JarvisHub: An Open Harness for Canvas-Native Multimodal Creative Agents
Paper • 2607.23588 • Published • 112
siyeng feng
siyengfeng
AI & ML interests
None yet
Recent Activity
upvoted a paper about 18 hours ago
JarvisHub: An Open Harness for Canvas-Native Multimodal Creative Agents upvoted a paper about 18 hours ago
StateAct: Program State, before Pixels, for Long-Horizon Computer-Use AgentsOrganizations
None yet
upvoted 5
papers about 18 hours ago
The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation
Paper • 2607.24720 • Published • 22
StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents
Paper • 2607.22798 • Published • 55
From Proprietary to Open-Source: Bridging the Distribution Gap via Multi-Agent Protocol Distillation in Agentic Search
Paper • 2607.24280 • Published • 73
Kimi K3: Open Frontier Intelligence
Paper • 2607.24653 • Published • 301
upvoted 4
papers 1 day ago
Multi-Head Latent Control: A Unified Interface for LLM Agent Decision Making
Paper • 2607.14277 • Published • 8
Agentic Context Management: Solving Agent Memory and Cost by Treating Them as Lifecycle and Architecture Problems
Paper • 2607.21503 • Published • 22
Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning
Paper • 2607.21653 • Published • 29
Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills
Paper • 2607.22529 • Published • 38
upvoted 7
papers 4 days ago
OpenForgeRL: Train Harness-native Agents in Any Environment
Paper • 2607.21557 • Published • 7
Multi-Turn On-Policy Distillation with Prefix Replay
Paper • 2607.04763 • Published • 11
Sample-Efficient Learning from Agent Experience
Paper • 2607.21051 • Published • 17
Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction
Paper • 2607.20911 • Published • 25
NVIDIA-labs OO Agents: Native Python Object-Oriented Agents
Paper • 2607.20709 • Published • 31
Visual Contrastive Self-Distillation
Paper • 2607.21556 • Published • 48
AREX: Towards a Recursively Self-Improving Agent for Deep Research
Paper • 2607.21461 • Published • 147
upvoted 3
papers 5 days ago
Linear Attention Architectures: Mechanisms, Trade-offs, and Cross-Layer Routing
Paper • 2607.07953 • Published • 16
Remember When It Matters: Proactive Memory Agent for Long-Horizon Agents
Paper • 2607.08716 • Published • 15
Generative Compilation: On-the-Fly Compiler Feedback as AI Generates Code
Paper • 2607.13921 • Published • 11
upvoted a paper 7 days ago