Data science research papers

PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation 📅 Publication Date: Jun 26, 2026 📑 Paper: https://arxiv.org/pdf/2606.28128.pdf 🔗 Code: https://github.com/huggingface 📝 Description: PhysisForcing enhances embodied video generation by enforcing physical consistency through pixel-level trajectory alignment and semantic-level relational alignment losses in a DiT-based framework.

LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing 📅 Publication Date: Jun 25, 2026 📑 Paper: https://arxiv.org/pdf/2606.26740.pdf 🔗 Code: N/A 📝 Description: A novel streaming video editing framework enables causal, frame-by-frame editing with stable long-horizon preservation and real-time responsiveness through a three-stage distillation pipeline and AR-oriented mask cache.

BlockPilot: Instance-Adaptive Policy Learning for Diffusion-based Speculative Decoding 📅 Publication Date: Jun 30, 2026 📑 Paper: https://arxiv.org/pdf/2606.31315.pdf 🔗 Code: N/A 📝 Description: Speculative decoding with adaptive block size selection improves inference efficiency by predicting optimal block sizes from prefilling representations, achieving significant speedup with minimal overhead.

DOPD: Dual On-policy Distillation 📅 Publication Date: Jun 29, 2026 📑 Paper: https://arxiv.org/pdf/2606.30626.pdf 🔗 Code: https://github.com/huggingface 📝 Description: DOPD addresses privilege illusion in on-policy distillation by dynamically routing token-level supervision between teacher and student policies based on advantage gaps and probabilities, improving capability transfer in large and vision-language models.

Dockerless: Environment-Free Program Verifier for Coding Agents 📅 Publication Date: Jun 26, 2026 📑 Paper: https://arxiv.org/pdf/2606.28436.pdf 🔗 Code: https://github.com/huggingface 📝 Description: A Dockerless environment-free agentic patch verifier improves code patch evaluation accuracy and enables effective post-training without execution-based verification costs.

Agentic Abstention: Do Agents Know When to Stop Instead of Act? 📅 Publication Date: Jun 27, 2026 📑 Paper: https://arxiv.org/pdf/2606.28733.pdf 🔗 Code: https://github.com/huggingface 📝 Description: Agentic abstention involves determining when an AI agent should cease interaction under uncertainty, requiring sequential decision-making across multiple environments and task types.

Orca: The World is in Your Mind 📅 Publication Date: Jun 29, 2026 📑 Paper: https://arxiv.org/pdf/2606.30534.pdf 🔗 Code: https://github.com/huggingface 📝 Description: Orca establishes a unified world latent space through next-state-prediction modeling using multimodal data and demonstrates superior performance in downstream tasks compared to specialized baselines.

Grouped Query Experts: Mixture-of-Experts on GQA Self-Attention 📅 Publication Date: Jun 18, 2026 📑 Paper: https://arxiv.org/pdf/2606.20945.pdf 🔗 Code: https://github.com/huggingface 📝 Description: Grouped Query Experts (GQE) improves Transformer efficiency by selectively activating query heads based on token content while maintaining key-value cache benefits of grouped-query attention.

PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystems 📅 Publication Date: Jun 21, 2026 📑 Paper: https://arxiv.org/pdf/2606.22388.pdf 🔗 Code: https://github.com/huggingface 📝 Description: PlanBench-XL evaluates large language model agents' ability to plan and adapt in complex tool-rich environments with limited visibility and dynamic disruptions.

Are We Ready For An Agent-Native Memory System? 📅 Publication Date: Jun 23, 2026 📑 Paper: https://arxiv.org/pdf/2606.24775.pdf 🔗 Code: https://github.com/huggingface 📝 Description: Large language model agents' memory systems have evolved into complex data management frameworks requiring systematic evaluation across multiple modules and workloads to understand their performance characteristics and trade-offs.

EnterpriseClawBench: Benchmarking Agents from Real Workplace Sessions 📅 Publication Date: Jun 22, 2026 📑 Paper: https://arxiv.org/pdf/2606.23654.pdf 🔗 Code: https://github.com/huggingface 📝 Description: EnterpriseClawBench presents a benchmark for enterprise agents based on real-world sessions with 852 reproducible tasks, emphasizing comprehensive evaluation metrics beyond single performance scores.

OpenRath: Session-Centered Runtime State for Agent Systems 📅 Publication Date: Jun 17, 2026 📑 Paper: https://arxiv.org/pdf/2606.19409.pdf 🔗 Code: https://github.com/huggingface 📝 Description: OpenRath introduces a PyTorch-like programming model for multi-agent systems using Session as a central runtime abstraction that enables explicit fork, merge, and replay operations while recording comprehensive execution state.

MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision 📅 Publication Date: Jun 15, 2026 📑 Paper: https://arxiv.org/pdf/2606.17162.pdf 🔗 Code: https://github.com/huggingface 📝 Description: MemSlides presents a hierarchical memory framework for personalized presentation agents that separates long-term user profiles, working memory for session constraints, and tool memory for reusable execution experiences to enable stable personalization and reliable local edits.

Formalizing Latent Thoughts: Four Axioms of Thought Representation in LLMs 📅 Publication Date: May 7, 2026 📑 Paper: https://arxiv.org/pdf/2606.27378.pdf 🔗 Code: N/A 📝 Description: An axiomatic evaluation framework reveals systematic failures in latent thought representations of LLMs across multiple reasoning tasks, demonstrating that current representations fail to satisfy fundamental functional axioms consistently across different model architectures.

EnterpriseClawBench: Benchmarking Agents from Real Workplace Sessions 📅 Publication Date: Jun 22, 2026 📑 Paper: https://arxiv.org/pdf/2606.23654.pdf 🔗 Code: https://github.com/huggingface 📝 Description: EnterpriseClawBench presents a benchmark for enterprise agents based on real-world sessions with 852 reproducible tasks, emphasizing comprehensive evaluation metrics beyond single performance scores.

Heterogeneous Scientific Foundation Model Collaboration 📅 Publication Date: Apr 30, 2026 📑 Paper: https://arxiv.org/pdf/2604.27351.pdf 🔗 Code: https://github.com/Violet24K/Eywa 📝 Description: Eywa is a heterogeneous agentic framework that extends language-centric systems to scientific foundation models by integrating domain-specific models with language-based reasoning interfaces for improved performance across diverse scientific domains.

OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents 📅 Publication Date: May 6, 2026 📑 Paper: https://arxiv.org/pdf/2605.05185.pdf 🔗 Code: https://github.com/shawn0728/OpenSearch-VL 📝 Description: OpenSearch-VL presents an open-source framework for training advanced multimodal search agents using reinforcement learning, featuring specialized data curation, diverse tool environments, and a novel training algorithm that improves performance across multiple benchmarks.

WorldOlympiad: Can Your World Model Survive a Triathlon? 📅 Publication Date: Jun 9, 2026 📑 Paper: https://arxiv.org/pdf/2606.11129 💻 Project Page: https://alibaba-damo-academy.github.io/WorldOlympiad/ 📝 Description: The paper introduces WorldOlympiad, a comprehensive benchmark for evaluating video-based world models. The problem with current generative models is that they often focus on visual quality, but lack physical faithfulness, geometric consistency, and interaction fidelity. To address this gap, WorldOlympiad decomposes world-model evaluation into three dimensions: physical faithfulness, geometric consistency, and interaction fidelity. WorldOlympiad covers three major downstream scenarios, including gaming, robotics, and general real-world videos, capturing diverse challenges from interactive control and embodied manipulation to open-domain motion and camera dynamics. #WorldModelEvaluation #VideoBasedWorldModels #PhysicalFaithfulness #GeometricConsistency

Qwen-AgentWorld: Language World Models for General Agents 📅 Publication Date: Jun 23, 2026 📑 Paper: https://arxiv.org/pdf/2606.24597.pdf 🔗 Code: https://github.com/huggingface 📝 Description: Language-based world models enable agentic environment simulation across multiple domains and enhance general agent performance through scalable simulation and improved downstream task performance.

HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation 📅 Publication Date: Apr 30, 2026 📑 Paper: https://arxiv.org/pdf/2604.28196.pdf 🔗 Code: https://github.com/H-EmbodVis/HERMESV2 📝 Description: HERMES++ combines 3D scene understanding and future geometry prediction through BEV representation, LLM-enhanced queries, temporal linking, and joint geometric optimization for autonomous driving applications.