相关论文: DenoiseFlow: Uncertainty-Aware Denoising for Relia…
Large language model (LLM) agents have shown remarkable reasoning abilities. However, existing multi-agent frameworks often rely on fixed roles or centralized control, limiting scalability and adaptability in long-horizon reasoning. We…
We propose ReinFlow, a simple yet effective online reinforcement learning (RL) framework that fine-tunes a family of flow matching policies for continuous robotic control. Derived from rigorous RL theory, ReinFlow injects learnable noise…
Understanding the contents of multimodal documents is essential to accurately extract relevant evidence and use it for reasoning. Existing document understanding models tend to generate answers with a single word or phrase directly,…
Modern agents powered by thinking LLMs achieve high accuracy through long chain-of-thought reasoning but incur substantial inference costs. While many LLMs now support configurable reasoning levels (e.g., high/medium/low), static strategies…
Learned classifiers deployed in agentic pipelines face a fundamental reliability problem: predictions are probabilistic inferences, not verified conclusions, and acting on them without grounding in observable evidence leads to compounding…
Long-horizon tasks requiring multi-step reasoning and dynamic re-planning remain challenging for large language models (LLMs). Sequential prompting methods are prone to context drift, loss of goal information, and recurrent failure cycles,…
When humans face problems beyond their immediate capabilities, they rely on tools, providing a promising paradigm for improving visual reasoning in multimodal large language models (MLLMs). Effective reasoning, therefore, hinges on knowing…
Recent advances in reinforcement learning (RL) have strengthened the reasoning capabilities of vision-language models (VLMs). However, enhancing policy exploration to better scale test-time compute remains largely underexplored. In…
Multi-Agentic AI systems, powered by large language models (LLMs), are inherently non-deterministic and prone to silent failures such as drift, cycles, and missing details in outputs, which are difficult to detect. We introduce the task of…
Reasoning is essential for large language models (LLMs), especially in complex tasks such as mathematical problem solving. However, multimodal reasoning still faces challenges in modality alignment and training scalability, as many existing…
The combination of LLM agents with external tools enables models to solve complex tasks beyond their knowledge base. Human-designed tools are inflexible and restricted to solutions within the scope of pre-existing tools created by experts.…
Large Language Models (LLMs) have shown remarkable capabilities in natural language tasks requiring complex reasoning, yet their application in agentic, multi-step reasoning within interactive environments remains a difficult challenge.…
Recent Vision-Language-Action (VLA) models equipped with Flow Matching (FM) action heads achieve state-of-the-art performance in complex robot manipulation. However, the multi-step iterative ODE solving required by FM introduces inference…
Although agentic workflows have demonstrated strong potential for solving complex tasks, existing automated generation methods remain inefficient and underperform, as they rely on predefined operator libraries and homogeneous LLM-only…
Metasurface inverse design has become central to realizing complex optical functionality, yet translating target responses into executable, solver-compatible workflows still demands specialized expertise in computational electromagnetics…
As agentic AI systems increasingly operate autonomously, establishing trust through verifiable evaluation becomes critical. Yet existing benchmarks lack the transparency and auditability needed to assess whether agents behave reliably. We…
Speech monologues recorded in naturalistic settings provide opportunities to characterize mental illness phenomenology and detect symptom exacerbation. Large language models (LLMs) offer new possibilities for automating this process, as…
Analog/mixed-signal circuits are key for interfacing electronics with the physical world. Their design, however, remains a largely handcrafted process, resulting in long and error-prone design cycles. While the recent rise of AI-based…
In recent years, the rapid development of AI systems has brought about the benefits of intelligent services but also concerns about security and reliability. By fostering appropriate user reliance on an AI system, both complementary team…
Recent work on activation and latent steering has demonstrated that modifying internal representations can effectively guide large language models (LLMs) toward improved reasoning and efficiency without additional training. However, most…