Related papers: Coordination as an Architectural Layer for LLM-Bas…
LLM-based agents for industrial asset operations show limited accuracy when reasoning over flat document stores. AssetOpsBench (KDD 2026) establishes that GPT-4 agents achieve 65% on 139 industrial maintenance scenarios backed by CouchDB,…
As Large Language Models (LLMs) evolve into autonomous agents, existing safety evaluations face a fundamental trade-off: manual benchmarks are costly, while LLM-based simulators are scalable but suffer from logic hallucination. We present…
AI-enabled Security Orchestration, Automation, and Response (SOAR) systems increasingly employ autonomous agents for cyber defense, yet their resilience to adaptive adversaries is underexplored. We introduce an autonomous red teaming…
Multi-agent LLM systems consistently outperform single-agent baselines, yet practitioners still cannot predict which design works for a new task or diagnose why one fails. We argue this gap persists largely because the field lacks a…
As LLM agents evolve into collaborative multi-agent systems, their memory requirements grow rapidly in complexity. This position paper frames multi-agent memory as a computer architecture problem. We distinguish shared and distributed…
Enhancing the reasoning capabilities of large language models (LLMs) is crucial for enabling them to tackle complex, multi-step problems. Multi-agent frameworks have shown great potential in enhancing LLMs' reasoning capabilities. However,…
As Language Models (LMs) increasingly operate as autonomous agents, accurately forecasting their capabilities becomes crucial for societal preparedness. We evaluate six forecasting methods that predict downstream capabilities of LM agents.…
Organisations are starting to adopt LLM-based AI agents, with their deployments naturally evolving from single agents towards interconnected, multi-agent networks. Yet a collection of safe agents does not guarantee a safe collection of…
We argue that LLM agent security is fundamentally an agent-human interaction (AHI) problem, not a purely algorithmic one. To substantiate this position, we conduct a systematic analysis of 59 academic papers, 21 production agent systems,…
A persistent challenge in machine learning for scientific applications is jointly achieving prediction and understanding. Statistical models excel on structured data but operate as black boxes, while existing interpretability methods are…
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…
Embedding LLM-driven agents into environmental FAIR data management is compelling - they can externalize operational knowledge and scale curation across heterogeneous data and evolving conventions. However, replacing deterministic…
Multi-agent LLM systems are increasingly used to solve complex tasks through decomposition, debate, specialization, and ensemble reasoning. However, these systems are usually evaluated in terms of robustness: whether performance is…
Ramp merging is one of the bottlenecks in traffic systems, which commonly cause traffic congestion, accidents, and severe carbon emissions. In order to address this essential issue and enhance the safety and efficiency of connected and…
LLMs often underperform on complex reasoning tasks when relying on a single generation-and-selection pipeline. Inference-time ensemble methods can improve performance by sampling diverse reasoning paths or aggregating multiple candidate…
Large Language Models (LLMs) have enabled collaborative Multi-Agent (MA) systems, where interacting agents improve performance through diverse reasoning and iterative refinement. However, these systems remain vulnerable to error…
Large Language Models (LLMs) have achieved high accuracy on complex commonsense and mathematical problems that involve the composition of multiple reasoning steps. However, current compositional benchmarks testing these skills tend to focus…
Diversity in training data, architecture, and providers is assumed to mitigate homogeneity in LLMs. However, we lack empirical evidence on whether different LLMs differ meaningfully. We conduct a large-scale empirical evaluation on over 350…
While large language models are capable diagnostic tools, the impact of multi-agent topology on diagnostic accuracy remains underexplored. This study evaluates four agent topologies, Control (single agent), Hierarchical, Adversarial, and…
Existing LLM-enabled multi-agent frameworks are predominantly limited to digital or simulated environments and confined to narrowly focused knowledge domain, constraining their applicability to complex engineering tasks that require the…