scalable Pre-training of Visual Tokenizers for Generation
Paper • 2512.13687 • Published • 105 -
MMGR: Multi-Modal Generative Reasoning
Paper • 2512.14691 • Published • 120 -
Coupling Experts and Routers in Mixture-of-Experts via an Auxiliary Loss
Paper • 2512.23447 • Published • 61 -
LiveTalk: Real-Time Multimodal Interactive Video Diffusion via Improved On-Policy Distillation
Paper • 2512.23576 • Published • 65
-
Multi-Agent Computer Use
Paper • 2606.01533 • Published • 5 -
OpenSkill: Open-World Self-Evolution for LLM Agents
Paper • 2606.06741 • Published • 29 -
Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills
Paper • 2606.07412 • Published • 13 -
Bayesian-Agent: Posterior-Guided Skill Evolution for LLM Agent Harnesses
Paper • 2606.08348 • Published • 16
-
Harness^2: Recursive Agent Harnessing for an Open World
Paper • 2610.14224 • Published • 69 -
ClawLoop: Self-Improving Agents via Harness-Native Training Loop
Paper • 2610.14118 • Published • 27 -
Latent World Action Model for GUI Agents
Paper • 2610.14228 • Published • 10 -
Jeva: System One Models from First Principles
Paper • 2610.18773 • Published • 129
-
Why Fine-Tuning Encourages Hallucinations and How to Fix It
Paper • 2604.15574 • Published • 25 -
Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation
Paper • 2604.24763 • Published • 69 -
Programming with Data: Test-Driven Data Engineering for Self-Improving LLMs from Raw Corpora
Paper • 2604.24819 • Published • 84 -
GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents
Paper • 2604.26752 • Published • 114
-
VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training
Paper • 2602.10693 • Published • 38 -
Flash-KMeans: Fast and Memory-Efficient Exact K-Means
Paper • 2603.09229 • Published • 82 -
DIVE: Scaling Diversity in Agentic Task Synthesis for Generalizable Tool Use
Paper • 2603.11076 • Published • 5 -
LongCat-Flash-Prover: Advancing Native Formal Reasoning via Agentic Tool-Integrated Reinforcement Learning
Paper • 2603.21065 • Published • 80
-
LTX-2: Efficient Joint Audio-Visual Foundation Model
Paper • 2601.03233 • Published • 203 -
MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head
Paper • 2601.07832 • Published • 53 -
Motion Attribution for Video Generation
Paper • 2601.08828 • Published • 71 -
Post-LayerNorm Is Back: Stable, ExpressivE, and Deep
Paper • 2601.19895 • Published • 27
-
Towards Scalable Pre-training of Visual Tokenizers for Generation
Paper • 2512.13687 • Published • 105 -
MMGR: Multi-Modal Generative Reasoning
Paper • 2512.14691 • Published • 120 -
Coupling Experts and Routers in Mixture-of-Experts via an Auxiliary Loss
Paper • 2512.23447 • Published • 61 -
LiveTalk: Real-Time Multimodal Interactive Video Diffusion via Improved On-Policy Distillation
Paper • 2512.23576 • Published • 65