All papers
Every paper that carries a page of its own here. The Papers page leads with what is trending and lets you filter the recent catalog; this is the plain index of the rest.
Think Twice: The Metis-1.6 Technical Report2026SciGame: Let Agents Play the Scientific Discovery Games in the Real and Counterfactual World2026EPSBench: Benchmarking LLM Agents for Earnings Forecasting2026Cross-Primitive Consistency in Jev2026AskStream: When and What to Ask Proactively under Uncertainty in Streaming Video Understanding2026Weaken to Strengthen: Weakening-Induced On-Policy Self-Distillation for Large Reasoning Models2026HALO: Human-Grounded Granular Evaluation of Proactive Agents2026Unlimited OCR Works 22026Diagnosing the Reference Gap: What Visual Scaffolds Can and Cannot Fix in Multimodal Reasoning2026rTaste: Do Research Agents Have Taste? Evaluating Early Stage Research Judgment2026Every Token Needs Its Own Teacher: Multi-teacher Adaptive On-policy Self-distillation2026WebAnything: From the Wild Web to Scalable Agent Environments2026Investor's Last Exam: Can AI Agents Do Equity Investment Without Seeing the Future?2026WeVisCut: The Whole Editing Room in One Agent From Narration to Long-Form Video2026A-RSI: Adaptive Task Refresh for Zero-Data Multimodal Self-Improvement2026WorldFlow: Joint Video and 3D Motion Prediction via Large-Scale Pretraining2026FDSML: Formula-Driven Supervised Metric Learning with Parameter-Aware Triplet Loss2026Intrinsic Distribution Matching2026Where Do Vision Language Models Fail at 3D Reasoning?2026Probing Spatial State Representations in Visual Foundation Models2026Read, Allocate, Route: Role-Coupled Tokenization for Pixel-Space Generative Transformers2026EvoTeam: Multi-Agent Collaboration via Evolving Teams2026"Shall We Approve?" Consequence-Aware Approval for Autonomous Coding Agents2026TSFLab: A Self-Improving Agent-Agnostic Workbench for Time Series Forecasting Research2026On the Origin and Evolution of Training-Inference Mismatch in LLM Reinforcement Learning2026Lineage Is Memory: Parent Inheritance and Feedback Disclosure in Short-Budget LLM-Guided Optimization2026DAMI: Dual-Axis Memory Initialization for Enhanced Long-Context Retrieval in Gated Linear Attention2026RoboArchitect: Automating the Design of Robotic Agents with Persistent Memory2026Multi-Token Prediction Done Right2026Unlocking Any-Order Generation in Pretrained Autoregressive Image Models2026Training Foundation Models with a Single Algorithm2026Mage-VL-Cowork: A Full Training Recipe to Learn Hybrid Computer Use From Evolved Harnesses2026AuditFL: A Contract-Backed Clearing Layer for Open Federated Learning2026BYOD: Build Your Own DLM - Efficient Autoregressive-to-Diffusion Language Model Conversion2026Latent Reasoning in Continuous Space for Unified Multimodal Models2026Hybrid Computer Use: A Unified Programmatic, Semantic, and Visual Interface for General Agents2026From Fragmentation to Fusion: A Survey and Roadmap for Omnimodal Embeddings2026Random Is Almost Enough? Stable and Low-Cost Benchmark Compression via BestRand2026FinForesight: A Diagnostic Backtesting Benchmark for Deep Research Systems in Financial Forecasting2026Switch-SWE: Do Coding Agents Hold Focus When Switching Between Unfinished Tasks?2026ParetoSaddler: Pareto-Guided Optimization of Agent Harnesses for Quality and Cost2026Can AI Reviewers See Your Efforts to Improve Your Paper? A Large-Scale Study of Paper Revision Trajectories2026LEANGUARD: Lean-Verified Guardrails for Tool-Using Agents2026GigaSpeech 3: Scaling Multi-Dialect Arabic Speech Recognition with Weakly Labeled Data2026DR Pixel: Page-Native Deep Research with Vision-Language Models2026CoworkOS:Scaling Agent Coworkers for Real-world Automation2026IdeaTaste: Do LLMs Share the Research Taste of Human Researchers?2026Library of Layers (LoL): Adaptively Ordering Transformer Layers at Runtime2026WebHarbor: Docking Real Websites for Evolving GUI Agent Environments2026Why Pay for Long Reasoning When Rewrite Do Trick? Causal Effects of Reasoning History Compaction on Future Generation and Agent Cost2026Length Is Cheap, Competition Is Not: Attention Predicts Context Rot in Retrieval2026Think Less, Locally: Local Preference Learning for Reasoning Compression2026HERIT: Enabling Global Access to Hanja-to-English Historical Translation by Mitigating Temporal Bias2026ToolSpace: Scaling Tool-Centric Environment Synthesis for Long-Horizon Agents2026LoopVQ: Sub 1-bit KV Cache Quantization for Looped Transformers2026Is Your Long-Horizon Benchmark Really Deep? Measuring and Synthesizing Depth in Terminal Tasks2026RoboColosseum: Evaluating Physical Intelligence at Scale In-The-Wild2026Measuring AI Agents as Teammates with Collaborative Intelligence2026MoviEdit: Long-form Multi-Shot Video Editing Made Easy2026SpecOPD: Branch-Parallel On-Policy Distillation for Speculative Decoding2026CUA-Master: Scaling Computer-use Agents through Open-World Recursive Improvements2026Can Coding Agents Sustain Continual Evolution without Forgetting?2026EvoMemState: Evolving Memory State for Personal Agents2026Enhancing Stock Market Information Retrieval with Retrieval-Augmented Generation2026Multi-layer Indexer: Overlapping Selection and Attention in DeepSeek Sparse Attention2026Harness-S: Learning from Sibling Harnesses for Generalizable Agent Training2026Axion 1.0: Open Agent Foundation Models, Simplified2026Human-to-Robot Transfer via Bridging Representation and Action Space in VLAs2026Kierston & KierstonBench: Simulation of Allentown, PA and Evaluation of Language Models in Crime Investigation and Surveillance Tasks2026VisSearch-Bench: Evaluating Long Horizon Visual Search in Multimodal Agents2026When Does Latent Prediction Error Support Physical Surprise Claims in Video World Models?2026SpecPilot: Autonomous Algorithm Discovery and Systems Optimization for Speculative Decoding2026FLAMIA: FLAsh MIcroscaling Attention for Fast and Causally Safe Training on Blackwell2026Every Pixel Is an Option: A System One Model for Medical Ultrasound Biometry2026BEND 2.0: Benchmarking the Capabilities Needed to Design DNA2026What Does Multi-Turn Reinforcement Learning Really Improve in LLM Agents?2026Turns Matter: Advancing Streaming Video RL via Turn-Level Credit2026