Incremental Open-Ended Deep Research with Structured Harness
Existing Open-Ended Deep Research (OEDR) systems primarily generate reports from scratch, making them inefficient for scenarios where research reports need to be continuously maint...
Research Papers
Latest AI/ML research from ArXiv and Papers with Code
OpenESM: Energy-Steered Models Are Scalable Foundation Learners
Energy-based models have shown promising properties for domain-specific tasks but remain challenging in modeling general-purpose scenarios. To bridge this gap, we design energy-ste...
Toward Part-Aware Choral Transcription with singing voice assignment
Single-instrument automatic music transcription (AMT) has advanced substantially, yet choral applications require soprano, alto, tenor, and bass (SATB) to be transcribed as separat...
Less from More: Reinforcing Sparse Video Reasoning from Dense References
Video-language models commonly assume that more temporal observations lead to more reliable reasoning. We question this assumption and argue that the key challenge is not merely pr...
miniTE: Diagnosing and Bridging the Execution Gap in Native NVFP4 Reinforcement Learning
Native NVFP4 promises to accelerate reinforcement learning (RL) for large language models (LLMs), but achieving stable learning across separate training and sampling engines remain...
Video-Conditioned Generative Joint 2D-3D Hand Motion Recovery
Recovering faithful 3D hand motion from video remains challenging due to frequent occlusions and incomplete visual observations, which make frame-wise pose estimates unreliable and...
DSReg: Provably Recovering Individual World Latents without Reconstruction
Methods that recover individual latent variables of the world, from nonlinear ICA to dictionary learning and causal representation learning, anchor the latents to observations thro...
NavGPT-3: Harnessing Context in a Hierarchical Navigation Runtime
Language models trained with long-horizon agentic reinforcement learning can generalize knowledge through reasoning, express precise actions, and pursue goals over many steps, rais...
Coding-Agent Benchmarks Should Match Their Users' Task Flows
The evaluation of coding agents generally strives to be as realistic as possible. In our study, we collect 4,782 agent sessions of real software engineers in JetBrains IDEs, which ...
UniSkill: Learning Actor-Aligned Skill Proposals for an Evolving Policy
Large language model agents can improve across tasks by retaining reusable skills distilled from prior interactions. Recent work jointly optimizes task execution and skill extracti...
From Pareto to Preference: Personalized Test-Time Scaling via Amortized Agentic Policy Discovery
Test-time scaling (TTS) improves the reasoning capabilities of large language models by allocating additional inference computation. Existing approaches to improving TTS efficiency...
Which Language Should a Skeleton Speak? Language Choices in Multilingual Reasoning
Skeleton-based reasoning prompting is a promising training-free approach for structuring LLM reasoning, but prior work largely assumes an English-centric setting. We propose the La...
SALD: Self-Referenced Advantage Learning for Diffusion Models
Recent work on language-model adaptation has shown that single models can obtain informative training signals by evaluating their behavior in demonstrationor feedback-augmented con...
Tetris3D: 3D Scene Generation With Objects That Fit Together
We propose Tetris3D, a generative framework for single-image 3D scene reconstruction that recovers objects which are physically and geometrically coherent as a scene. Existing meth...
Controlled Acquisition and Abstention in Three-Channel Score Conflicts
When audio, video, and text disagree, accuracy alone does not show whether to acquire another source or abstain. We study these choices in a controlled three-score benchmark: a pol...
SWE-Game: Can Coding Agents Build the Games We Want?
We introduce SWE-Game, a benchmark of 247 tasks grounded in 41 executable reference Godot games spanning 13 gameplay categories in 2D and 3D. Five task types cover development from...
RunningTab: Direct Workspace Interaction with Environment-Side Tabs
Much knowledge work produces new deliverables from files a workspace already holds, and LLM agents are beginning to take such work over. Through direct corpus interaction, an agent...
RobotWorld: Benchmarking Multimodal Agents for Robot Use Across Diverse Tasks and Embodiments
General-purpose agents increasingly write code, use tools, and complete complex digital tasks, raising the question of how far these capabilities carry into the physical world. To ...
RoboQuest: Generalist Physical Agents that Search, Inspect and Test
Recent advances in multimodal foundation models have made them capable generalist physical agents for a range of manipulation tasks. However, successful operation in an unfamiliar ...
On-Policy Distillation Teaches New Skills but Not New Knowledge
On-policy distillation (OPD) strengthens language-model reasoning, yet whether students acquire new factual knowledge or compositional skill for multi-step reasoning remains unknow...
WebFovea: When the Model Is Right but the Click Is Wrong -- Reliable Round Trips for Vision-Based Web Agents on Live Websites
We present WebFovea, a vision-based web agent that placed 2nd in the WebRetriever Challenge 2026 with a final score of 57.0 out of 100. The challenge evaluates agents end to end on...
RLHND: Video Foundation Models as Physically Grounded Hand Trackers for Robot Learning
Recently, approaches that leverage human video datasets for robot policy training have become increasingly prevalent. However, most existing hand trackers regress pose from cropped...
We Query, Therefore We Compute: On Oracle Computation beyond the Machine, with an Application to Agents
Agentic systems use large language models (LLMs) to carry out concrete tasks. Prior work often borrows abstractions such as scheduling, caching or isolation piecemeal from operatin...
MIRA: A Musical Intent Refinement Agent for Aligning Text-to-Music Generation with User Intent
Text-to-music systems produce increasingly convincing audio, yet evaluation reveals little about whether the result matches user intent. A global text-audio relevance score can ove...