Agents Score Higher but Fail the Same Way

Featured

• Learning Personalized Agents from Human Feedback score 10
  机构: Princeton; 入选 HF Daily Papers; HF 热度: 6 upvotes (+2); 关键词(4): preference, agent, agents, embodied
• Learning Humanoid End-Effector Control for Open-Vocabulary Visual Loco-Manipulation score 8
  入选 HF Daily Papers; HF 热度: 26 upvotes (+4); 关键词(1): robotics
• Multi-agent cooperation through in-context co-player inference score 8
  入选 HF Daily Papers; HF 热度: 15 upvotes (+3); 关键词(4): fast, inference, agent, agents
• Towards a Science of AI Agent Reliability score 8
  入选 HF Daily Papers; HF 热度: 12 upvotes (+3); 关键词(5): agent, agents, agentic, reasoning, safety
• Reinforced Fast Weights with Next-Sequence Prediction score 8
  入选 HF Daily Papers; HF 热度: 12 upvotes (+3); 关键词(5): fast, fine-tuning, GRPO, post-training, attention
• MMA: Multimodal Memory Agent score 7
  入选 HF Daily Papers; HF 热度: 6 upvotes (+2); 关键词(6): RAG, agent, agents, multimodal, benchmark
• Learning Situated Awareness in the Real World score 7
  入选 HF Daily Papers; HF 热度: 5 upvotes (+2); 关键词(5): agent, reasoning, multimodal, benchmark, evaluation
• Discovering Multiagent Learning Algorithms with Large Language Models score 8
  入选 HF Daily Papers; HF 热度: 10 upvotes (+3); 关键词(3): agent, coding, evaluation
• On the Mechanism and Dynamics of Modular Addition: Fourier Features, Lottery Ticket, and Grokking score 6
  入选 HF Daily Papers; HF 热度: 6 upvotes (+2); 关键词(1): alignment

Also Worth Noting

• Collaborative Zone-Adaptive Zero-Day Intrusion Detection for IoBT score 2
  关键词(4): efficient, lightweight, deployment, latency
• Axle Sensor Fusion for Online Continual Wheel Fault Detection in Wayside Railway Monitoring score 2
  关键词(4): efficient, lightweight, cost, safety
• GPSBench: Do Large Language Models Understand GPS Coordinates? score 2
  关键词(4): finetuning, tool use, reasoning, robotics
• Can Adversarial Code Comments Fool AI Security Reviewers -- Large-Scale Empirical Study of Comment-Based Attacks and Defenses Against LLM Code Analysis score 2
  关键词(4): production, code generation, benchmark, open-source
• Federated Graph AGI for Cross-Border Insider Threat Intelligence in Government Financial Schemes score 2
  关键词(3): inference, MoE, reasoning
• OmniCT: Towards a Unified Slice-Volume LVLM for Comprehensive CT Analysis score 2
  关键词(6): efficient, MoE, reasoning, vision-language, benchmark
• Surrogate-Based Prevalence Measurement for Large-Scale A/B Testing score 2
  关键词(3): fast, latency, evaluation
• Evolutionary Context Search for Automated Skill Acquisition score 2
  关键词(6): efficient, deployment, inference, fine-tuning, retrieval-augmented
• Rethinking ANN-based Retrieval: Multifaceted Learnable Index for Large-scale Recommendation System score 2
  关键词(8): efficient, efficiency, quantization, serving, real-time
• Empirical Cumulative Distribution Function Clustering for LLM-based Agent System Analysis score 2
  关键词(3): agent, agents, evaluation
• DeepVision-103K: A Visually Diverse, Broad-Coverage, and Verifiable Mathematical Dataset for Multimodal Reasoning score 6
  入选 HF Daily Papers; HF 热度: 2 upvotes (+1); 关键词(2): reasoning, multimodal
• CHAI: CacHe Attention Inference for text2video score 2
  关键词(5): inference, latency, attention, diffusion, text-to-video
• Retrieval Collapses When AI Pollutes the Web score 2
  关键词(3): retrieval-augmented, RAG, search