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

Recent advances in Large Language Model Multi-Agent Systems enable scalable orchestration and retrieval of specialized, parallelized subagents, each equipped with hundreds or thousands of Model Context Protocol (MCP) servers and tools.…

For agentic systems to use external tools to solve complex, long-horizon tasks, we need a large set of diverse and controllable tool-use environments. We introduce SynthTools, a fully LLM-based pipeline spanning the entire lifecycle:…

Single-agent systems (SAS) have become the default pattern for LLM-driven scientific workflows, but routing planning, tool use, and synthesis through a single context window comes with a well-known cost: as tool specifications and…

Large Language Models (LLMs) increasingly rely on agentic capabilities-iterative retrieval, tool use, and decision-making-to overcome the limits of static, parametric knowledge. Yet existing agentic frameworks treat external information as…

Recently, large language models (LLMs) have demonstrated remarkable problem-solving capabilities by autonomously integrating with external tools for collaborative reasoning. However, due to the inherently complex and diverse nature of…

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…

Skill libraries enable large language model agents to reuse experience from past interactions, but most existing libraries store skills as isolated entries and retrieve them only by semantic similarity. This leads to two key challenges for…

Tool-using LLM agents face a reliability-cost tradeoff: routing every decision through the LLM improves correctness but incurs high latency and inference cost, while pre-coded workflow graphs reduce cost but become brittle under…

Advancements in Large Language Models (LLMs) are revolutionizing the development of autonomous agentic systems by enabling dynamic, context-aware task decomposition and automated tool selection. These sophisticated systems possess…

LLM-powered coding agents, which operate in iterative loops (turns) to solve software engineering tasks, are becoming increasingly powerful. However, their practical deployment is hindered by significant and unpredictable costs. This…

Recent advancements in large language models (LLMs) have enabled significant progress in decision-making and task planning for embodied autonomous agents. However, most existing methods struggle with complex, long-horizon tasks because they…

Large Language Models (LLMs) have shown remarkable capabilities as autonomous agents, yet existing benchmarks either focus on single-agent tasks or are confined to narrow domains, failing to capture the dynamics of multi-agent coordination…

Multi-agent systems built on large language models (LLMs) require many coordination choices that are difficult to fix a priori: which skill protocol to invoke, which agent role should perform a subtask, which model to bind to each role, how…

Recent mechanistic studies suggest that large language models (LLMs) may utilize their depth inefficiently in standard single-turn tasks. Whether this still holds in autonomous agent settings, where models must perform multi-turn planning,…

Existing benchmarks for tool-augmented language models (TaLMs) lack fine-grained control over task difficulty and remain vulnerable to data contamination. We present FuncBenchGen, a unified, contamination-free framework that evaluates TaLMs…

Large language models (LLMs) are increasingly used to complete complex tasks by selecting and coordinating external tools across multiple steps. This requires aligning tool choices with subtask intent while satisfying directional execution…

As multimodal large language models (MLLMs) advance, MLLM-based virtual agents have demonstrated remarkable performance. However, existing benchmarks face significant limitations, including uncontrollable task complexity, extensive manual…

Large Language Models (LLMs) have demonstrated exceptional abilities in reasoning for task planning. However, challenges remain under-explored for parallel schedules. This paper introduces a novel paradigm, plan-over-graph, in which the…

Real-world tool-using agents operate over long-horizon workflows with recurring structure and diverse demands, where effective behavior requires not only invoking atomic tools but also abstracting, and reusing higher-level tool…

Large Language Model (LLM)-empowered multi-agent systems extend the cognitive boundaries of individual agents through disciplined collaboration and interaction, while constructing these systems often requires labor-intensive manual designs.…