Related papers: Mixture-of-Minds: Multi-Agent Reinforcement Learni…

Feature transformation enhances downstream task performance by generating informative features through mathematical feature crossing. Despite the advancements in deep learning, feature transformation remains essential for structured data,…

Recent advances in Large Language Models (LLMs) demonstrate that chain-of-thought prompting and deep reasoning substantially enhance performance on complex tasks, and multi-agent systems can further improve accuracy by enabling model…

Multi-agent systems (MAS) extend large language models (LLMs) from independent single-model reasoning to coordinative system-level intelligence. While existing LLM agents depend on text-based mediation for reasoning and communication, we…

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 consider the problem of multi-task reasoning (MTR), where an agent can solve multiple tasks via (first-order) logic reasoning. This capability is essential for human-like intelligence due to its strong generalizability and simplicity for…

Developing Large Language Models (LLMs) to cooperate and compete effectively within multi-agent systems (MASs) is a critical step towards more advanced intelligence. While reinforcement learning (RL) has proven effective for enhancing…

Model ensemble is a useful approach in reinforcement learning (RL) for training effective agents. Despite wide success of RL, training effective agents remains difficult due to the multitude of factors requiring careful tuning, such as…

Reasoning in a complex and ambiguous environment is a key goal for Reinforcement Learning (RL) agents. While some sophisticated RL agents can successfully solve difficult tasks, they require a large amount of training data and often…

Multi-agent systems (MAS) have shown great potential in executing complex tasks, but coordination and safety remain significant challenges. Multi-Agent Reinforcement Learning (MARL) offers a promising framework for agent collaboration, but…

Remarkable performance of large language models (LLMs) in a variety of tasks brings forth many opportunities as well as challenges of utilizing them in production settings. Towards practical adoption of LLMs, multi-agent systems hold great…

Making sophisticated, robust, and safe sequential decisions is at the heart of intelligent systems. This is especially critical for planning in complex multi-agent environments, where agents need to anticipate other agents' intentions and…

Recent advances in reinforcement learning (RL) have substantially improved the training of large-scale language models, leading to significant gains in generation quality and reasoning ability. However, most existing research focuses on…

Multi-agent reinforcement learning shines as the pinnacle of multi-agent systems, conquering intricate real-world challenges, fostering collaboration and coordination among agents, and unleashing the potential for intelligent…

We present a controlled study of multi-hop contextual reasoning in large language models, providing a clean demonstration of the task-method dissociation: rule-based pattern matching achieves 100% success on structured information retrieval…

Table reasoning (TR) requires structured reasoning over semi-structured tabular data and remains challenging, particularly for small language models (SLMs, e.g., LLaMA-8B) due to their limited capacity compared to large LMs (LLMs, e.g.,…

The rise of Large Reasoning Models (LRMs) signifies a paradigm shift toward advanced computational reasoning. Yet, this progress disrupts traditional agent frameworks, traditionally anchored by execution-oriented Large Language Models…

Multilingual reasoning remains a significant challenge for large language models (LLMs), with performance disproportionately favoring high-resource languages. Drawing inspiration from cognitive neuroscience, which suggests that human…

Large language models (LLMs) excel in complex tasks through advanced prompting techniques like Chain-of-Thought (CoT) and Tree-of-Thought (ToT), but their reliance on manually crafted, task-specific prompts limits adaptability and…

Real-world multimodal applications often require any-to-any capabilities, enabling both understanding and generation across modalities including text, image, audio, and video. However, integrating the strengths of autoregressive language…

A key method for creating Artificial Intelligence (AI) agents is Reinforcement Learning (RL). However, constructing a standalone RL policy that maps perception to action directly encounters severe problems, chief among them being its lack…