2 citations · 3 across the 9 of their papers we have counts for
9 papers
PrologMCP: A Standardized Prolog Tool Interface for LLM Agents
Agnieszka Mensfelt, Adarsh Prabhakaran, Adrian Haret +2
Frontier reasoning-tuned language models still fail on deductive tasks at depth, and the cost of improved performance through extended internal reasoning scales poorly. Symbolic de…
Hypergame Rationalisability: Solving Agent Misalignment In Strategic Play
Vince Trencsenyi
Differences in perception, information asymmetries, and bounded rationality lead game-theoretic players to derive a private, subjective view of the game that may diverge from the u…
Towards a Common Framework for Autoformalization
Agnieszka Mensfelt, David Tena Cucala, Santiago Franco +3
Autoformalization has emerged as a term referring to the automation of formalization - specifically, the formalization of mathematics using interactive theorem provers (proof assis…
A Survey on Hypergame Theory: Modelling Misaligned Perceptions and Nested Beliefs for Multi-Agent Systems
Vince Trencsenyi, Agnieszka Mensfelt, Kostas Stathis
Classical game-theoretic models typically assume rational agents, complete information, and common knowledge of payoffs - assumptions that are often violated in real-world MAS char…
The Influence of Human-inspired Agentic Sophistication in LLM-driven Strategic Reasoners
Vince Trencsenyi, Agnieszka Mensfelt, Kostas Stathis
The rapid rise of large language models (LLMs) has shifted artificial intelligence (AI) research toward agentic systems, motivating the use of weaker and more flexible notions of a…
Approximating Human Strategic Reasoning with LLM-Enhanced Recursive Reasoners Leveraging Multi-agent Hypergames
Vince Trencsenyi, Agnieszka Mensfelt, Kostas Stathis
LLM-driven multi-agent-based simulations have been gaining traction with applications in game-theoretic and social simulations. While most implementations seek to exploit or evalua…
Generative Agents for Multi-Agent Autoformalization of Interaction Scenarios
Agnieszka Mensfelt, Kostas Stathis, Vince Trencsenyi
Multi-agent simulations are versatile tools for exploring interactions among natural and artificial agents, but their development typically demands domain expertise and manual effo…
Autoformalization of Game Descriptions using Large Language Models
Agnieszka Mensfelt, Kostas Stathis, Vince Trencsenyi
Game theory is a powerful framework for reasoning about strategic interactions, with applications in domains ranging from day-to-day life to international politics. However, applyi…
Towards Logically Sound Natural Language Reasoning with Logic-Enhanced Language Model Agents
Agnieszka Mensfelt, Kostas Stathis, Vince Trencsenyi
Large language models (LLMs) are increasingly explored as general-purpose reasoners, particularly in agentic contexts. However, their outputs remain prone to mathematical and logic…