相关论文: Evaluating Self-Correcting Vision Agents Through Q…

Vision-language models (VLMs) frequently generate hallucinated content plausible but incorrect claims about image content. We propose a training-free self-correction framework enabling VLMs to iteratively refine responses through…

Vision-Language-Action (VLA) models achieve strong performance in robotic manipulation by leveraging pre-trained vision-language backbones. However, in downstream robotic settings, they are typically fine-tuned with limited data, leading to…

Large language models can translate natural-language chart descriptions into runnable code, yet approximately 15\% of the generated scripts still fail to execute, even after supervised fine-tuning and reinforcement learning. We investigate…

Large Language Model (LLM)-based Multi-Agent Systems (MAS) enable complex problem-solving but introduce significant debugging challenges, characterized by long interaction traces, inter-agent dependencies, and delayed error manifestation.…

Current Vision-Language-Action (VLA) paradigms in autonomous driving primarily rely on Imitation Learning (IL), which introduces inherent challenges such as distribution shift and causal confusion. Online Reinforcement Learning offers a…

Vision-language-action models must enable agents to execute long-horizon tasks under partial observability. However, most existing approaches remain observation-driven, relying on short context windows or repeated queries to vision-language…

Register-Transfer Level (RTL) verification is a primary bottleneck, consuming 60-70% of development time. While Large Language Models (LLMs) show promise for RTL automation, their performance and research focus have overwhelmingly centered…

Recent advances in Multimodal Large Language Models (MLLMs) have significantly improved performance on tasks such as visual grounding and visual question answering. However, the reasoning processes of these models remain largely opaque;…

Recursive self-improvement--where a model iteratively trains on its own outputs--promises sustained capability growth but faces a fundamental obstacle: recursive drift. As models train on self-generated data across multiple iterations,…

Uncertainty quantification is essential for assessing the reliability and trustworthiness of modern AI systems. Among existing approaches, verbalized uncertainty, where models express their confidence through natural language, has emerged…

Current research on Vision-Language-Action (VLA) models predominantly focuses on enhancing generalization through established reasoning techniques. While effective, these improvements invariably increase computational complexity and…

Current multimodal models often suffer from shallow reasoning, leading to errors caused by incomplete or inconsistent thought processes. To address this limitation, we propose Self-Verification and Self-Rectification (SVSR), a unified…

Evaluating vision-language models (VLMs) in urban driving contexts remains challenging, as existing benchmarks rely on open-ended responses that are ambiguous, annotation-intensive, and inconsistent to score. This lack of standardized…

Post-training with explicit reasoning traces is common to improve the reasoning capabilities of Multimodal Large Language Models (MLLMs). However, acquiring high-quality reasoning traces is often costly and time-consuming. Hence, the…

Reliability and failure detection of large language models (LLMs) is critical for their deployment in high-stakes, multi-step reasoning tasks. Prior work explores confidence estimation for self-evaluating LLM-scorer systems, with confidence…

Vision-language-action models (VLAs) have been extensively used in robotics applications, achieving great success in various manipulation problems. More recently, VLAs have been used in long-horizon tasks and evaluated on benchmarks, such…

The use of Vision-Language Models (VLMs) in automated driving applications is becoming increasingly common, with the aim of leveraging their reasoning and generalisation capabilities to handle long tail scenarios. However, these models…

Multimodal Large Language Models (MLLMs) have achieved significant advances in integrating visual and linguistic information, yet their ability to reason about complex and real-world scenarios remains limited. The existing benchmarks are…

Deploying small language models (7-9B parameters) as autonomous agents requires trust in their reasoning, not just their outputs. We reveal a critical reliability crisis: 50-69\% of correct answers from these models contain fundamentally…

Multi-round incomplete information tasks are crucial for evaluating the lateral thinking capabilities of large language models (LLMs). Currently, research primarily relies on multiple benchmarks and automated evaluation metrics to assess…