相关论文: AdaReasoner: Dynamic Tool Orchestration for Iterat…

Learning general-purpose reasoning capabilities has long been a challenging problem in AI. Recent research in large language models (LLMs), such as DeepSeek-R1, has shown that reinforcement learning techniques like GRPO can enable…

Humans intuitively solve complex problems by flexibly shifting among reasoning modes: they plan, execute, revise intermediate goals, resolve ambiguity through associative judgment, and apply formal procedures to well-specified subproblems.…

Recent research on Large Language Models (LLMs) has led to remarkable advancements in general NLP AI assistants. Some studies have further explored the use of LLMs for planning and invoking models or APIs to address more general multi-modal…

Agentic reinforcement learning has advanced large language models (LLMs) to reason through long chain-of-thought trajectories while interleaving external tool use. Existing approaches assume a fixed inventory of tools, limiting LLM agents'…

Visual reasoning (VR), which is crucial in many fields for enabling human-like visual understanding, remains highly challenging. Recently, compositional visual reasoning approaches, which leverage the reasoning abilities of large language…

Rule-based reasoning is acknowledged as one of the fundamental problems of reasoning. While recent studies show that large reasoning models (LRMs) have remarkable reasoning capabilities enhanced by reinforcement learning (RL), real…

Multimodal Large Language Models (MLLMs) achieve stronger visual understanding by scaling input fidelity, yet the resulting visual token growth makes jointly sustaining high spatial resolution and long temporal context prohibitive. We argue…

Recent advances in Multimodal Large Language Models (MLLMs) have significantly improved 2D visual understanding, prompting interest in their application to complex 3D reasoning tasks. However, it remains unclear whether these models can…

Recently, long-thought reasoning models achieve strong performance on complex reasoning tasks, but often incur substantial inference overhead, making efficiency a critical concern. Our empirical analysis reveals that the benefit of using…

Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in vision-language answering tasks. Despite their strengths, these models often encounter challenges in achieving complex reasoning tasks such as…

Data-driven approaches for autonomous driving (AD) have been widely adopted in the past decade but are confronted with dataset bias and uninterpretability. Inspired by the knowledge-driven nature of human driving, recent approaches explore…

Large Language Models (LLMs) have demonstrated strong reasoning capabilities in solving complex problems. However, current approaches primarily enhance reasoning through the elaboration of thoughts while neglecting the diversity of…

Large Language Models (LLMs) demonstrate impressive ability in handling reasoning tasks. However, unlike humans who can instinctively adapt their problem-solving strategies to the complexity of task, most LLM-based methods adopt a…

We present a framework for optimizing prompts in vision-language models to elicit multimodal reasoning without model retraining. Using an evolutionary algorithm to guide prompt updates downstream of visual tasks, our approach improves upon…

Large reasoning models have demonstrated strong problem-solving abilities, yet real-world tasks often require external tools and long-horizon interactions. Existing agent frameworks typically follow predefined workflows, which limit…

Although Reinforcement Learning (RL) agents are effective in well-defined environments, they often struggle to generalize their learned policies to dynamic settings due to their reliance on trial-and-error interactions. Recent work has…

The video reasoning ability of multimodal large language models (MLLMs) is crucial for downstream tasks like video question answering and temporal grounding. While recent approaches have explored text-based chain-of-thought (CoT) reasoning…

Effective social intelligence simulation requires language agents to dynamically adjust reasoning depth, a capability notably absent in current studies. Existing methods either lack explicit reasoning or employ lengthy Chain-of-Thought…

When designing robots to assist in everyday human activities, it is crucial to enhance user requests with visual cues from their surroundings for improved intent understanding. This process is defined as a multimodal classification task.…

Augmented Language Models (ALMs) blend the reasoning capabilities of Large Language Models (LLMs) with tools that allow for knowledge retrieval and action execution. Existing ALM systems trigger LLM thought processes while pulling…