AI Research Agents Narrow Scientific Exploration
AI research agents can now generate research ideas, design experiments, run code, and draft papers, raising the possibility of large-scale AI-assisted scientific discovery. Many cu...
Research Papers
Latest AI/ML research from ArXiv and Papers with Code
Joint Training of Multi-Token Prediction in Reinforcement Learning via Optimal Coefficient Calibration
Reinforcement Learning from Verifiable Rewards (RLVR) has emerged as the standard paradigm for improving reasoning capability of large language models, while Multi-Token Prediction...
Revealing Algorithmic Deductive Circuits for Logical Reasoning
Recent studies have shown that Large Language Models (LLMs) can achieve strong reasoning performance by incorporating functional symbolic representations that abstractly describe g...
Learn from Weaknesses: Automated Domain Specialization for Small Computer-Use Agents
Computer-use agents (CUAs) have recently made substantial progress, but deploying a separate large expert for each software domain remains expensive. Small open computer-use agents...
Clark Hash: Stateless Sparse Johnson-Lindenstrauss Quantization for Neural Embeddings
Clark Hash is a small method for storing neural embeddings in less space. It normalizes each database vector, applies a deterministic sparse signed Johnson-Lindenstrauss projection...
VibeSearchBench: Benchmarking Long-horizon Proactive Search in the Wild
LLM-based agents score well on search benchmarks, yet real users consistently find results unsatisfying, revealing a persistent evaluation-experience gap. We attribute this gap to ...
Agent Explorative Policy Optimization for Multimodal Agentic Reasoning
Vision-language models with extended reasoning succeed on complex problems, but many real-world problems require external tools that internal reasoning alone often cannot resolve. ...
Self-Improving Language Models with Bidirectional Evolutionary Search
Search has been proposed as an effective method for self-improving language models and agentic systems, both for post-training sample generation and for inference. However, widely ...
HRBench: Benchmarking and Understanding Thinking-Mode Switch Strategies in Hybrid-Reasoning LLMs
Hybrid-reasoning large language models (LLMs) expose explicit controls over reasoning effort, allowing users or systems to trade off answer quality against inference cost. However,...
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players
World models for interactive video generation have largely focused on single-agent settings, where future observations are generated from a single control signal. However, many gen...
AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation
Scientific research proceeds through iterative cycles of hypothesis generation, experiment design, execution, and revision. AI agents can automate parts of this process, but existi...
CubePart: An Open-Vocabulary Part-Controllable 3D Generator
Interactive 3D assets used in games and simulation are typically decomposed into specific semantic parts to support animation, physics, and scripted behaviors, yet most generative ...
SmartDirector: Keyframe-Conditioned Cinematic Video Generation with Narrative Pacing Control
The narrative quality of a video fundamentally determines its perceptual value. Although existing video generation methods can produce visually appealing content, they predominantl...
AsyncTool: Evaluating the Asynchronous Function Calling Capability under Multi-Task Scenarios
Large language model (LLM)-based agents have shown strong capabilities in using external tools to solve complex tasks. However, existing evaluations often overlook the temporal dim...
Pruning and Distilling Mixture-of-Experts into Dense Language Models
Mixture-of-Experts (MoE) is now the dominant architecture for frontier language models, yet it requires all expert parameters to be loaded in memory, making it less preferable for ...
Which Pretraining Paradigm Better Serves Spatial Intelligence? An Empirical Comparison of Vision-Language and Video Generation Models
Spatial intelligence requires visual representations that capture both semantic objects and geometric structure in the physical world. To support this, two major pre-training schem...
A Matter of TASTE: Improving Coverage and Difficulty of Agent Benchmarks
As agent capabilities advance, existing benchmarks, such as τ^2-Bench, are becoming increasingly saturated. Yet constructing new benchmark tasks remains complex, costly, and labor-...
Frequency-Guided Action Diffusion via Sub-Frequency Manifold Traversal
Learning visuomotor policies via behavior cloning typically involves mimicking expert demonstrations collected by human operators. However, natural human demonstrations inherently ...
Comprehensive Benchmarking of Long-Form Speech Generation in Diverse Scenarios
Recent advances in speech generation have enabled high-fidelity synthesis, yet systematic evaluation of models under long-context conditions remains largely underexplored. A compre...
Models That Know How Evaluations Are Designed Score Safer
The validity of AI safety evaluations depends on models behaving consistently across controlled and deployment settings. Prior work has identified test-time contextual cues, such a...
FRAPPE: Full Input, Residual Output Autoencoding with Projection Pursuit Encoder
Media compression standards have reached a plateau in terms of the rate-distortion-complexity trade-off, limiting the ability to offload expensive AI perception to the cloud in app...
ESC-Skills: Discovering and Self-Evolving Skills for Emotional Support Conversations
Existing emotional support conversation (ESC) systems mainly rely on end-to-end response generation or coarse strategy supervision, offering limited interpretability and little sup...
DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes
Reinforcement learning has become a central paradigm for advancing reasoning in large language models, yet most existing methods still depend on stronger teacher models or heavily ...
Review Arcade: On the Human Alignment and Gameability of LLM Reviews
LLM-generated reviews for scientific papers are gaining considerable traction and are even being officially piloted by major conferences. We have to assume that not only reviewers ...