Related papers: MobileIPL: Enhancing Mobile Agents Thinking Proces…

This paper introduces the "GPT-in-the-loop" approach, a novel method combining the advanced reasoning capabilities of Large Language Models (LLMs) like Generative Pre-trained Transformers (GPT) with multiagent (MAS) systems. Venturing…

Mathematical problem solving is a fundamental benchmark for assessing the reasoning capabilities of artificial intelligence and a gateway to applications in education, science, and engineering where reliable symbolic reasoning is essential.…

Preference-based reinforcement learning is an effective way to handle tasks where rewards are hard to specify but can be exceedingly inefficient as preference learning is often tabula rasa. We demonstrate that Large Language Models (LLMs)…

Building general-purpose graphical user interface (GUI) agents has become increasingly promising with the progress in vision language models. However, developing effective mobile GUI agents with reinforcement learning (RL) remains…

Large language models (LLMs) can achieve highly effective performance on various reasoning tasks by incorporating step-by-step chain-of-thought (CoT) prompting as demonstrations. However, the reasoning chains of demonstrations generated by…

Reward functions are difficult to design and often hard to align with human intent. Preference-based Reinforcement Learning (RL) algorithms address these problems by learning reward functions from human feedback. However, the majority of…

User modeling in large e-commerce platforms aims to optimize user experiences by incorporating various customer activities. Traditional models targeting a single task often focus on specific business metrics, neglecting the comprehensive…

Accurate short-term mobile traffic prediction is important for proactive resource allocation and low-latency network management in fifth generation (5G) and sixth generation (6G). While large language models (LLMs) can perform in-context…

Exploration efficiency is a challenging problem in multi-agent reinforcement learning (MARL), as the policy learned by confederate MARL depends on the collaborative approach among multiple agents. Another important problem is the less…

Information-seeking is a core capability for AI agents, requiring them to gather and reason over tool-generated information across long trajectories. However, such multi-step information-seeking tasks remain challenging for agents backed by…

Vision-language model-based mobile agents have gained the ability to understand complex instructions and mobile screenshots, benefiting from reinforcement learning paradigms like Group Relative Policy Optimization (GRPO). However, existing…

Recent advancements in Multimodal Large Language Models (MLLMs) have incentivized models to ``think with images'' by actively invoking visual tools during multi-turn reasoning. The common Reinforcement Learning (RL) practice of relying on…

Mobile graphical user interface (GUI) agents are designed to automate everyday tasks on smartphones. Recent advances in large language models (LLMs) have significantly enhanced the capabilities of mobile GUI agents. However, most…

We introduce a novel large language model (LLM)-driven agent framework, which iteratively refines queries and filters contextual evidence by leveraging dynamically evolving knowledge. A defining feature of the system is its decoupling of…

The problem of path planning has been studied for years. Classic planning pipelines, including perception, mapping, and path searching, can result in latency and compounding errors between modules. While recent studies have demonstrated the…

Existing multi-agent learning approaches have developed interactive training environments to explicitly promote collaboration among multiple Large Language Models (LLMs), thereby constructing stronger multi-agent systems (MAS). However,…

Distributed Multi-Agent Path Finding (MAPF) integrated with Multi-Agent Reinforcement Learning (MARL) has emerged as a prominent research focus, enabling real-time cooperative decision-making in partially observable environments through…

The rapid advancement of large vision language models (LVLMs) and agent systems has heightened interest in mobile GUI agents that can reliably translate natural language into interface operations. Existing single-agent approaches, however,…

Multi-tool-integrated reasoning enables LLM-empowered tool-use agents to solve complex tasks by interleaving natural-language reasoning with calls to external tools. However, training such agents from outcome-only rewards suffers from…

Recent advances in reinforcement learning (RL) have significantly enhanced the agentic capabilities of large language models (LLMs). In long-term and multi-turn agent tasks, existing approaches driven solely by outcome rewards often suffer…