Arrow Research search

Author name cluster

Kostas Stathis

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

14 papers
2 author rows

Possible papers

14

AAAI Conference 2026 Conference Paper

Towards a Common Framework for Autoformalization

  • Agnieszka Mensfelt
  • David Tena Cucala
  • Santiago Franco
  • Angeliki Koutsoukou-Argyraki
  • Vince Trencsenyi
  • Kostas Stathis

Autoformalization has emerged as a term referring to the automation of formalization in the context of the formalization of mathematics using interactive theorem provers (proof assistants). Its rapid development has been driven by progress in deep learning, especially large language models (LLMs). More recently, usage of the term has expanded beyond mathematics to describe tasks that involve translating natural language input into verifiable logical representations. At the same time, a growing body of research explores using LLMs to translate informal language into formal representations for reasoning, planning, and knowledge representation, but without explicitly referring to this process as autoformalization. As a result, despite addressing similar tasks, the largely independent development of these research areas has limited opportunities for shared methodologies, benchmarks, and theoretical frameworks that could accelerate progress. Our goal is to review - explicit or implicit - instances of what can be considered autoformalization and to propose a unified framework, encouraging cross-pollination between different fields to advance the development of next generation AI systems.

PDF Details DOI

ECAI Conference 2025 Conference Paper

Generative Agents for Multi-Agent Autoformalization of Interaction Scenarios

  • Agnieszka Mensfelt
  • Kostas Stathis
  • Vince Trencsenyi

Multi-agent simulations are a versatile tool for exploring interactions among natural and artificial agents, but their development typically demands domain expertise and manual effort. This work introduces the Generative Agents for Multi-Agent Autoformalization (GAMA) framework, which automates the formalization of interaction scenarios in simulations using agents augmented with large language models (LLMs). To demonstrate the application of GAMA, we use natural language descriptions of game-theoretic scenarios representing social interactions, and we autoformalize them into executable logic programs defining game rules, with syntactic correctness enforced through a solver-based validation. To ensure runtime validity, an iterative, tournament-based procedure tests the generated rules and strategies, followed by exact semantic validation when ground truth outcomes are available. In experiments with 110 natural language descriptions across five 2 × 2 simultaneous-move games, GAMA achieves 100% syntactic and 76. 5% semantic correctness with Claude 3. 5 Sonnet, and 99. 82% syntactic and 77% semantic correctness with GPT-4o. The framework also shows high semantic accuracy in autoformalizing agents’ strategies.

Details

ECAI Conference 2025 Conference Paper

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 agency. However, this shift raises key questions about the extent to which LLM-based agents replicate human strategic reasoning, particularly in game-theoretic settings. In this context, we examine the role of agentic sophistication in shaping artificial reasoners’ performance by evaluating three agent designs: a simple game-theoretic model, an unstructured LLM-as-agent model, and an LLM integrated into a traditional agentic framework. Using guessing games as a testbed, we benchmarked these agents against human participants across general reasoning patterns and individual role-based objectives. Furthermore, we introduced obfuscated game scenarios to assess agents’ ability to generalise beyond training distributions. Our analysis, covering over 2000 reasoning samples across 25 agent configurations, shows that human-inspired cognitive structures can enhance LLM agents’ alignment with human strategic behaviour. Still, the relationship between agentic design complexity and human-likeness is non-linear, highlighting a critical dependence on underlying LLM capabilities and suggesting limits to simple architectural augmentation.

Details

AAAI Conference 2023 Conference Paper

Disentangling Reafferent Effects by Doing Nothing

  • Benedict Wilkins
  • Kostas Stathis

An agent's ability to distinguish between sensory effects that are self-caused, and those that are not, is instrumental in the achievement of its goals. This ability is thought to be central to a variety of functions in biological organisms, from perceptual stabilisation and accurate motor control, to higher level cognitive functions such as planning, mirroring and the sense of agency. Although many of these functions are well studied in AI, this important distinction is rarely made explicit and the focus tends to be on the associational relationship between action and sensory effect or success. Toward the development of more general agents, we develop a framework that enables agents to disentangle self-caused and externally-caused sensory effects. Informed by relevant models and experiments in robotics, and in the biological and cognitive sciences, we demonstrate the general applicability of this framework through an extensive experimental evaluation over three different environments.

PDF Details DOI

AAMAS Conference 2022 Conference Paper

Deep Learnable Strategy Templates for Multi-Issue Bilateral Negotiation

  • Pallavi Bagga
  • Nicola Paoletti
  • Kostas Stathis

We propose the notion of deep reinforcement learning-based strategy templates for multi-issue bilateral negotiation. Each strategy template consists of a set of interpretable parameterized tactics that are used to decide an optimal action at any time. This contrasts with existing work that only estimates the threshold utility for those tactics that require it. As a result, we build automated agents for multi-issue negotiations that can adapt to different negotiation domains without the need to be pre-programmed.

PDF

JAAMAS Journal 2021 Journal Article

ANEGMA: an automated negotiation model for e-markets

  • Pallavi Bagga
  • Nicola Paoletti
  • Kostas Stathis

Abstract We present a novel negotiation model that allows an agent to learn how to negotiate during concurrent bilateral negotiations in unknown and dynamic e-markets. The agent uses an actor-critic architecture with model-free reinforcement learning to learn a strategy expressed as a deep neural network. We pre-train the strategy by supervision from synthetic market data, thereby decreasing the exploration time required for learning during negotiation. As a result, we can build automated agents for concurrent negotiations that can adapt to different e-market settings without the need to be pre-programmed. Our experimental evaluation shows that our deep reinforcement learning based agents outperform two existing well-known negotiation strategies in one-to-many concurrent bilateral negotiations for a range of e-market settings.

Details DOI

IJCAI Conference 2020 Conference Paper

A Deep Reinforcement Learning Approach to Concurrent Bilateral Negotiation

  • Pallavi Bagga
  • Nicola Paoletti
  • Bedour Alrayes
  • Kostas Stathis

We present a novel negotiation model that allows an agent to learn how to negotiate during concurrent bilateral negotiations in unknown and dynamic e-markets. The agent uses an actor-critic architecture with model-free reinforcement learning to learn a strategy expressed as a deep neural network. We pre-train the strategy by supervision from synthetic market data, thereby decreasing the exploration time required for learning during negotiation. As a result, we can build automated agents for concurrent negotiations that can adapt to different e-market settings without the need to be pre-programmed. Our experimental evaluation shows that our deep reinforcement learning based agents outperform two existing well-known negotiation strategies in one-to-many concurrent bilateral negotiations for a range of e-market settings.

PDF Details DOI

IJCAI Conference 2013 Conference Paper

Multi-Dimensional Causal Discovery

  • Ulrich Schaechtle
  • Kostas Stathis
  • Stefano Bromuri

We propose a method for learning causal relations within high-dimensional tensor data as they are typically recorded in non-experimental databases. The method allows the simultaneous inclusion of numerous dimensions within the data analysis such as samples, time and domain variables construed as tensors. In such tensor data we exploit and integrate non-Gaussian models and tensor analytic algorithms in a novel way. We prove that we can determine simple causal relations independently of how complex the dimensionality of the data is. We rely on a statistical decomposition that flattens higher-dimensional data tensors into matrices. This decomposition preserves the causal information and is therefore suitable for structure learning of causal graphical models, where a causal relation can be generalised beyond dimension, for example, over all time points. Related methods either focus on a set of samples for instantaneous effects or look at one sample for effects at certain time points. We evaluate the resulting algorithm and discuss its performance both with synthetic and real-world data.

PDF Details DOI

ICAART Conference 2009 Conference Paper

Arguing over Motivations within the V3A-Architecture for Self-Adaptation

  • Maxime Morge
  • Kostas Stathis
  • Laurent Vercouter

The Vowel Agent Argumentation Architecture (V3A) is an abstract model by means of which an autonomous agent argues with itself to manage its motivations and arbitrate its possible internal conflicts. We propose an argumentation technique which specifies the internal dialectical process and a dialogue-game amongst internal components which can dynamically join/leave the game, thus having the potential to support the development of self-adaptive agents. We exemplify this dialectical representation of the V3A model with a scenario, whereby components of the agent's mind called facets can be automatically downloaded to argue an agent's motivation.

Details