Related papers: More Is Not Always Better: Cross-Component Interfe…

Multi-agent deliberation systems using large language models (LLMs) are increasingly proposed for policy simulation, yet they suffer from artificial consensus: evaluator agents converge on the same option regardless of their assigned value…

Agentic language model (LM) systems power modern applications like "Deep Research" and "Claude Code," and leverage multi-LM architectures to overcome context limitations. Beneath their apparent diversity lies a recurring pattern: smaller…

The explosive growth of Large Language Models (LLMs), such as GPT-4 with 1.8 trillion parameters, demands a fundamental rethinking of data center architecture to ensure scalability, efficiency, and cost-effectiveness. Our work provides a…

Identifying and articulating limitations is essential for transparent and rigorous scientific research. However, zero-shot large language models (LLMs) approach often produce superficial or general limitation statements (e.g., dataset bias…

While most existing works on LLM prompting techniques focus only on how to select a better set of data samples inside one single prompt input (In-Context Learning or ICL), why can not we design and leverage multiple prompts together to…

Alignment of Large Language models (LLMs) is crucial for safe and trustworthy deployment in applications. Reinforcement learning from human feedback (RLHF) has emerged as an effective technique to align LLMs to human preferences and broader…

Multi-agent systems (MAS) have emerged as a prominent paradigm for leveraging large language models (LLMs) to tackle complex tasks. However, the mechanisms governing the effectiveness of MAS built upon publicly available LLMs, specifically…

Ensuring semantic consistency between source code and its accompanying comments is crucial for program comprehension, effective debugging, and long-term maintainability. Comment inconsistency arises when developers modify code but neglect…

LLM-based tools are automating more software development tasks at a rapid pace, but there is no rigorous way to evaluate how different architectural choices -- prompts, skills, tools, multi-agent setups -- materially affect both capability…

Inter-cell interference (ICI) is one of the major performance-limiting factors in the context of modern cellular systems. To tackle ICI, coordinated multi-point (CoMP) schemes have been proposed as a key technology for next-generation…

AI systems have become increasingly capable of dangerous behaviours in many domains. This raises the question: Do models sometimes choose to violate human instructions in order to perform behaviour that is more useful for certain goals? We…

The integration of large language models (LLMs) into healthcare IoT systems promises faster decisions and improved medical support. LLMs are also deployed as multi-agent teams to assist AI doctors by debating, voting, or advising on…

Multi-agent LLM systems have shown promise for complex reasoning, yet recent evaluations reveal they often underperform single-model baselines. We identify a structural failure mode in sequential fine-tuning of shared-context teams:…

Cascaded LLM systems coordinate models of varying sizes with human experts to balance accuracy, cost, and abstention under uncertainty. However, single-model tiers at each stage often struggle with ambiguous queries, triggering premature…

Multi-agent applications often execute complex tasks as multi-stage workflows, where each stage is an LLM call whose output becomes part of context for subsequent steps. Existing LLM serving systems largely assume homogeneous clusters with…

Designing effective collaboration structure for multi-agent LLM systems to enhance collective reasoning is crucial yet remains under-explored. In this paper, we systematically investigate how collaborative reasoning performance is affected…

Traditional Reinforcement Learning (RL) suffers from replicating human-like behaviors, generalizing effectively in multi-agent scenarios, and overcoming inherent interpretability issues.These tasks are compounded when deep environment…

Agents, language model-based systems capable of reasoning, planning, and acting are widely adopted in real-world tasks, yet how their performance changes as these systems scale across key dimensions remains underexplored. We introduce…

Compound AI applications, composed from interactions between Large Language Models (LLMs), Machine Learning (ML) models, external tools and data sources are quickly becoming an integral workload in datacenters. Their diverse sub-components…

Multi-agent large language model (LLM) systems have emerged as a promising approach for clinical diagnosis, leveraging collaboration among agents to refine medical reasoning. However, most existing frameworks rely on single-vendor teams…