HuggingFace
Towards Full Pipeline FP8 Reinforcement Learning for LLMs
Reinforcement learning (RL) has become a key technique for improving the reasoning and agentic abilities of large lan...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
OSWorld-Pro: Process-based Evaluation for Computer Use Agents
Evaluation of Computer-Use Agents (CUAs) is often limited to the final deliverables they create (at the end of hundre...
arXiv
Visuomotor Robotic Pruning in Planar Orchards Using Hybrid Reinforcement Learning
Dormant tree pruning is labor-intensive yet essential for maintaining modern high-productivity fruit orchards. In thi...
arXiv
BackTrend: Evaluating Scientific Weak-Signal Prediction via Backward Reconstruction
Scientific weak signals are early, low-visibility research directions that later become central to mature scientific ...
arXiv
Et Tu, Brute? Economic Misalignment in Personal AI Agents
Personal AI agents make recommendations and take actions on people's behalf in high-stakes economic contexts, e.g., b...
arXiv
Exactness at Inference: A Representational Criterion for Out-of-Distribution Generalization
A model generalizes outside its training distribution only when it computes a representation structurally equivalent ...
arXiv
Generative Tutorial: Towards Live Contextualized Visual Instructions for Physical Tasks
Visual instructions for physical tasks are typically authored in one context and followed in another, requiring users...
arXiv
Jev for Scientific Decisions: Evaluating Semantic Choices and Their Consequences
Scientific workflows often require choosing among known relations before a deterministic calculation can proceed. Whe...
arXiv
Emergent Collusion in Long-Horizon LLM Agent Interaction
LLM agents are increasingly deployed in collaborative settings, yet long-term interaction may give rise to undesirabl...
arXiv
Rare Event Estimation via Iterative Unalignment
As agents are deployed with increased autonomy, even extremely rare events along their stochastic output trajectories...
arXiv
DolphinBench: Mapping the Pareto Frontier of Agent Memory
Agents today often take real-world actions that depend on long-term memory and context recall over time. However, mos...
arXiv
RRSI: Regularized Recursive Self-Improvement of Agent Harnesses
An LLM agent's capability is largely magnified by its harness, namely the prompts, control flow, tooling, memory, and...