HuggingFace
Stratified Sparse Attention: Reducing the Sparse-to-Dense Gap at Extreme Sparsity
Large Language Model inference over long contexts is increasingly bottlenecked by the cost of attending to a growing ...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
Bridged Self-Distillation for On-Policy Learning
On-policy distillation can transfer the reasoning capabilities of a strong teacher to a smaller student. However, dis...
HuggingFace
Same Simulation, Different Evidence: Where Retrieved Tool Output Costs LLM Agents Accuracy
LLM agents that compute the right answer can still answer wrongly. Agent harnesses increasingly keep long tool output...
arXiv
Which Differences Matter? Controlled Tests of Rule Transfer, Joint Reliability, and Information Use in Decision Models
Decision models map stated rules and observed states to discrete answers. Aggregate accuracy leaves unresolved which ...
arXiv
SWE-DIVE: Multi-Turn Coding Agent Evaluation with Dynamic User Simulation
Coding agents are typically evaluated using one-shot, well-formulated prompts. Benchmarks such as SWE-bench use exist...
arXiv
From Reasoning to Action: Benchmarking Frontier AI Models on LIBERO-10 Robot Manipulation Tasks
Recent advances in frontier AI models have demonstrated remarkable capabilities in visual understanding, reasoning, p...
arXiv
Charts as Epistemic Actions for Experience-Driven Agentic Data Analysis
Data agents built on ReAct-style loops now execute complex analytical workflows over structured data, yet their inter...
arXiv
Parallel AI Agent Collaboration as Graph-Structured Distributed Block Optimization
Parallel AI agents can produce useful local edits yet degrade a shared solution when their edits are combined. We mod...
arXiv
AtomicRL: Atomic Reinforcement Learning for Long-Horizon Robotic Manipulation
Vision-language-action (VLA) models have shown promise in robotic manipulation, but imitation learning (IL) alone oft...
arXiv
Differentially Private Sparse Reward Estimation with Preference Feedback
Reinforcement Learning with Human Feedback (RLHF) has become a central paradigm for aligning Large Language Models wi...
arXiv
BatchBench: Benchmarking AI Robustness to Batch Effects and Domain Shift in Biomedical Images - A JUMP Cell Painting Leaderboard
Despite recent advances, current AI systems remain highly susceptible to domain shifts, particularly in biomedical im...
arXiv
Asymmetric On-Policy Distillation Learns In-Context Exploration
Sequential decision-making under partial observability is difficult because agents must explore to infer hidden, task...