Rethinking Verification in Agent Harnesses
Agent harnesses enable large language models to act through tools, observe the results, and iteratively work toward a task goal. Verification checks and revises agents' work to improve output quality.
nlp
MLINFO COLLECTION
品質予測
工程条件、原料ロット、検査値から品質指標や不良リスクを予測するための技術です。
記事一覧
3 / 27Novel or Not? PatEx-Gym: Agentic Prior-Art Search for Novelty Assessment in Patent Examination
Patent examination is a challenging real-world task that requires agents to discover sparse prior art, iteratively refine queries, inspect technical evidence, and produce novelty assessments…
deep-learning
AdaPRA: Process Reward Agents with Adaptive Rubrics for Data Science
Data science agents can automate end-to-end machine learning workflows, yet they remain far from competitive on human leaderboards. Agents make process errors such as insufficient exploration,…
nlp
DraMaze: A Multi-Agent Pipeline with Future-Aware Memory for Diverse Microdrama Script Generation
The rapid growth of microdramas has increased demand for high-quality script production. Long-form microdrama script generation with LLMs requires both diverse plot progression and long-range…
nlp
Beyond the Estimate: Wiener-Informed Decoding for Easier Training of Pixel-Space Flow Models
Learning velocity fields directly in pixel space is difficult and slow. We show that coarse second-order image statistics can ease this task: frozen Wiener estimates improve velocity learning, with…
deep-learning
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…
nlp
Easy-3Dfy: Object-Level Geometric Composition for Single-Image 3D Scene Construction
Single-image 3D scene construction is a fundamental problem in 3D vision. Recent methods such as SAM-3Dfy enable end-to-end reconstruction of 3D assets and their scene layouts, but still struggle…
computer-vision
MMVistaReason: Toward Open-Data and Post-Training Recipes for Multimodal Reasoning
Open multimodal reasoning models have benefited from large-scale reasoning supervision, yet reliable post-training remains challenging due to uneven data quality, inefficient supervision…
deep-learning
CausalAlign: Causal Alignment of Video Generation Models for Consistent Ego-Motion
Diffusion-based video generation models (VGMs) can produce visually plausible videos, yet their camera ego-motion often drifts over long horizons. Camera ego-motion determines how the viewpoint…
nlp
SpatialBrain: Spatial Intelligence Growing from Experience
Spatial reasoning requires more than access to geometric tools: a reasoner must decide when direct observation is sufficient and when to reconstruct, measure, or change reference frames. We present…
nlp
EvaOmni: An Evidence-Grounded Benchmark for Audio-Visual Reasoning
Omni LLMs can naturally locate key audio and visual evidence and integrate information across modalities for audiovisual reasoning. Existing audio-visual reasoning benchmarks that mainly rely on…
nlp
Code2Video-Compass: A Comprehensive Benchmark for General-Purpose Code-Based Video Generation across T2V, I2V, and V2V
Code-based video generation offers fine-grained control, targeted editing, and component reuse compared with direct video generation. This approach requires multimodal large language models (MLLMs)…
nlp
CoworkEnv: Synthesizing Training Environments for Long-Horizon Cowork Agents
AI coworkers must coordinate tools, communicate across turns, and act on changing workspace state while respecting workflow constraints. Constructing training experience for these capabilities…
nlp
EvalResearchBench: Can AI Agents Build Their Own Feedback for Recursive Self-Improvement?
Recursive self-improvement (RSI) relies on evaluation feedback to assess progress and guide further research, yet repeatedly running complex benchmarks is costly and slows iteration. Human experts…
computer-vision
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…
generative-ai
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…
nlp
WorldStream: Streaming Interactive 3D Worlds with Hierarchical Planning and Persistent State
We present WorldStream, an open-ended 3D world model with three simultaneous capabilities: it extends playable terrain beyond any pre-specified map, acts on open-ended language in the running world,…
computer-vision
Large Flow Language Models
Continuous flow language models offer a path to parallel generation with tools for control and acceleration unavailable to discrete diffusion, yet effective techniques for building them at the…
deep-learning
Judging the Justification: Decision Certificate Supervision for Generative Reward Models
Generative reward models (GenRMs) generate natural language rationales to justify preference judgments, yet a correct verdict does not guarantee a sound justification. Existing approaches often rely…
computer-vision
SWIFT: Self-guided Weak-to-strong dIFfusion models via Target extrapolation
Training high-quality diffusion models is computationally expensive, and inference-time guidance often adds further sampling cost. In this work, we introduce Swift, a simple yet effective self-guided…
deep-learning
MT Forcing: Towards Stable and Consistent Multi-Turn Image Editing with Autoregressive Diffusion
Multi-turn image editing aims to modify an image according to a sequence of instructions, enabling more effective interactive visual content creation for users. However, existing methods often…
deep-learning
Function-Space Temporal Self-Distillation for Policy Optimization
Reinforcement Learning with Verifiable Rewards (RLVR) improves reasoning in language models, but scalar outcomes provide coarse supervision over response trajectories. Self-distillation offers denser…
deep-learning
evidently — Evidently is an open-source ML and LLM observability framework. Evaluate, test, and monitor any AI-powered system or data pipeline. From tabular data to Gen AI. 100+ metrics.
AIパワードシステムやデータパイプラインの監視と評価を行うための、オープンソースのMLとLLMの観測性フレームワーク。
AIパワードシステムやデータパイプラインの監視と評価
LoCA: Enabling Multi-Modality in Geospatial Location Encoders
Location encoders map geographic coordinates to high-dimensional descriptors through contrastive alignment with paired Earth Observation imagery. We prove that this construction is structurally…
nlp