Related papers: Complete Cyclic Subtask Graphs for Tool-Using LLM …

As agentic AI becomes more widespread, agents with distinct and possibly conflicting goals will interact in complex ways. These multi-agent interactions pose a fundamental challenge, particularly in social dilemmas, where agents' individual…

The real world is awash with multi-agent problems that require collective action by self-interested agents, from the routing of packets across a computer network to the management of irrigation systems. Such systems have local incentives…

Graph Retrieval-Augmented Generation (GraphRAG) enhances factual reasoning in LLMs by structurally modeling knowledge through graph-based representations. However, existing GraphRAG approaches face two core limitations: shallow retrieval…

Retrieval-Augmented Generation (RAG) mitigates hallucination in LLMs by incorporating external knowledge, but relies on chunk-based retrieval that lacks structural semantics. GraphRAG methods improve RAG by modeling knowledge as…

LLM agents excel when environments are mostly static and the needed information fits in a model's context window, but they often fail in open-ended investigations where explanations must be constructed by iteratively mining evidence from…

The emergence of Large Language Models (LLMs) like ChatGPT has inspired the development of LLM-based agents capable of addressing complex, real-world tasks. However, these agents often struggle during task execution due to methodological…

Large language models (LLMs) have demonstrated remarkable potential in solving complex tasks across diverse domains, typically by employing agentic workflows that follow detailed instructions and operational sequences. However, constructing…

We introduce a framework to study the effective objectives at different time scales of financial market microstructure. The financial market can be regarded as a complex adaptive system, where purposeful agents collectively and…

The integration of large language models (LLMs) with external tools has significantly expanded the capabilities of AI agents. However, as the diversity of both LLMs and tools increases, selecting the optimal model-tool combination becomes a…

Financial report generation tasks range from macro- to micro-economics analysis, also requiring extensive data analysis. Existing LLM models are usually fine-tuned on simple QA tasks and cannot comprehensively analyze real financial…

Large Language Models (LLMs) have significantly advanced tool-augmented agents, enabling autonomous reasoning via API interactions. However, executing multi-step tasks within massive tool libraries remains challenging due to two critical…

Text-to-image models like stable diffusion and DALLE-3 still struggle with multi-turn image editing. We decompose such a task as an agentic workflow (path) of tool use that addresses a sequence of subtasks by AI tools of varying costs.…

This benchmark suite provides a comprehensive evaluation framework for assessing both individual LLMs and multi-agent systems in Real-world planning and scheduling scenarios. The suite encompasses 14 designed planning and scheduling…

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…

Contemporary multi-agent systems encounter persistent challenges in cross-platform interoperability, dynamic task scheduling, and efficient resource sharing. Agents with heterogeneous implementations often lack standardized interfaces;…

In this paper, we aim to evaluate multi-agent systems against complex dependencies, including spatial, causal, and temporal constraints. First, we construct a new benchmark, named VillagerBench, within the Minecraft…

We present Plancraft, a multi-modal evaluation dataset for LLM agents. Plancraft has both a text-only and multi-modal interface, based on the Minecraft crafting GUI. We include the Minecraft Wiki to evaluate tool use and Retrieval Augmented…

Recent advances in large language model-powered multi-agent systems have demonstrated remarkable collective intelligence through effective communication. However, existing approaches face two primary challenges: (i) \textit{Ineffective…

Training large language models (LLMs) to reason via reinforcement learning (RL) significantly improves their problem-solving capabilities. In agentic settings, existing methods like ReAct prompt LLMs to explicitly plan before every action;…

Designing effective collaboration structure for multi-agent LLM systems to enhance collective reasoning is crucial yet remains under-explored. In this paper, we systematically investigate how collaborative reasoning performance is affected…