Related papers: Shepherd: A Runtime Substrate Empowering Meta-Agen…

With the increasing adoption of large language models (LLM), agentic workflows, which compose multiple LLM calls with tools, retrieval, and reasoning steps, are increasingly replacing traditional applications. However, such workflows are…

Agents powered by large language models have shown remarkable abilities in solving complex tasks. However, most agent systems remain reactive, limiting their effectiveness in scenarios requiring foresight and autonomous decision-making. In…

Teams of LLM agents increasingly collaborate on tasks spanning days or weeks: multi-day data-generation sprints where generator, reviewer, and auditor agents coordinate in real time on overlapping batches; specialists carrying findings…

Despite the promise of autonomous agentic reasoning, existing workflow generation methods frequently produce fragile, unexecutable plans due to unconstrained LLM-driven construction. We introduce MermaidFlow, a framework that redefines the…

Remarkable progress has been made on automated problem solving through societies of agents based on large language models (LLMs). Existing LLM-based multi-agent systems can already solve simple dialogue tasks. Solutions to more complex…

Large Language Models (LLMs) deployed in agentic environments must exercise multiple capabilities across different task instances, where a capability is performing one or more actions in a trajectory that are necessary for successfully…

Agent skills today are static artifact: authored once -- by human curation or one-shot generation from parametric knowledge -- and then consumed unchanged, with no mechanism to improve from real use. We propose \textbf{SkillEvolver}, a…

LLM-based multi-agent systems (MAS) have emerged as an effective paradigm for complex and long-horizon tasks. However, in real-world tasks, MAS often exhibit various failures during execution and such failures are difficult to eliminate…

Recent advances in large language models (LLMs) have enabled a new generation of autonomous agents that operate over sustained periods and manage sensitive resources on behalf of users. Trusted for their ability to act without direct…

In recent years, agentic workflows have been widely applied to solve complex human tasks. However, existing workflow construction still faces key challenges, including human-dependent workflow construction, the lack of graph-level execution…

Equipping LLMs with tool-use capabilities via Agentic Reinforcement Learning (Agentic RL) is bottlenecked by two challenges: the lack of scalable, robust execution environments and the scarcity of realistic training data that captures…

Embodied agents face significant challenges when tasked with performing actions in diverse environments, particularly in generalizing across object types and executing suitable actions to accomplish tasks. Furthermore, agents should exhibit…

Pre-trained and frozen large language models (LLMs) can effectively map simple scene rearrangement instructions to programs over a robot's visuomotor functions through appropriate few-shot example prompting. To parse open-domain natural…

Frontier LLMs can navigate complex websites, but their cost and reliance on third-party APIs make local deployment impractical. We introduce Agent-as-Annotators, a framework that structures synthetic trajectory generation for web agents by…

We study how a principal can efficiently and effectively intervene on the rewards of a previously unseen learning agent in order to induce desirable outcomes. This is relevant to many real-world settings like auctions or taxation, where the…

Autonomous agents, which perceive environments and take actions to achieve goals, have become increasingly feasible with the advancements in large language models (LLMs). However, current powerful agents often depend on sophisticated prompt…

Recent advances in LLM Multi-Agent Systems enable scalable orchestration of sub-agents, each coordinating hundreds or thousands of tools or Model Context Protocol (MCP) servers. However, existing retrieval methods typically match queries…

We introduce a new approach to agent programming, the development of LLM-based agents. Current approaches to agent programming often entangle two aspects of agent design: the core workflow logic and the inference-time strategy (e.g., tree…

Agentic evolution has emerged as a powerful paradigm for improving programs, workflows, and scientific solutions by iteratively generating candidates, evaluating them, and using feedback to guide future search. However, existing methods are…

Recent advancements in Large Language Models (LLMs) have spurred interest in deploying LLM agents to undertake tasks in the world. LLMs are often deployed in agent systems: code that orchestrates LLM calls and provides them with tools. We…