Related papers: CascadeDebate: Multi-Agent Deliberation for Cost-A…

To improve the reasoning and question-answering capabilities of Large Language Models (LLMs), several multi-agent approaches have been introduced. While these methods enhance performance, the application of collective intelligence-based…

Tabular anomaly detection is often handled by single detectors or static ensembles, even though strong performance on tabular data typically comes from heterogeneous model families (e.g., tree ensembles, deep tabular networks, and tabular…

There are two main barriers to using large language models (LLMs) in clinical reasoning. Firstly, while LLMs exhibit significant promise in Natural Language Processing (NLP) tasks, their performance in complex reasoning and planning falls…

LLM-based search agents achieve strong performance but suffer from severe latency, as each step requires serialized LLM reasoning followed by action of tool execution. We revisit this bottleneck through the lens of speculation. While…

Context: Large Language Model (LLM) agents are becoming widely used for various Requirements Engineering (RE) tasks. Research on improving their accuracy mainly focuses on prompt engineering, model fine-tuning, and retrieval augmented…

Multi-agent debate (MAD) systems leverage collective intelligence to enhance reasoning capabilities, yet existing approaches struggle to simultaneously optimize accuracy, consensus formation, and computational efficiency. Static topology…

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…

As modern artificial intelligence (AI) systems become more advanced and capable, they can leverage a wide range of tools and models to perform complex tasks. The task of orchestrating these models is increasingly performed by Large Language…

We introduce FinDebate, a multi-agent framework for financial analysis, integrating collaborative debate with domain-specific Retrieval-Augmented Generation (RAG). Five specialized agents, covering earnings, market, sentiment, valuation,…

Multi-agent LLM frameworks are widely used to accelerate the development of agent systems powered by large language models (LLMs). These frameworks impose distinct architectural structures that govern how agents interact, store information,…

With advancements in reasoning capabilities, Large Language Models (LLMs) are increasingly employed for automated judgment tasks. While LLMs-as-Judges offer promise in automating evaluations, current approaches often rely on simplistic…

Therapy recommendation for chronic patients with multimorbidity is challenging due to risks of treatment conflicts. Existing decision support systems face scalability limitations. Inspired by the way in which general practitioners (GP)…

Large language models (LLMs) demonstrate remarkable performance across diverse tasks, yet their effectiveness frequently depends on costly commercial APIs or cloud services. Model selection thus entails a critical trade-off between…

LLM alignment has progressed in single-agent settings through paradigms such as RL with human feedback (RLHF), while recent work explores scalable alternatives such as RL with AI feedback (RLAIF) and dynamic alignment objectives. However,…

Multi-Agent Debate (MAD) has shown promise in leveraging collective intelligence to improve reasoning and reduce hallucinations, yet it remains unclear how information exchange shapes the underlying ability. Empirically, MAD exhibits…

Large Language Models (LLMs) still struggle with natural language reasoning tasks. Motivated by the society of minds (Minsky, 1988), we propose ReConcile, a multi-model multi-agent framework designed as a round table conference among…

We introduce AgenticSimLaw, a role-structured, multi-agent debate framework that provides transparent and controllable test-time reasoning for high-stakes tabular decision-making tasks. Unlike black-box approaches, our courtroom-style…

Many of us now treat LLMs as modern-day oracles asking it almost any kind of question. However, consulting an LLM does not have to be a single turn activity. But long multi-turn interactions can get tedious if it is simply to clarify…

Test-time scaling has become a dominant paradigm for improving LLM agent reliability, yet current approaches treat compute as an abundant resource, allowing agents to exhaust token and tool budgets on redundant steps or dead-end…

Large Language Models (LLMs) are increasingly used for clinical decision support, where hallucinations and unsafe suggestions may pose direct risks to patient safety. These risks are hard to assess: subtle clinical errors are often missed…