Winners of the #ECAI2025 outstanding paper awards announced

by Lucy Smith

28 October 2025

ECAI-2025 outstanding papers

FAIRGAME: A Framework for AI Agents Bias Recognition Using Game Theory
Alessio Buscemi, Daniele Proverbio, Alessandro Di Stefano, The Anh Han, German Castignani, Pietro Liò

Abstract: Letting AI agents interact in multi-agent applications adds a layer of complexity to the interpretability and prediction of AI outcomes, with profound implications for their trustworthy adoption in research and society. Game theory offers powerful models to capture and interpret strategic interaction among agents, but requires the support of reproducible, standardized and user-friendly IT frameworks to enable comparison and interpretation of results. To this end, we present FAIRGAME, a Framework for AI Agents Bias Recognition using Game Theory. We describe its implementation and usage, and we employ it to uncover biased outcomes in popular games among AI agents, depending on the employed Large Language Model (LLM) and used language, as well as on the personality trait or strategic knowledge of the agents. Overall, FAIRGAME allows users to reliably and easily simulate their desired games and scenarios and compare the results across simulation campaigns and with game-theoretic predictions, enabling the systematic discovery of biases, the anticipation of emerging behavior out of strategic interplays, and empowering further research into strategic decision-making using LLM agents.

Read the paper in full here.

Conditional Dominance Analysis for Classical Planning
Anna Wilhelm, Álvaro Torralba

Abstract: Dominance analysis methods compare pairs of states in a planning task to prove that one is at least as close to the goal as other. Existing methods compute fact-dominance relations, which identify facts that are at least as good as others in any situation. However, this is only possible when a fact is at least as good as another in every single possible context. We introduce a new notion of conditional dominance, which can identify that a fact dominates another under certain conditions. We extend previous methods to compute dominance by taking into account a set of “contexts” in order to find maximal dominance relations. We propose several strategies to find relevant contexts automatically and show that even with one single condition, one can achieve significant pruning in certain domains.

Read the paper in full here.

Analysing Temporal Reasoning in Description Logics Using Formal Grammars
Camille Bourgaux, Anton Gnatenko, Michaël Thomazo

Abstract: We establish a correspondence between (fragments of) TEL^◯, a temporal extension of the EL description logic with the LTL operator ◯^k, and some specific kinds of formal grammars, in particular, conjunctive grammars (context-free grammars equipped with the operation of intersection). This connection implies that TEL^◯ does not possess the property of ultimate periodicity of models, and further leads to undecidability of query answering in TEL^◯, closing a question left open since the introduction of TEL^◯. Moreover, it also allows to establish decidability of query answering for some new interesting fragments of TEL^◯, and to reuse for this purpose existing tools and algorithms for conjunctive grammars.

Read the paper in full here.

PAIS-2025 outstanding paper

Optimizing Parcels Sorting Through Reinforcement Learning for Intralogistics
Loris Roveda, Marco Maccarini, Filippo Pura, Fabio Reiso and Blerina Spahiu

Abstract: Sorting of parcels is a critical process in intralogistics for the proper processing and dispatching of packages. Commonly, such a process is manually executed by operators along the plant, without any added value, and might result in musculoskeletal injuries due to the non-ergonomic working conditions. Automation solutions are also present in the market and scientific literature. However, available solutions are usually implemented with pre-defined, simplified sorting rules/finite state machines capable of managing only a limited number of parcel types/sorting scenarios. To generalize and fully automate the sorting process in intralogistics, we propose to employ Reinforcement Learning (RL) for the derivation of sorting policies in combination with machine vision for the online tracking of the parcels, used as the state of the RL. More in detail, the on-policy Proximal Policy Optimization (PPO) algorithm is used for RL, and Yolo is chosen as the machine vision algorithm for parcel recognition and tracking. Based on the AMS sorting module of the SAIET Engineering company, a modular kinematic model (with parcels collision modeling) of the sorting system (an n by m AMS – i.e., 2-action actuators – matrix) is derived, and used as the environment for the PPO. Offline sorting policy training is performed by randomizing the parcel number, size, and entry positions. The trained policy is then deployed to the sorting module, which is equipped with cameras for machine vision implementation and performance evaluation. In-distribution and out-of-distribution (i.e., with parcel types not considered in the off-line training) tests achieved the target performance of 96.5% and 94% sorting accuracy, respectively.

Read the paper in full here.

The conference proceedings can be found here.