Harness Self-Evolution for Long-Horizon Terminal Agents
Long-horizon terminal agents may solve a task in one run yet fail across repeated runs. Stochastic errors can propagate through actions and context, creating a gap between capabili...
Papers
DecisionPivot: A Diagnostic Benchmark for Decision Models in LLM Systems
Decision models support routing, guardrails, and output verification in LLM systems. However, item accuracy alone cannot establish whether models make correct decisions across cont...
Slot-JEPA: Object-Structured Prediction Interfaces for Latent World Models
As a prototypical latent world model, Joint-Embedding Predictive Architectures (JEPAs) provide strong semantic representations. However, dense patch representations expose a redund...
HRoPE: Homography Relative Positional Encoding
Geometric Relative Positional Encoding has become the primary mechanism for injecting spatial inductive biases into multi-view transformers. Existing designs condition attention on...
Policy-Mask: Budget-Aware Adaptation of Diffusion Features to Discriminative Tasks
Selecting intermediate features from a frozen diffusion model for discriminative tasks is non-trivial because the useful signal is distributed across the denoising trajectory, netw...
Lost in Recovery: Demystifying Recovery Behavior of Computer-Use Agents via Goal-Oriented Action Replay
Recent advances in large (vision) language models have enabled computer-use agents that automate digital workflows via fine-grained keyboard and mouse operations. However, such age...
RoboJudge: Multimodal Language Models as Judges for Embodied Video Generation
Video generation models are promising foundations for embodied world models, but only if their generated rollouts are physically valid and faithful to task instructions. Multimodal...
World Models with Configurable Perception
Real-world observations are noisy and often contain excessive task-irrelevant information. Effective world modeling and planning need to abstract observations into world state repr...
Automating ML for Science: Can Frontier Agents Climb Scientific Hills in the Wild?
Frontier coding agents are increasingly framed as end-to-end automated researchers, and ML for science offers a demanding test of that promise: improving a scientific model often r...
RLSplat: Resource-Linear Budget Control for Feed-forward 3D Gaussian Splatting
Feed-forward 3D Gaussian Splatting (FF3DGS) reconstructs 3D scenes from images in a single forward pass, making it well-suited to applications that must operate within limited reso...
Sage-A1.5: From Long-Horizon Execution to Scientific Exploration with Capability Composition
In this report, we introduce Sage-A1.5, a 35B Mixture-of-Experts agentic model that builds on A1 to advance long-horizon problem solving through adaptive capability composition. Co...
SolarRenderer: Few-Step Generative Reference Rendering
Game engines and coding agents can specify the layout, motion, and camera of a scene, yet turning such coarse structure into realistic video requires a renderer that follows the st...
MultiAgent-OPD: End-to-End Training of Hierarchical Multi-Agent Systems with On-Policy Distillation
In a hierarchical multi-agent system, a Leader assigns tasks and subagents carry them out. Jointly training the Leader and the subagents is difficult because a final answer gives o...
MMEnterprise-Bench: Evaluating Enterprise Agents over Evolving Multimodal Records
Enterprise agents answer questions over workplace records that evolve through team collaboration. As information is shared, corrected, and revised across documents, chats, and figu...
Joints, Camera, Action! Co-Generating 3D Motion and Video for Arbitrary Rigs
Video generation models can now depict remarkably realistic motion. Yet it is unclear how to use this motion beyond pixels: to animate a specific 3D asset and replay the animation ...
From RL Papers to Framework Code: Inclusion and Review in Seven Open-Source Training Frameworks
Practitioners use reinforcement learning methods for language models through training frameworks, so a method that a framework includes is one configuration change away for its use...
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 ...
Specter: Fast MoE Inference via Quantization-Enabled Multi-Step Speculative Offloading
Mixture-of-experts (MoE) models often exceed a single accelerator's memory capacity. Offloading experts to host memory creates a severe PCIe I/O bottleneck because data-dependent r...
Multimodal Reranking Is a System One Decision
Multimodal rerankers are usually dedicated models: a vision-language model (VLM) is trained on retrieval data to score the candidates of a query. Scoring options is not specific to...
Bridged Self-Distillation for On-Policy Learning
On-policy distillation can transfer the reasoning capabilities of a strong teacher to a smaller student. However, distillation from a stronger teacher model faces two mismatches: i...
Diffusion Language Models Change Speed Across Tasks and Languages
Diffusion language models can write several tokens in one forward pass, and they decide during generation how many passes to spend. Two outputs of the same token length can therefo...
DeOverlay: A Benchmark and Source-Anchored Flow for Video Overlay Removal
Video overlay removal aims to recover scenes obscured by subtitles, titles, and logos while preserving surrounding content. Existing methods use temporal propagation or source-cond...
HarnessPro: Recursive Harness Self-Improvement with Pareto Optimization for Performance-Cost Trade-offs
Harness development plays a crucial role in building capable AI agents. Recent approaches improve harnesses through recursive self-improvement (RSI), but their performance gains of...
MMedAgent-Plus: Scaling Multimodal Medical Agents across Modalities, Tasks and Workflows
Medical workflows often require multiple interdependent analyses, but existing specialist and generalist AI models are not designed to coordinate them. We introduce MMedAgent-Plus,...