AI论文速递 2026年08月03日（HuggingFace Daily Papers）¶
数据来源：https://huggingface.co/papers 采集时间：2026-08-03
📌 重点关注¶
- Beacon: Knowing When and How to Perform Agentic Visual Reasoning | arXiv — 【重点关注】 The fundamental goal of agentic visual reasoning is to improve the success ra... 💡 Agent视觉推理的按需调用框架，避免无效多模态开销，多模态agent架构必读
- LEDGERMIND: Provenance-Constrained Multimodal Agentic Reasoning with a Structured Evidence Ledger | arXiv — 【重点关注】 Multimodal agents for visual question answering increasingly operate as multi... 💡 用结构化证据链追踪多模态推理，让agent决策可溯源可审计
- BM25 Wins at Scale: A Scaling Study of Retrieval-Augmented Generation Paradigms | arXiv — 【重点关注】 Retrieval-augmented generation (RAG) spans lexical and dense retrieval, graph... 💡 大规模RAG中BM25反超向量检索，知识库检索方案选型必读
📋 其他值得关注¶
- From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement | arXiv — Reinforcement Learning with Verifiable Rewards (RLVR) has driven recent progr...
- VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System | arXiv — Text-to-video models have achieved remarkable visual quality, yet they still ...
- Memory Decoder at Scale: A Pretrained, Parametric Long-Term Memory | arXiv — Decoder-only language models entangle long-term memory and reasoning in a sin...
- Is Deep Research Reliable? Misleading Knowledge Induces False Conclusions | arXiv — Deep Research agents extend LLM-based assistants into long-horizon workflows ...
- SpecFirst: Behavioral Specification Elicitation as a First-Class Step in Agent-Based Program Synthesis from Scratch | arXiv — LLM-based agents excel at software engineering tasks where an existing codeba...
- Filesystem-Based Memory for LLM Agents: Organization, Evolution, and Sustainability | arXiv — Deployed LLM agents increasingly keep their long-term memory as a filesystem:...
- AI Tour Meeting: Group Travel Planning by LLM Agents | arXiv — This paper proposes AI Tour Meeting, a group travel planning framework powere...