Related papers: FutureWeaver: Planning Test-Time Compute for Multi…

Test-time scaling has become a powerful way to improve large language models. However, existing methods are best suited to short, bounded outputs that can be directly compared, ranked or refined. Long-horizon coding agents violate this…

We propose a new multi-agent task grammar to encode collaborative tasks for a team of heterogeneous agents that can have overlapping capabilities. The grammar allows users to specify the relationship between agents and parts of the task…

Scaling test-time computation improves performance across different tasks on large language models (LLMs), which has also been extended to tool-augmented agents. For these agents, scaling involves not only "thinking" in tokens but also…

The rapid development of large language model (LLM)-based agents has unlocked new possibilities for autonomous multi-turn reasoning and tool-augmented decision-making. However, their real-world deployment is hindered by severe…

Large language models are increasingly deployed as complex agentic systems that scale with task complexity. While prior work has extensively explored model- and system-level scaling, algorithm- and task-level scaling remain largely…

In recent research advancements within the community, large language models (LLMs) have sparked great interest in creating autonomous agents. However, current prompt-based agents often heavily rely on large-scale LLMs. Meanwhile, although…

We investigate the problem of co-designing computation and communication in a multi-agent system (e.g. a sensor network or a multi-robot team). We consider the realistic setting where each agent acquires sensor data and is capable of local…

In most multiagent applications, communication is essential among agents to coordinate their actions, and thus achieve their goal. However, communication often has a related cost that affects overall system performance. In this paper, we…

Large Language Model (LLM) based multi-agent systems (MAS) have shown promise in tackling complex tasks, but often rely on predefined roles and centralized coordination, limiting their adaptability to evolving challenges. This paper…

Large language model (LLM) agents have shown increasing promise for collaborative task completion. However, existing multi-agent frameworks often rely on static workflows, fixed roles, and limited inter-agent communication, reducing their…

One of the key challenges for multi-agent learning is scalability. In this paper, we introduce a technique for speeding up multi-agent learning by exploiting concurrent and incremental experience sharing. This solution adaptively identifies…

Multi-agent systems (MAS) built on large language models (LLMs) offer a promising path toward solving complex, real-world tasks that single-agent systems often struggle to manage. While recent advancements in test-time scaling (TTS) have…

Multi-agent systems have demonstrated exceptional performance in downstream tasks beyond diverse single agent baselines. A growing body of work has explored ways to improve their reasoning and collaboration, from vote, debate, to complex…

We argue that multi-agent test-time evolution is not single-agent evolution replicated N times. A single-agent learner can only evolve its own context and memory. A multi-agent system additionally evolves who collaborates, how they…

Recent agent frameworks and inference-time algorithms often struggle with complex planning problems due to limitations in verifying generated plans or reasoning and varying complexity of instances within a single task. Many existing methods…

Recent breakthroughs in large language model-driven autonomous agents have revealed that multi-agent collaboration often surpasses each individual through collective reasoning. Inspired by the neural scaling law--increasing neurons enhances…

Advances in inference methods have enabled language models to improve their predictions without additional training. These methods often prioritize raw performance over cost-effective compute usage. However, computational efficiency is key…

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;…

Research concerning organization and coordination within multi-agent systems continues to draw from a variety of architectures and methodologies. The work presented in this paper combines techniques from game theory and multi-agent systems…

Current evaluations of agents remain centered around one-shot task completion, failing to account for the inherently iterative and collaborative nature of many real-world problems, where human goals are often underspecified and evolve. We…