模型与评测

OlmoEarth v1.3: State-of-the-art embeddings for the whole planet

A rubric landscape for evaluating clinical reasoning in large language models: what exists, what is missing, and what needs to be combined

arXiv:2610.01938v2 Announce Type: replace-cross Abstract: Exam-style accuracy does not establish whether large language models (LLMs) reason well over clinical records. We define clinical reasoning as integrating and updating evidence across time and sources to form, revise and j

Agent Behavior Maps: Locating Agents by What They Would Do, Without Running Them

arXiv:2610.30014v1 Announce Type: cross Abstract: LLM agents with similar success rates can follow different action sequences. An Agent Behavior Map represents LLM-harness combinations using centered action log-likelihoods on shared reference trajectories, without requiring new e

Agentic Video Understanding: A Survey

arXiv:2609.31713v2 Announce Type: replace-cross Abstract: As large language models (LLMs) become capable of processing increasingly diverse modalities and longer temporal contexts, an emerging line of work is moving beyond fixed video-language inference toward agentic systems tha

Decision language models as affordable and rapid alternatives to LLM judges of clinical generative AI

arXiv:2610.28826v1 Announce Type: new Abstract: Automated judges of clinical artificial intelligence (AI) outputs are necessary, but large language model (LLM) judges are costly and slow at scale. We compared Jev, a decision language model that returns structured judgments, with

From Atomic to Agentic: Towards Interpretable Evaluation of LLMs' Agentic Mathematical Capabilities

arXiv:2608.26950v2 Announce Type: replace Abstract: Large Language Models (LLMs) are evolving from performing end-to-end mathematical reasoning to integrating agentic intelligence. However, most existing math benchmarks evaluate only final answers. This outcome-oriented evaluatio

HGM-Dual: Lineage-Aware Guided Agent Harness Optimization for Long-Horizon Planning

arXiv:2610.30042v1 Announce Type: new Abstract: Harness optimization, which improves an agent's prompts, tools, and workflows, is an increasingly effective way to enhance agents built on frozen or closed-source LLMs. Leading approaches such as the Darwin--Godel Machine and the Hu

Inheritance as an Admission Test for LLM Prompt Merge Operators

arXiv:2610.29023v1 Announce Type: new Abstract: Large language model (LLM) agents are often improved by iterating until a fixed verifier is done. Once that verifier saturates, the loop has nothing left to climb. We instead score agents against the current population, and a frozen

LocalAgent: Collaborative Agentic Verification for Fine-Grained Instance-Level Consistency

arXiv:2610.29174v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have made rapid progress in general visual understanding, yet they still struggle with fine-grained instance-level consistency verification, where the goal is to determine whether two images

Metamodel-Guided LLM Decoding for Consistent DSL Generation

arXiv:2610.29749v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to generate software engineering artifacts written in domain-specific languages (DSLs). Correct DSL instances usually must comply with not only the concrete syntax but also the ab

Steering Black-Box Large Language Model Agents with Pitfall Anticipation World Model

arXiv:2610.29139v1 Announce Type: new Abstract: Frontier black-box Large Language Model (LLM) agents are proficient at long-horizon reasoning and precise action generation. However, when it comes to a specific agentic task, they have no internalized knowledge of how that particul

When Agent Evaluation Becomes Unreliable: An Empirical Study of Oracle Failures and Configuration-Dependent Measurement in an LLM Agent Benchmark

arXiv:2610.16067v2 Announce Type: replace-cross Abstract: Agent evaluation harnesses are software: they run a test suite, drive a test input generator, and decide outcomes with a test oracle. We audit them for defects a score table cannot show. First, a systematic oracle-integrit

VideoGen Model 1: Prompt Expansion Versus Formatting in Audiovisual Generation

arXiv:2610.29407v1 Announce Type: new Abstract: Creative prompt expansion improved overall audiovisual quality scores over raw prompts in a controlled pilot of VideoGen Model 1, our post-trained version of MiniMax H3. We compared the raw, reformatted, and expanded versions of 30

Extending Affordance Segmentation for Wearable Robots to Multi-Object Images

arXiv:2610.29474v1 Announce Type: new Abstract: This paper proposes a refinement to existing vision-based portable pipelines for the recognition of graspable object parts. Such pipelines can effectively support automatic grasp selection and preshaping in upper-limb prosthetic dev

Physical AI for Intralogistics: Benchmarking the NVIDIA Sim-to-Real Ecosystem for Cosmos-Enhanced COMPASS Navigation on Industrial Mobile Robots

arXiv:2610.28432v2 Announce Type: replace Abstract: Classical robot navigation stacks are reliable but often require re-engineering for each new robot type and site. Learning-based navigation shifts this effort from hand-tuned parameters to data generation and training, where a p

Agentic Music Post-Production

arXiv:2610.29093v1 Announce Type: cross Abstract: We introduce MixAgent, an agentic pipeline for music post-production that follows the workflow of audio engineers to build interpretable and editable mixing plans guided by a reference song. A grouping agent first routes related i

An Evidence-Driven Multi-Agent Compound AI System for Head and Neck Proton Radiotherapy Planning

arXiv:2610.29010v1 Announce Type: new Abstract: Radiation treatment planning requires balancing competing objectives to satisfy clinical criteria while accommodating physicians' preferences. This study aims to develop an evidence-driven, multi-agent compound AI system that integr

Arbitrary-Scale Anisotropic 3D MRI Super-Resolution with Gaussian Prototypes

arXiv:2610.24858v2 Announce Type: replace Abstract: Reducing MRI acquisition time improves patient comfort, reduces motion artefacts, and increases scanner throughput. Clinical protocols often shorten acquisitions by sacrificing spatial resolution, particularly along the slice ax

Back Up Before You Regret: Measuring Backup Awareness and Automating Backup in Coding Agents

arXiv:2610.28934v1 Announce Type: new Abstract: Coding agents now complete tasks autonomously, modifying real-world state such as artifacts, software environments, and configurations along the way. Yet they show limited backup awareness: recognizing that an action will modify sta

Beyond Masks and Trajectories: Flow-Guided Latent Action Injection for Stable Surgical Video Generation

arXiv:2610.09800v2 Announce Type: replace Abstract: Surgical video generation holds substantial potential for surgical education, simulation, and data augmentation, yet generating surgical videos with realistic and clinically plausible motion remains challenging. Most existing me

Brittle by Design? Multi-Scenario Reinforcement Learning for Robust Mission Coordination in Systems of Systems

arXiv:2610.28818v1 Announce Type: cross Abstract: As systems engineering (SE) shifts from monolithic systems to Systems of Systems, Mission Engineering (ME) has emerged as a new line of thinking in SE. Mission environments are uncertain and dynamic, and outcomes depend on how mis

CTBench: Evaluating Troubleshooting Capabilities of AI Agents in Realistic Telecom Network Operations

arXiv:2608.12002v2 Announce Type: replace Abstract: While autonomous agents show promise for network operations, existing telecom troubleshooting evaluations fail to capture the partial observability and heterogeneity of real-world telecom environments. We introduce CTBench, a pu

Carving Radiology Reports at Their Evidential Joints: Anatomical Region Sets as Generation Units

arXiv:2610.29165v1 Announce Type: cross Abstract: Organizing radiology reports into independently generated units offers a way to generate fine-grained clinical content and bind it to visual evidence. However, existing methods typically adopt generation-unit structures not direct

Charts as Epistemic Actions for Experience-Driven Agentic Data Analysis

arXiv:2610.30072v1 Announce Type: new Abstract: Data agents built on ReAct-style loops now execute complex analytical workflows over structured data, yet their intermediate reasoning still runs almost entirely through text. Human analysts instead move between numbers, tables, and