Training LLMs for Multi-Agent Collaboration with Verifiable Information Rewards
Paper • 2610.17893 • Published • 8
Kye Gomez
kye
·
AI & ML interests
Neuroscience, Behavior Science, Anti-Matter, Anti-Gravity propulsion,
Recent Activity
upvoted a paper 2 days ago
Training LLMs for Multi-Agent Collaboration with Verifiable Information Rewards upvoted a paper 2 days ago
Rethinking Projector Training in Multimodal LLMs upvoted a paper 2 days ago
Joint Subspace Sparse Attention for Efficient Long-Context DecodingOrganizations
upvoted 10
papers 2 days ago
Rethinking Projector Training in Multimodal LLMs
Paper • 2610.18598 • Published • 10
Joint Subspace Sparse Attention for Efficient Long-Context Decoding
Paper • 2610.19026 • Published • 13
SafeDriveVLA: Navigation-Conditioned World Model Dreaming for Conflict-Aware End-to-End Autonomous Driving
Paper • 2610.20609 • Published • 12
LLM-to-Flow Distillation: Teaching Natural Language Goals to Scientific Generators
Paper • 2610.17246 • Published • 11
SwarmRSI: Recursive Self-Improvement through Evolving Scientific Agent Swarm
Paper • 2610.20431 • Published • 68
Super-Resolution in The Right Latent Space: A Frozen Vision-Foundation Substrate
Paper • 2610.04781 • Published • 20
Hybrid Reasoning Agents
Paper • 2610.18861 • Published • 32
Towards Agentic Robots: Model, Data, Environment, and Harness
Paper • 2610.20442 • Published • 32
LatentLoop: Scaling Looped MoE Models with Asymmetric Compute Allocation
Paper • 2610.19975 • Published • 66
upvoted 10
papers 3 days ago
Omni-Modal LLMs Know More Than They Say
Paper • 2610.16135 • Published • 9
Agent Sociodrama: Social-Dynamics-Guided Persona Recasting for LLM Agent Teams
Paper • 2610.15788 • Published • 7
Fish Audio Drama 3 Technical Report
Paper • 2610.18010 • Published • 28
Tev: Scaling Long-Horizon Agentic Environments with Dense Progress Rewards
Paper • 2610.18868 • Published • 107
ClawLoop: Self-Improving Agents via Harness-Native Training Loop
Paper • 2610.14118 • Published • 28
Multics: Generative Multi-Player World Model with Hierarchical Communication
Paper • 2610.17201 • Published • 67
DoSA: Dots Sparse Attention
Paper • 2610.13990 • Published • 77
Vela: User Behavior as Supervision Sparks LLM Intelligence
Paper • 2610.14709 • Published • 81
Harness^2: Recursive Agent Harnessing for an Open World
Paper • 2610.14224 • Published • 105
Jeva: System One Models from First Principles
Paper • 2610.18773 • Published • 398