Related papers: When Agents Disagree: The Selection Bottleneck in …

Multi-Agent Systems (MAS) with Large Language Model (LLM)-powered agents are gaining attention, yet fewer studies explore their team dynamics. Inspired by human team science, we propose a multi-agent framework to examine core aspects of…

Multi-agent systems where Large Language Models (LLMs) deliberate to form consensus have gained significant attention, yet their practical value over simpler methods remains under-scrutinized. We introduce DELIBERATIONBENCH, a controlled…

In this paper, we introduce a high-level controller synthesis framework that enables teams of heterogeneous agents to assist each other in resolving environmental conflicts that appear at runtime. This conflict resolution method is built…

Topology optimization can generate efficient structures, but designers often must manually translate qualitative intent, such as desired visual style, product experience, or manufacturability into solver settings that are not directly tied…

Supply networks require collaboration in a competitive environment. To achieve this, nodes in the network often form symbiotic relationships as they can be adversely effected by the closure of companies in the network, especially where…

Producing high-quality code across multiple programming languages is increasingly important as today's software systems are built on heterogeneous stacks. Large language models (LLMs) have advanced the state of automated programming, yet…

Recent Large Language Model (LLM)-based AutoML systems demonstrate impressive capabilities but face significant limitations such as constrained exploration strategies and a severe execution bottleneck. Exploration is hindered by one-shot…

Large language models applied to clinical prediction exhibit case-level heterogeneity: simple cases yield consistent outputs, while complex cases produce divergent predictions under minor prompt changes. Existing single-agent strategies…

Multi-AI collaboration, such as ensembling or debating large language models (LLMs), is a promising paradigm for aggregating information and boosting performance. A foundational step in these pipelines is to feed the responses of several…

In many real-world systems, such as adaptive robotics, achieving a single, optimised solution may be insufficient. Instead, a diverse set of high-performing solutions is often required to adapt to varying contexts and requirements. This is…

We consider multi-agent systems where agents' preferences are aggregated via sequential majority voting: each decision is taken by performing a sequence of pairwise comparisons where each comparison is a weighted majority vote among the…

Emerging AI systems in behavioral health and psychiatry use multi-step or multi-agent LLM pipelines for tasks like assessing self-harm risk and screening for depression. However, common evaluation approaches, like LLM-as-a-judge, do not…

Multi-agent systems (MAS) are increasingly used for open-ended idea generation, driven by the expectation that collective interaction will broaden the exploration diversity. However, when and why such collaboration truly expands the…

Model ensemble is a useful approach in reinforcement learning (RL) for training effective agents. Despite wide success of RL, training effective agents remains difficult due to the multitude of factors requiring careful tuning, such as…

We present ActuBench, a multi-agent LLM pipeline for the automated generation and evaluation of advanced actuarial assessment items aligned with the International Actuarial Association (IAA) Education Syllabus. The pipeline separates four…

LLMs generate buggy code: 29.6% of SWE-bench solved patches fail, 62% of BaxBench solutions have vulnerabilities, and existing tools only catch 65% of bugs with 35% false positives. We built CodeX-Verify, a multi-agent system that uses four…

Recent studies show that LLMs possess different skills and specialize in different tasks. In fact, we observe that their varied performance occur in several levels of granularity. For example, in the code optimization task, code LLMs excel…

Multi-agent LLM committees replicate the same model under different role prompts and aggregate outputs by majority vote, implicitly assuming that agents contribute complementary evidence. We embed each agent's chain-of-thought rationale and…

Mixture-of-Agents (MoA) inference can suffer from dense inter-agent communication and low hardware utilization, which jointly inflate serving latency. We present a serving design that targets these bottlenecks through an algorithm-system…

While AI agents show potential in scientific ideation, most existing frameworks rely on single-agent refinement, limiting creativity due to bounded knowledge and perspective. Inspired by real-world research dynamics, this paper investigates…