arXiv
Hierarchical Graph Memory for LLM Agents with Path-level Localization and Rewrite
Agents for long term reasoning require a memory that can be efficiently and effectively updated over time, as new fac...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment
Long-horizon search agents must make multiple sequential actions (steps) to search, retrieve, verify, and integrate e...
arXiv
CoPlan: A Trustworthy Co-Intelligence Interface for Care Planning through Role-Based Contestable Argument Graphs
AI-supported care planning can help clinicians, patients, caregivers, and care teams coordinate complex decisions acr...
arXiv
Representational separation between unitary and channel quantum generative models via shared classical randomness at shallow depth
Near-term quantum hardware limits circuit depth and often imposes geometrically local connectivity for quantum genera...
arXiv
Robust and Efficient Motion Reasoning for Privacy-Aware Classroom Incident Recognition
Can computer vision help make classrooms safer? In this pilot study, we investigate privacy-aware and computationally...
arXiv
Chained Recursive Language Models for Multi-Iteration Reasoning
Long context reasoning in large language models (LLMs) is usually constrained by the fact that a single inference tra...
arXiv
SSTQ:Privacy-Preserving Vector Quantization via Subsampled Stochastic TurboQuant
Achieving local differential privacy in distributed optimization while maintaining low communication cost remains cha...
arXiv
OPD-V: Visual On-Policy Self-Distillation with Modality Balance
On-Policy Self-Distillation (OPSD) has become a standard post-training approach for improving visual reasoning in mul...
arXiv
Teaching Nemotron Greek: Mining a Corpus, Adapting Retrieval, and Grounding Generation for Modern Greek across Specialist Domains
Modern Greek is absent from NVIDIA's Nemotron retrieval models and from major multilingual retrieval benchmarks, desp...
arXiv
OctoLong: Mid-Training On Cross-Repository Code Contexts Enhances Long-Context Modeling
Context lengths of language models (LMs) have dramatically increased, driven by the demands for in-context learning, ...
arXiv
Argus: A General-Purpose Agentic Runtime for Long-Horizon Reasoning
Long-horizon reasoning requires an agentic runtime that can persist when evidence supports its current approach and p...
HuggingFace
UniWorld-View: Large-Baseline View Synthesis via Video Diffusion Models
The abundance of casually captured monocular videos and images on social media provides a valuable source for immersi...