CADFather: Autonomous CAD Reconstruction through Coordinated Tool Use
Paper • 2610.09127 • Published • 24
Kaito Miyazaki
kaitomiya
·
AI & ML interests
index compression, orchestration, function calling, time series forecasting, multi-agent systems
Recent Activity
upvoted a paper about 4 hours ago
CADFather: Autonomous CAD Reconstruction through Coordinated Tool Use upvoted a paper about 4 hours ago
Scoring Higher, Answering Worse: Mitigating Reward Hacking in Rubric-Based RL via Protocol-Level Rubrics upvoted a paper 1 day ago
ReSAIL: Mitigating Collapse in Iterative Agent Self-DistillationOrganizations
None yet
upvoted 2
papers about 4 hours ago
upvoted 2
papers 1 day ago
upvoted 2
papers 2 days ago
upvoted a paper 3 days ago
upvoted 2
papers 4 days ago
upvoted 3
papers 5 days ago
Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments?
Paper • 2610.08215 • Published • 157
Accurate but Not Humble: Evaluating Epistemic Humility in LLM Agents under Knowledge Conflict
Paper • 2610.12360 • Published • 13
From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation
Paper • 2610.06100 • Published • 144
upvoted 3
papers 8 days ago
upvoted 5
papers 10 days ago
EVISKILL: Grounding Skill Evolution in Replayable Evidence
Paper • 2610.05030 • Published • 55
Understanding and Enhancing Backdoor Persistency in LLM Agent Post-Training
Paper • 2610.07510 • Published • 14
TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models
Paper • 2610.07767 • Published • 93
Foundations of Proactive Agents: Principles, Technical Layers, and Proactivity-Gym
Paper • 2609.37267 • Published • 40
LMBuild: Evaluating LLM Agents for Generating Buildable and Functional Structures
Paper • 2610.04292 • Published • 40