相关论文: The Observer-Situation Lattice: A Unified Formal B…

Large Language Models (LLMs) perform well on many language tasks, but their Theory of Mind (ToM) reasoning is still uneven in complex social settings. Existing benchmarks, including ExploreToM, do not always test the recursive beliefs and…

We present an interactive framework for evaluating whether large language models (LLMs) exhibit genuine "understanding" in a simple yet strategic environment. As a running example, we focus on Rock-Paper-Scissors (RPS), which, despite its…

Large language models can consult information that fixed static analyzers cannot, such as documentation, current security advisories, version-specific metadata, and informal API contracts. This makes LLMs a compelling option for program…

Data within a specific context gains deeper significance beyond its isolated interpretation. In distributed systems, interdependent data sources reveal hidden relationships and latent structures, representing valuable information for many…

Large Vision-Language Models (LVLMs) have achieved remarkable success but continue to struggle with object hallucination (OH), generating outputs inconsistent with visual inputs. While previous work has proposed methods to reduce OH, the…

This paper introduces OSC (Orchestrating Cognitive Synergy), a knowledge-aware adaptive collaboration framework designed to enhance cognitive synergy in multi-agent systems with large language models. While prior work has advanced agent…

Spatial reasoning, the ability to ground language in 3D understanding, remains a persistent challenge for Vision-Language Models (VLMs). We identify two fundamental bottlenecks: inadequate 3D understanding capabilities stemming from…

Large language models (LLMs) are increasingly integrated into autonomous systems, giving rise to a new class of software known as Agentware, where LLM-powered agents perform complex, open-ended tasks in domains such as software engineering,…

The importance of taking individual, potentially conflicting perspectives into account when dealing with knowledge has been widely recognised. Many existing ontology management approaches fully merge knowledge perspectives, which may…

We abstract the core logical functions from applications that require ultra-low-latency wireless communications to provide a novel definition for reliability. Real-time applications -- such as intelligent transportation, remote surgery, and…

Large language models (LLMs) are increasingly deployed on long-horizon tasks in partially observable environments, where they must act while inferring and tracking a complex environment state over many steps. This leads to two challenges:…

Multimodal large language models (MLLMs) show promise in tasks like visual question answering (VQA) but still face challenges in multimodal reasoning. Recent works adapt agentic frameworks or chain-of-thought (CoT) reasoning to improve…

One-shot Imitation Learning~(OSIL) aims to imbue AI agents with the ability to learn a new task from a single demonstration. To supervise the learning, OSIL typically requires a prohibitively large number of paired expert demonstrations --…

Vision-Language Models (VLMs) have achieved remarkable progress in integrating visual perception with language understanding. However, effective multimodal reasoning requires both accurate perception and robust reasoning, and weakness in…

Joint audio-visual reasoning is essential for omnimodal understanding, yet current multimodal large language models (MLLMs) still struggle when reasoning requires fine-grained evidence from both modalities. A central limitation is that…

Object-centric learning (OCL) aspires general and compositional understanding of scenes by representing a scene as a collection of object-centric representations. OCL has also been extended to multi-view image and video datasets to apply…

The integration of large language models (LLMs) with embodied agents has improved high-level reasoning capabilities; however, a critical gap remains between semantic understanding and physical execution. While vision-language-action (VLA)…

This paper introduces KOS-TL (Knowledge Operation System Type Logic), a novel constructive framework designed to provide a rigorous logical foundation for autonomous and executable knowledge systems. Traditional knowledge representation…

Vision-Language-Action (VLA) models have emerged as a promising paradigm for general-purpose robotic control, with test-time scaling (TTS) gaining attention to enhance robustness beyond training. However, existing TTS methods for VLAs…

Monitoring autonomous large language model (LLM) agents for covert malicious behavior is challenging due to delayed, context-dependent, and long-horizon attack patterns. Agents may pursue hidden objectives while maintaining superficially…