Related papers: JAF: Judge Agent Forest
The rapid evolution of neural architectures - from multilayer perceptrons to large-scale Transformer-based models - has enabled language models (LLMs) to exhibit emergent agentic behaviours when equipped with memory, planning, and external…
We propose a framework for adaptive data-centric collaborative machine learning among self-interested agents, coordinated by an arbiter. Designed to handle the incremental nature of real-world data, the framework operates in an online…
Error attribution in Large Language Model (LLM) multi-agent systems presents a significant challenge in debugging and improving collaborative AI systems. Current approaches to pinpointing agent and step level failures in interaction traces…
While language models (LMs) have shown potential across a range of decision-making tasks, their reliance on simple acting processes limits their broad deployment as autonomous agents. In this paper, we introduce Language Agent Tree Search…
Despite the effort of many researchers in the area of multi-agent systems (MAS) for designing and programming agents, a few years ago the research community began to take into account that common features among different MAS exists. Based…
Artificial intelligence (AI) has emerged as a transformative force across industries, driven by advances in deep learning and natural language processing, and fueled by large-scale data and computing resources. Despite its rapid adoption,…
We present Federation of Agents (FoA), a distributed orchestration framework that transforms static multi-agent coordination into dynamic, capability-driven collaboration. FoA introduces Versioned Capability Vectors (VCVs): machine-readable…
Recent work explores agentic inference-time techniques to perform structured, multi-step reasoning. However, stateless inference often struggles on multi-step tasks due to the absence of persistent state. Moreover, task-specific fine-tuning…
This review critically distinguishes between AI Agents and Agentic AI, offering a structured, conceptual taxonomy, application mapping, and analysis of opportunities and challenges to clarify their divergent design philosophies and…
Foundation models, such as large language models (LLMs), have been widely recognised as transformative AI technologies due to their capabilities to understand and generate content, including plans with reasoning capabilities. Foundation…
Cybersecurity decision-making increasingly occurs in environments characterized by uncertainty, partial observability, and adversarial manipulation, where heterogeneous signals from multiple sources are often incomplete, ambiguous, or…
Future sixth-generation (6G) mobile networks are envisioned to be equipped with a diverse set of powerful, yet highly specialized, optimization experts. Such a promising vision is concurrently expected to give rise to the need for scalable…
This paper introduces lateral thinking to implement System-2 reasoning capabilities in AI systems, focusing on anticipatory and causal reasoning under uncertainty. We present a framework for systematic generation and modeling of lateral…
Although Reinforcement Learning (RL) agents are effective in well-defined environments, they often struggle to generalize their learned policies to dynamic settings due to their reliance on trial-and-error interactions. Recent work has…
Agentic systems are becoming more capable: agents define strategies, take actions, and interact with different environments. This autonomy poses serious challenges for overseeing and assessing agent behavior. Most current tools are limited,…
Agentic search such as Deep Research systems-where agents autonomously browse the web, synthesize information, and return comprehensive citation-backed answers-represents a major shift in how users interact with web-scale information. While…
The use of AI in legal analysis and prediction (LegalAI) has gained widespread attention, with past research focusing on retrieval-based methods and fine-tuning large models. However, these approaches often require large datasets and…
Retrieval-augmented generation (RAG) has been widely adopted to ground large language models (LLMs) in external knowledge, yet it remains largely underexplored for improving reasoning. Existing methods either rely on online exploration…
We formalize three design axioms for sustained adoption of agent-centric AI systems executing multi-step tasks: (A1) Reliability > Novelty; (A2) Embed > Destination; (A3) Agency > Chat. We model adoption as a sum of a decaying novelty term…
Modern large-scale ranking systems operate within a sophisticated landscape of competing objectives, operational constraints, and evolving product requirements. Progress in this domain is increasingly bottlenecked by the engineering context…