Kaito Miyazaki

kaitomiya's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 2 papers about 6 hours ago

JockeyBench: Evaluating LLM Agents on Horse-Racing Decision-Making

Paper • 2610.19589 • Published 14 days ago • 8

Co-adaptive Rule Routing and Constraining for Structured Knowledge Retrieval

Paper • 2610.14465 • Published 11 days ago • 7

upvoted 2 papers 1 day ago

SCOPE: Compiling Natural-Language Policies into Neurosymbolic Predicate Programs

Paper • 2610.31062 • Published 6 days ago • 32

SEAM: Spectral Embedding Alignment and Merging for Low-Resource TTS

Paper • 2610.26252 • Published 9 days ago • 19

upvoted 3 papers 2 days ago

VerifierBench: Benchmarking the Generation of Executable Verifiers for LLM Agents

Paper • 2610.28679 • Published 9 days ago • 32

SciΠvot: Benchmarking Principal-Investigator Judgment at Pivotal Moments of Scientific AutoResearch Agents

Paper • 2610.21082 • Published 13 days ago • 16

ToM2Vec: Continuous Theory-of-Mind Tokens for Multi-Agent Coordination

Paper • 2610.29934 • Published 7 days ago • 16

upvoted 3 papers 4 days ago

Socratic Skill Learning: Interleaving Teaching and Practice for Transferable Agent Skills

Paper • 2610.17860 • Published 15 days ago • 51

Agent World Model in the Wild: Computer-Use Agent Environment Synthesis

Paper • 2610.26828 • Published 9 days ago • 102

Right Screen, Wrong Transition: World Models as Verifiers for GUI Agents

Paper • 2610.11942 • Published 20 days ago • 190

upvoted 4 papers 5 days ago

Muse Glimmer 30B: An On-Device Agentic Model

Paper • 2610.24628 • Published 11 days ago • 19

More Memory, Worse Agents: Error Reproduction and Anti-Persistence in LLM Agents

Paper • 2610.27406 • Published 9 days ago • 17

EAU: Environment-Agent-User Co-evolution for Training User-Centric Agents

Paper • 2610.16523 • Published 16 days ago • 26

FlowState: Execution State as Memory for Long-Horizon LLM Agents

Paper • 2609.34565 • Published 20 days ago • 24

upvoted 2 papers 8 days ago

MAI-Gym: An Open All-in-One Platform for GUI Agent Evaluation and RL Training across Mobile and Computer Environments

Paper • 2610.20939 • Published 14 days ago • 158

MJev-Spatial: System One Spatial Intelligence via Native Attention Matching

Paper • 2610.22276 • Published 13 days ago • 416

upvoted 4 papers 9 days ago

HumanoidToolBench: Benchmarking Humanoid Tool Use from Selection to Mobile Execution

Paper • 2610.02089 • Published 27 days ago • 36

Hybrid Reasoning Agents

Paper • 2610.18861 • Published 15 days ago • 44

τ-Emotion-Bench: Exposing the Interaction Fragility of LLM Agents through Real-World User Emotions

Paper • 2610.19560 • Published 14 days ago • 28

Long-Horizon RL Needs Muon

Paper • 2610.20256 • Published 14 days ago • 30