Related papers: Symphony: A Cognitively-Inspired Multi-Agent Syste…
Modern language agents must operate over long-horizon, multi-turn histories, yet deploying such agents with Small Language Models (SLMs) remains fundamentally difficult. Full-context prompting causes context overflow, flat retrieval exposes…
Document Understanding (DU) in long-contextual scenarios with complex layouts remains a significant challenge in vision-language research. Although Large Vision-Language Models (LVLMs) excel at short-context DU tasks, their performance…
Recent studies have shown that agent-based systems leveraging large language models (LLMs) for key information retrieval and integration have emerged as a promising approach for long video understanding. However, these systems face two…
This paper presents a multi-agent perception-action exploration alliance, dubbed A4VL, for efficient long-video reasoning. A4VL operates in a multi-round perception-action exploration loop with a selection of VLM agents. In each round, the…
Simulation is a crucial tool for accelerating the development of autonomous vehicles. Making simulation realistic requires models of the human road users who interact with such cars. Such models can be obtained by applying learning from…
Multimodal large language models (MLLMs) have shown strong capabilities but remain limited to fixed modality pairs and require costly fine-tuning with large aligned datasets. Building fully omni-capable models that can integrate text,…
We introduce Agentic Reasoning, a framework that enhances large language model (LLM) reasoning by integrating external tool-using agents. Agentic Reasoning dynamically leverages web search, code execution, and structured memory to address…
Vision-language models (VLMs) have shown impressive capabilities in perceptual tasks, yet they degrade in complex multi-hop reasoning under multiplayer game settings with imperfect and deceptive information. In this paper, we study a…
Recent advancements have highlighted that Large Language Models (LLMs) are prone to hallucinations when solving complex reasoning problems, leading to erroneous results. To tackle this issue, researchers incorporate Knowledge Graphs (KGs)…
Large Language Models (LLMs) have revolutionized Natural Language Processing but exhibit limitations, particularly in autonomously addressing novel challenges such as reasoning and problem-solving. Traditional techniques like…
Large Language Models (LLMs) trained with reinforcement learning and verifiable rewards have achieved strong results on complex reasoning tasks. Recent work extends this paradigm to a multi-agent setting, where a meta-thinking agent…
Long video understanding presents significant challenges for vision-language models due to extremely long context windows. Existing solutions relying on naive chunking strategies with retrieval-augmented generation, typically suffer from…
Large language models (LLMs) have advanced in large strides due to the effectiveness of the self-attention mechanism that processes and compares all tokens at once. However, this mechanism comes with a fundamental issue -- the predetermined…
Vision-Language-Action (VLA) models have demonstrated significant potential for embodied decision-making; however, their application in complex chemical laboratory automation remains restricted by limited long-horizon reasoning and the…
Long-form video understanding remains challenging due to the extended temporal structure and dense multimodal cues. Despite recent progress, many existing approaches still rely on hand-crafted reasoning pipelines or employ token-consuming…
The advent of always-on personal AI assistants, enabled by all-day wearable devices such as smart glasses, demands a new level of contextual understanding, one that goes beyond short, isolated events to encompass the continuous,…
Autonomous Vehicles (AVs) have entered the commercialization stage, but their limited ability to interact and express intentions still poses challenges in interactions with Human-driven Vehicles (HVs). Recent advances in large language…
Video agentic models have advanced challenging video-language tasks. However, most agentic approaches still heavily rely on greedy parsing over densely sampled video frames, resulting in high computational cost. We present VideoSeek, a…
Effective human-AI collaboration on complex reasoning tasks requires that users understand and interact with the model's process, not just receive an output. However, the monolithic text from methods like Chain-of-Thought (CoT) prevents…
Recently, to comprehensively improve Vision Language Models (VLMs) for Visual Question Answering (VQA), several methods have been proposed to further reinforce the inference capabilities of VLMs to independently tackle VQA tasks rather than…