arXiv
DynaHarness: A Dynamic Physical Harness for Self-Evolving Robot Agents
Pretrained robot policies provide useful action priors, but long-horizon manipulation still requires coordination bet...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
Scaling Laws for Looped Mixture of Experts
Looped transformers and Mixture-of-Experts (MoE) offer complementary routes to efficient scaling: recurrence increase...
arXiv
MatLoom: Layered Text-to-Material Generation in a Compact Program Space
Material generation should produce not only an appearance, but also the rules that construct it. We introduce MatLoom...
arXiv
Cogentic: Multi-Agent Orchestration for Automated Proof Discovery
We present Cogentic, a multi-agent harness for automated proof discovery on open research problems. While frontier la...
arXiv
WorldAuditBench: Interactive 3D World Auditing with Multimodal Agents
As interactive 3D worlds are increasingly used to study intelligent behavior, it becomes important to develop efficie...
arXiv
Turbo Harness: Instance-Adaptive Harness Optimization
Automating the search for effective harnesses is an important step toward enabling agents to recursively self-improve...
arXiv
ViTeX-Bench: Benchmarking High-Fidelity Video Scene Text Editing
Recent video generation is increasingly realistic and controllable, yet video editing remains less developed, particu...
arXiv
Semifactual Credit-Augmented Policy Optimization
Reinforcement learning with verifiable rewards (RLVR) has improved the reasoning capabilities of large language model...
HuggingFace
Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents
Terminal agents act through stochastic model generations, yet the ability to generate a useful action does not ensure...
HuggingFace
Unmask the State: When Does State Adaptation Matter for Masked Diffusion Language Models
Masked diffusion language models (MDMs) admit flexible generation orders, making the unmasking strategy an inference ...
HuggingFace
EVOKE: Eliciting World Knowledge in Agents for Transferable Decision-Making
Large language models (LLMs) are increasingly deployed as agents for multi-step decision-making, yet transfer poorly ...
HuggingFace
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents
Self-evolving search agents build their own training curricula by jointly optimizing a proposer that generates questi...