论文雷达

模型与评测

今天论文：EditAgent（Agent 原型），Youtu-Parsing-Omni（Agent 原型）。并行还有 L3G-World、Read, Allocate, Route、HairDeck。看方法能不能迁到自己的 Agent 或生成管线。

日期: 2026/11/01
今日条目: 50
当前类目: 50

往期

全部50 编码代理0 Agent与工具0 个人助理0 模型与评测50 创作成片0 开发与开源0 产品接入0

领域机器人具身1 金融2 行业观察1

#25

WorkFactory: Turning Professional Intents into Executable Work for Scalable Agent Training

Scaling supervised training for working agents requires diverse professional tasks that yield reliable expert demonstrations. However, missing or inconsistent task information can obstruct teacher execution and weaken the resulting supervision. We propose WorkFactory, a scalable

HF daily papers · 赞 36打开原文

#26

Co-Design Bench: Multimodal Collaborative Coding Evaluation for Agentic Models

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

HF daily papers · 赞 20打开原文

#27

SO-101 Bench: Accessible Spatial Manipulation

Low-cost arms such as the SO-101 have become the most common entry point to robot learning, yet no released policy performs spatially constrained, language-conditioned tasks on them out of the box, and existing SO-101 benchmarks run only on physical hardware with simple tasks and

HF daily papers · 赞 8打开原文

#28

Know, then Draw: A New Learning Paradigm for Visual Generation

Visual generation requires both high-level semantic knowledge and fine-grained pixel details. We propose a learning paradigm that assigns these roles to autoregressive pretraining for knowledge acquisition and diffusion post-training for high-fidelity rendering. Within this frame

HF daily papers · 赞 2打开原文

#29

Evaluating DeepSeek V4.1 Flash-1017 for loss of control and harmful manipulation risks

As frontier language models grow increasingly capable and autonomous, independent third-party evaluations are critical for characterizing their systemic safety risks. While closed-source releases are routinely accompanied by comprehensive system cards, open-weight models receive

HF daily papers · 赞 7打开原文

#30

Instruction Capacity: Behavior and Degradation of Language Models under Controlled Load

The quality with which language models follow instructions falls as the load grows, yet there is still no quantity that expresses the limit of a model in units of load with an uncertainty. We propose an instrument in which the load consists of rules that replace single-token word

HF daily papers · 赞 4打开原文

#31

Matched Capabilities, Different Behaviors: A Controlled Study of MCP and CLI Interfaces for Language Agents

Language agents increasingly act through external tools and interactive environments, making the interface between the model and its executable capabilities part of the decision process. Model Context Protocol (MCP) and command-line interfaces (CLI) can expose the same semantic o

HF daily papers · 赞 4打开原文

#32

Broken on Arrival: Non-Functional Quantized LLM Artifacts in Public Model Registries and How to Catch Them

Developers download quantized large language models (LLMs) from public registries to run them locally. None of the registries we examined documented functional testing of their files. We tested all 305 eligible code-capable GGUF tags (the llama.cpp format) across 15 model lines i

HF daily papers · 赞 5打开原文

#33

PreView: Enhancing GUI Grounding with Preprocessed Views and Cues

GUI grounding requires locating small controls in cluttered screenshots and identifying which control a natural-language instruction refers to. Cropping and enlargement can expose local detail, but the resulting image may still leave ambiguity about the intended target. We propos

HF daily papers · 赞 4打开原文

#34

A Broader Look into MLLM's Retrieval Heads

Locating relevant evidence in long inputs is a core capability of Multimodal Large Language Models. Prior studies attribute this capability to retrieval heads, a sparse set of attention heads that transfer information from the context to the output. However, these analyses are co

HF daily papers · 赞 28打开原文

#35

VibeGame: Prompt-to-Game Development with AI-Native Engine and Self-Evolving Adversarial Agent Team

Large language model agents have enabled software development through natural-language interaction, but extending this paradigm to end-to-end game development remains challenging. Building a playable game requires coordinating code, scenes, assets, animations, physics, and config

HF daily papers · 赞 22打开原文

#36

Your Benchmark Is an Empirical Measure Over Difficulty

A benchmark is not merely a collection of test questions; it naturally induces an empirical measure over difficulty. In this work, we develop this measure-based view of benchmark evaluation. This perspective allows us to identify and formalize two central failure modes: measure m

HF daily papers · 赞 21打开原文

#37

LongZero: Enhancing Long-Context Reasoning in LLMs from Zero Data

Reinforcement learning (RL) is an effective way to strengthen the long-context reasoning of large language models (LLMs), but it needs training data that are long, diverse, challenging, and verifiable. Human annotation of such data is expensive, naturally occurring data are too s

HF daily papers · 赞 7打开原文

#38

CausGround: Causal Interaction Grounding for Adaptive Embodied Planning

Multimodal large language models (MLLMs) show promising reasoning capabilities, but reliable physical interaction requires planning that accounts for when actions are executable and how they change the world. These preconditions and effects are environment-dependent and often not

HF daily papers · 赞 4打开原文

#39

LOB-Impact Benchmark: Emergent Market Impact in Generative Limit Order Book Models

Realistic market impact is essential for generative limit order book (LOB) models to serve as world models for trading agents. If a simulator misprices this mechanism, agents learn policies that are optimal in the simulator but wrong in the real market. Existing metrics assess ge

HF daily papers · 赞 4打开原文

#40

Holo4D: Holistic 4D Reconstruction as Geometric Control for Video Diffusion

Synthesizing a monocular video from a new camera trajectory requires preserving the observed scene geometry and motion while completing regions that become newly visible. Feed-forward 4D reconstructors recover the structure of the observed scene, whereas video diffusion models pr

HF daily papers · 赞 3打开原文

#41

ABF-Bench: A Verifiable Benchmark for Agentic Blockchain Forensics

Blockchain forensics is adversarial and open-ended: money launderers split, swap, and bridge funds, cut their trail at mixers or custodial services, and change tactics from one incident to the next. Investigators must keep adapting their tracing in response. Yet the immutability

HF daily papers · 赞 3打开原文

#42

PersonaCUABench: Benchmarking Computer-Use Agents Serving Diverse Personas

Computer-use agents (CUAs) are commonly evaluated against fixed task specifications, but users may omit requirements, add constraints, or require approval before consequential actions. Completing the benchmark instruction does not guarantee serving the person who asked. We introd

HF daily papers · 赞 16打开原文

#43

RealCLI: Toward a Unified Evaluation of Human-Agent Collaboration for CLI Agents

Command-line interface (CLI) agents increasingly execute longer-horizon tasks, yet existing benchmarks either assume that user instructions remain fixed throughout execution or evaluate task outcomes without capturing runtime collaboration quality. In this paper, we present REALC

HF daily papers · 赞 17打开原文

#44

CoSTA: Compressed Speech Token Adaptation for Efficient Spoken Dialogue Models

Spoken Dialogue Models (SDMs) typically share a speech-token space for generation and synthesis, leading to long autoregressive sequences and costly inference. Lower-rate speech tokenizers shorten sequences but may introduce compression-quality trade-offs and costly replacement w

HF daily papers · 赞 12打开原文

#45

Amortizing Sequential Experimental Design in Reasoning LLMs

Despite their extensive pretraining knowledge and strong reasoning capabilities, large language models (LLMs) struggle to adaptively gather information in experimental design tasks. We study how to amortize sequential Bayesian experimental design (BED) into an LLM by explicitly t

HF daily papers · 赞 8打开原文

#46

After One-Click Video: The Inflow of Service-Type Content, the Failure of the Recommendation Pool Mechanism, and the BoLe System

In September 2026, a new large language model was released. Soon after, a new way of making explainer videos became very popular: people asked the model to write a program, and the program produced the video. "One-click video" content then appeared in large amounts on many platfo

HF daily papers · 赞 2打开原文

#47

OpenFlyV2: An onboard vision-language-action model for aerial perception and navigation

Human cognition flexibly draws on a shared perceptual foundation to understand environments, attend to referenced entities, reason about spatial relationships, and act. Endowing aerial robots with an analogous functional organization remains challenging, as existing systems are o

HF daily papers · 赞 5打开原文

#48

Proving and Improving the Platonic Representation Hypothesis with JEPAs

Whether models trained on different modalities converge to the same representation of the world is central to AI. The Platonic Representation Hypothesis (PRH) conjectures that they do as they scale, but without a proof it offers neither a guarantee nor a recipe. We turn the hypot

HF daily papers · 赞 58 · ★ 40打开原文