cập nhật 52 phút trước

⏱ Độ trễ thật của tab này: trung bình 6.8 giờ sau khi CVE được công bố (n = 5441, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

24
UserArena: Benchmarking Interactive User Simulation for Long-Horizon Shopping Agents
📄 Paper HF Daily Papers 28 ngày trước

Agentic recommendation pursues shopper goals through sequences of context-dependent decisions. Developing and evaluating such policies requires faithful recommendation world models that capture both the interactive shopping environment and users' behavioral responses over long in…

🅲 hạng C
24
WorldCast: World-Consistent Character Video Generation with Large-Angle Camera Control
📄 Paper HF Daily Papers 27 ngày trước

Precise camera control is essential for cinematic character video generation, yet existing methods struggle to follow large-angle trajectories with combined rotation, translation, and radius variation from arbitrary initial azimuths. Such viewpoint changes also reveal character r…

🅲 hạng C
24
Behind Video Generation: Observations and Insights on Multimodal Understanding from Kling
📄 Paper HF Daily Papers 16 ngày trước

Video generation has progressed from isolated clips to coherent short-form audiovisual sequences, and the bottleneck is shifting from rendering to semantic control. This report summarizes the observations and insights on multimodal understanding gained from successive generations…

🅲 hạng C
24
Few-Step Streaming Video Generation via Condition Shifting
📄 Paper HF Daily Papers 9 ngày trước

Few-step sampling reduces the cost of streaming video generation. Distribution Matching Distillation (DMD) supervises few-step generators with a separate fake-score network, which adds training memory and computation and must track the evolving generator. We extend APEX to stream…

🅲 hạng C
24
BirdDreams: Joint Perspective and BEV Video Generation for a Plausible, Reactive Driving World Model
📄 Paper HF Daily Papers 9 ngày trước

Driving world models aim to simulate how a scene unfolds under different ego actions. This requires plausible motion of surrounding vehicles as well as precise ego-trajectory control. Learning vehicle motion from perspective video alone is challenging because motion is entangled …

🅲 hạng C
24
HiSTEVE 1.0: Harnessing Human-Interface VLA Agents for Open-World Games
📄 Paper HF Daily Papers 28 ngày trước

Building virtual embodied agents that operate in open-ended games like human players is a long-standing goal requiring both long-horizon autonomy and reliable native-interface control. As a procedurally generated open world, Minecraft provides a natural testbed for studying the i…

🅲 hạng C
24
RynnUnify: Towards Unified Embodied Brain
📄 Paper HF Daily Papers 27 ngày trước

We introduce RynnUnify, a 16B unified embodied model that combines strong embodied understanding with long-horizon visual planning through interleaved video--language reasoning. With capabilities spanning spatial reasoning, physical prediction, and grounding, RynnUnify connects a…

🅲 hạng C
24
SWE-Trail: History-Guided Trajectory Collection for Coding Agent Training
📄 Paper HF Daily Papers 18 ngày trước

Coding agents solve repository issues through long sequences of exploration, editing, and validation. These trajectories are increasingly used as post-training data, so how they are collected shapes what the trained model learns. A common approach is to sample multiple trajectori…

🅲 hạng C
24
Actor, Judge, or Teacher? Understanding Decision Models in Long-Horizon Agents
📄 Paper HF Daily Papers 7 ngày trước

Decision models answer a question with a typed output, such as a choice among options with a probability for each, so one model can choose an agent's actions, evaluate actions already taken, or score every action to teach a policy with reinforcement learning. Prior work has studi…

🅲 hạng C
24
Wizard: Manipulate Any World in Real Time via Agentic Control
📄 Paper HF Daily Papers 21 ngày trước

Recent advances in video world models have enabled the generation of increasingly realistic and interactive virtual environments, opening new possibilities for player-customizable gameplay. Agentic frameworks further advance this direction by decoupling explicit game logic and co…

🅲 hạng C
24
Reviso: Not All Visual Evidence Deserves Equal Attention in Video Captioning
📄 Paper HF Daily Papers 16 ngày trước

Multimodal large language models (MLLMs) can generate detailed video captions, yet they may overemphasize minor details while overlooking essential context and key events. We argue that not all visual evidence deserves equal attention, as the importance of visual information depe…

🅲 hạng C
24
Embodied First Exam
📄 Paper HF Daily Papers 10 ngày trước

Early successes on agentic robotics point to a potential paradigm shift toward using coding agents to control robots. Existing robotics benchmarks are built around visuomotor policy learning, leaving it open whether coding agents can reliably control diverse robots under physical…

🅲 hạng C
24
StreamDuo: A Live Commentator and a Research Agent for Unseen Games
📄 Paper HF Daily Papers 19 ngày trước

Streaming video LLMs can now commentate live gameplay, but they are trained and tested on the same games. We study cross-game streaming commentary, in which a model trained on one game commentates games it has never seen, and find that current commentators transfer their timing b…

🅲 hạng C
24
EvoTeam: Multi-Agent Collaboration via Evolving Teams
📄 Paper HF Daily Papers 20 ngày trước

LLM-based multi-agent systems (MAS) rely on collaboration among specialized agents to solve complex tasks. Existing methods improve MAS by refining the prompts, skills, and execution strategies of individual agents based on task feedback. However, improving individual agents does…

🅲 hạng C
24
Beneath the Surface: What We Overlook When We Talk About Agent Evolution
📄 Paper HF Daily Papers 14 ngày trước

Agent harness evolution enables recursive self-improvement (RSI) without updating model weights. We examine whether higher benchmark scores yield reliable, efficient, and transferable improvement. We evaluate four methods across harnesses, general and coding tasks. Repeated evalu…

🅲 hạng C
24
Δτ-Bench: Pushing Agents Toward a Moving Capability
📄 Paper HF Daily Papers 25 ngày trước

In this paper, we introduce Δτ-Bench, an executable agent benchmark that models the structural evolution of large tool ecosystems. In Δτ-Bench, independently evolving services continually reshape how tasks can be accomplished: familiar tools may disappear or be replaced, while mo…

🅲 hạng C
24
h1: A Taste of the Bitter Lesson in Automated Theorem Proving
📄 Paper HF Daily Papers 25 ngày trước

While progress in informal mathematics has come largely from scaling the chain-of-thought and agentic reasoning of frontier language models, formal theorem proving has increasingly relied on human-designed workflows around these models, such as planning, decomposition, and orches…

🅲 hạng C
24
TAO: Tool-Aware Joint Scheduling for LLM-Based Agentic Serving
📄 Paper HF Daily Papers 23 ngày trước

Agentic services alternate between model inference on clustered GPUs and external tools on distributed CPUs. In this scenario, existing systems (1) overlook tool-return readiness in service evaluation, wasting limited resources, and (2) use heuristic strategies to decide admissio…

🅲 hạng C
24
Co-Design Bench: Multimodal Collaborative Coding Evaluation for Agentic Models
📄 Paper HF Daily Papers 24 ngày trước

Evaluating human-AI co-design requires testing whether coding agents can translate real users' multimodal requests into working application revisions. We introduce Co-Design Bench, a reference-free benchmark of 273 tasks curated from 37,463 deduplicated queries across 26,314 real…

🅲 hạng C
24
CaPtain: A Pipeline for Post-Training Code-as-Policy Robot Agents
📄 Paper HF Daily Papers 21 ngày trước

Across coding, web, and tool-use tasks, language-model agents are now routinely trained with the same recipe: supervised fine-tuning (SFT) to learn the interface, then multi-turn reinforcement learning (RL) to master it. Code-as-policy (CaP) casts robot manipulation in the same f…

🅲 hạng C
24
WebHarbor: Docking Real Websites for Evolving GUI Agent Environments
📄 Paper HF Daily Papers 17 ngày trước

GUI web agents require realistic and interactive environments that remain stable during both evaluation and training. Live website evaluation suffers from changing content, access restrictions, and limited coverage of authenticated workflows, while existing synthetic environments…

🅲 hạng C
24
On the Generalization Limitation of On-Policy Distillation for Post-RL Consolidation
📄 Paper HF Daily Papers 16 ngày trước

Multi-teacher on-policy distillation (MOPD) extends on-policy distillation (OPD) to consolidate capabilities from multiple teachers. Although prior work reports near-perfect in-distribution (IND) distillation performance, we find that this can mask incomplete capability consolida…

🅲 hạng C
24
Towards Foundation Decision Models: Drex
📄 Paper HF Daily Papers 14 ngày trước

Autoregressive approaches with large language models, such as long chain-of-thought reasoning, have become the default for new AI applications because they reach higher accuracy on a wide range of tasks. In production, however, they give inconsistent answers, require parsing of o…

🅲 hạng C
24
FINCOSMOS: An Open-World Evaluation Paradigm for Agents in Finance
📄 Paper HF Daily Papers 14 ngày trước

Language agents increasingly work for users on the open Web, and finance is where trusting them is hardest. The data must come from the Web, the strategy lives in the user's head, and correctness depends on time, so an agent can fail silently: a strategy the user never asked for,…

🅲 hạng C
24
Together Compiler: Continual Compilation for AI Inference
📄 Paper arXiv cs.AI 6 ngày trước

arXiv:2611.14681v1 Announce Type: new Abstract: Today's AI workloads are rapidly changing: new models are released more often, model architectures are increasingly diverse, and traffic distributions change frequently. The challenge we face at Together AI is continual optimizatio…

🅲 hạng C
24
Robust Task-Aware State Estimation from Pre-trained Perception
📄 Paper arXiv cs.AI 6 ngày trước

arXiv:2611.14781v1 Announce Type: new Abstract: Agents that perform state estimation using pretrained perception models, e.g., Vision-Language Models (VLMs), face the fundamental challenge that predictions are uncertain. Still, most approaches determinize these predictions into …

🅲 hạng C
24
Termination Lag: Coding Agents Solve Early but Stop Late
📄 Paper arXiv cs.AI 6 ngày trước

arXiv:2611.14960v1 Announce Type: new Abstract: Coding agents can solve a task well before they stop working on it. We characterize \emph{termination lag}--the number of steps between an agent's first correct patch and the end of its run--across five models, two agent frameworks…

🅲 hạng C