相关论文: Emergent Cognitive Convergence via Implementation:…
In recent years, a variety of powerful LLM-based agentic systems have been applied to automate complex tasks through task orchestration. However, existing orchestration methods still face key challenges, including strategy collapse under…
Leveraging multiple Large Language Models(LLMs) has proven effective for addressing complex, high-dimensional tasks, but current approaches often rely on static, manually engineered multi-agent configurations. To overcome these constraints,…
The Human Cognitive Simulation Framework proposes a governed cognitive AI architecture designed to improve personalization, adaptability, and long-term coherence in human AI interaction. The framework integrates short-term memory…
Background: There is great interest in agentic LLMs, large language models that act as agents. Objectives: We review the growing body of work in this area and provide a research agenda. Methods: Agentic LLMs are LLMs that (1) reason, (2)…
In order to flexibly act in an everyday environment, a robotic agent needs a variety of cognitive capabilities that enable it to reason about plans and perform execution recovery. Large language models (LLMs) have been shown to demonstrate…
Across millennia, complex societies have faced the same coordination problem of how to organize collective action among cognitively bounded and informationally incomplete individuals. Different civilizations developed different political…
To date, formal models of collective intelligence have lacked a plausible mathematical description of the relationship between local-scale interactions between highly autonomous sub-system components (individuals) and global-scale behavior…
The emergence of Large Language Models (LLMs) has ushered in a transformative paradigm in artificial intelligence, Agentic AI, where intelligent agents exhibit goal-directed autonomy, contextual reasoning, and dynamic multi-agent…
Natural language has long enabled human cooperation, but its lossy, ambiguous, and indirect nature limits the potential of collective intelligence. While machines are not subject to these constraints, most LLM-based multi-agent systems…
We introduce SwiftSage, a novel agent framework inspired by the dual-process theory of human cognition, designed to excel in action planning for complex interactive reasoning tasks. SwiftSage integrates the strengths of behavior cloning and…
Cybersecurity has become one of the earliest adopters of agentic AI, as security operations centers increasingly rely on multi-step reasoning, tool-driven analysis, and rapid decision-making under pressure. While individual large language…
The arrival of large language models (LLMs) capable of multi-step reasoning, tool use, and long-horizon planning has produced a qualitative shift in software engineering. Where earlier code-completion tools such as GitHub Copilot operated…
A major challenge for world models in multi-agent systems is to understand interdependent agent dynamics, predict interactive multi-agent trajectories, and plan over long horizons with collective awareness, without centralized supervision…
Inspired by the dual-process theory of human cognition from \textit{Thinking, Fast and Slow}, we introduce \textbf{PRIME} (Planning and Retrieval-Integrated Memory for Enhanced Reasoning), a multi-agent reasoning framework that dynamically…
We propose cognitive prompting as a novel approach to guide problem-solving in large language models (LLMs) through structured, human-like cognitive operations, such as goal clarification, decomposition, filtering, abstraction, and pattern…
Large language model (LLM) agents are moving beyond prompting alone. ChatGPT marked the rise of general-purpose LLM assistants, DeepSeek showed that on-policy reinforcement learning with verifiable rewards can improve reasoning and tool…
The integration of Large Language Models (LLMs) into cybersecurity education for criminal justice professionals is currently hindered by the "statelessness" of reactive chatbots and the risk of hallucinations in high-stakes legal contexts.…
Current LLM post-training methods optimize complete reasoning trajectories through Supervised Fine-Tuning (SFT) followed by outcome-based Reinforcement Learning (RL). While effective, a closer examination reveals a fundamental gap: this…
When are multi-agent LLM systems merely a collection of individual agents versus an integrated collective with higher-order structure? We introduce an information-theoretic framework to test -- in a purely data-driven way -- whether…
Current LLM agents lack principled mechanisms for managing persistent memory across long interaction horizons. We present a biologically-grounded memory architecture comprising six cognitive mechanisms: (1) sleep-phase consolidation, (2)…