数据来源：HuggingFace Papers Latest Papers1. OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video InteractionAbstract:Streaming video LLMs must retain evidence before its relevance to future tasks is known and respond when sufficient evidence becomes available. The challenge is to form reusable factual memory without compromising real-time perception. We introduce OneStreamer, which jointly learns query-independent evidence recording and task response through a shared ...

数据来源：HuggingFace Papers Latest Papers1. World Embedding BenchmarkAbstract:Physical fidelity has received increasing attention in world models and video generation, yet how video representations encode physical information remains less understood. We introduce the World Embedding Benchmark, comprising 8,000 controlled simulation cases from 80 families spanning fluid mechanics, solid mechanics, dynamics, and optics & electromagnetism. Each case pairs a rendered video with simulation-derived ...

数据来源：HuggingFace Papers Latest Papers1. ASCENT: Online Test-Time Training of Long-Horizon Agents via Self-Distillation of Verified ExperienceAbstract:A large language model (LLM) agent solves long-horizon tasks through many reasoning-action turns, with one verification signal at termination. Deployed agents face streams of related tasks, making their trajectories a natural resource for improvement. In-context adaptation agents store reflections, memories, or skills as text, so reuse depends on ...

数据来源：HuggingFace Papers Latest Papers1. Selection-Based Structured Reasoning: Toward Efficient Multimodal Search AgentsAbstract:Multimodal agents commonly generate free-form reasoning before each action. For small models, limited model capacity can result in lengthy reasoning that provides little useful guidance for action generation while incurring substantial inference cost. To address this challenge, we introduce Selection-based Structured Reasoning (SSR), a framework that reformulates reas ...

数据来源：github.com/trending global Languagesanthropics/claude-plugins-officialOfficial, Anthropic-managed directory of high quality Claude Code Plugins. ⭐ Stars: 40604 🍴 Forks: 0 📝 Language: Python K-Dense-AI/scientific-agent-skillsTurn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 250,000+ scientists worldwide. 177 ready-to-use validated skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Curs ...

数据来源：HuggingFace Papers Latest Papers1. Questioning the Questions: Sustaining Self-Evolution in Reasoning ModelsAbstract:Self-evolving reasoning models learn from their own generated questions, yet repeated self-training can lead to performance collapse. In this paper, we investigate why performance deteriorates over successive rounds and how to sustain self-evolution. Our analysis identifies two recurring quality problems in self-generated questions: invalid questions and repeated variants of ...

数据来源：HuggingFace Papers Latest Papers1. SuperNav: An Agentic Navigation System for Any Task in Any SceneAbstract:General-purpose service robots need navigation systems that can handle diverse human requests in unfamiliar environments, combining task generality with scene generality. Some existing methods fine-tune multimodal large language models (MLLMs) to predict navigation actions, making their behavior dependent on the coverage of navigation training data and potentially limiting generaliz ...

数据来源：HuggingFace Papers Latest Papers1. AgentGarten: Code Worlds for Evolving AgentsAbstract:Interactive virtual worlds allow agents to learn through exploration and interaction. What agents can learn is bounded by the environments they practice in, which must be faithful, with consistent state, rules, and dynamics, and realistic, with observations that follow the real-world visual distributions. Achieving both across diverse worlds remains a bottleneck. We introduce AgentGarten, a framework t ...

数据来源：HuggingFace Papers Latest Papers1. SoloQ: Calibration-Free Quantization for Diffusion Language ModelsAbstract:Diffusion large language models dLLMs) have emerged as a promising alternative to autoregressive language models through bidirectional diffusion-based token generation. However, their growing model sizes and high inference costs make efficient deployment challenging: full-sequence denoising repeatedly invokes compute-intensive forward passes, while block-diffusion models additiona ...

数据来源：HuggingFace Papers Latest Papers1. Scaling Agentic Data for Long-Horizon Terminal IntelligenceAbstract:Terminal agents are moving beyond local operations toward completing real-world professional tasks. Short trajectories can demonstrate commands and tool calls, but they do not fully show how agents accumulate evidence through exploration, use it to inform judgments, continually adjust strategies based on feedback, and turn intermediate results into final deliverables. High-quality long-h ...

数据来源：HuggingFace Papers Latest Papers1. PANINI-DR: Controlled Deep Research through Generative Semantic WorkspacesAbstract:Deep research requires connecting multiple steps of search, reasoning, and computation, with intermediate findings guiding what to investigate next. As investigations grow, agents must maintain research state across model calls and check findings before errors propagate into subsequent work. We introduce PANINI-DR, a multi-agent harness that separates coordination of the o ...

数据来源：HuggingFace Papers Latest Papers1. Training LLMs for Multi-Agent Collaboration with Verifiable Information RewardsAbstract:Effective collaboration among large language model (LLM) agents in multi-agent systems requires sharing relevant evidence, requesting missing information, and incorporating teammates’ contributions into decisions. Training these behaviors is challenging because final task outcomes provide limited feedback on the value of individual messages. We introduce CoSIR (Collab ...

数据来源：HuggingFace Papers Latest Papers1. SWE-at-Scale: Scalable Issue Synthesis from Historical Bug FixesAbstract:As coding agents become increasingly capable, robust evaluation requires a broader and more diverse supply of verifiable software engineering (SWE) tasks. However, real-world tasks are constrained by the natural frequency of issue reporting and the substantial cost of manual curation. Furthermore, existing synthetic approaches rely primarily on the pretrained knowledge of large mode ...

数据来源：HuggingFace Papers Latest Papers1. OmniCompass: A Holistic Benchmark for Omni-Modal Video Grounding and UnderstandingAbstract:With the rapid development of multimodal large language models (MLLMs), evaluating their video understanding capabilities has become increasingly important. Existing video understanding benchmarks cover only part of the evaluation dimensions, limiting systematic diagnosis of omni-modal video understanding. We introduce OmniCompass, a holistic benchmark for omni-mod ...

数据来源：HuggingFace Papers Latest Papers1. Pack Light, CarryOn: Building Object-Oriented Context for Long-Horizon AgentsAbstract:Long-horizon agents accumulate progress in persistent task state, yet repeatedly process interaction histories describing how that progress was achieved. This raises a natural question: can long-horizon context instead be organized around reusable progress rather than the history that produced it? In this paper, we introduce CarryOn, an object-oriented context runtime t ...