1 Radboud University
2 University of Amsterdam
Information retrieval has long focused on ranking documents by semantic relatedness. Yet many real-world information needs demand more: enforcement of logical constraints, multi-step inference, and synthesis of multiple pieces of evidence.
Addressing these requirements is, at its core, a problem of reasoning.
Across AI communities, researchers are developing diverse solutions for the problem of reasoning, from inference-time strategies and post-training of LLMs, to neuro-symbolic systems, Bayesian and probabilistic frameworks, geometric representations, and energy-based models. These efforts target the same problem: to move beyond pattern-matching systems toward structured, verifiable inference. However, they remain scattered across disciplines, making it difficult for IR researchers to identify the most relevant ideas and opportunities. To help navigate the fragmented landscape of research in reasoning, this tutorial first articulates a working definition of reasoning within the context of information retrieval and derives from it a unified analytical framework. The framework maps existing approaches along axes that reflect the core components of the definition. By providing a comprehensive overview of recent approaches and mapping current methods onto the defined axes, we expose their trade-offs and complementarities, highlight where IR can benefit from cross-disciplinary advances, and illustrate how retrieval process itself can play a central role in broader reasoning systems. The tutorial will equip participants with both a conceptual framework and practical guidance for enhancing reasoning-capable IR systems, while situating IR as a domain that both benefits and contributes to the broader development of reasoning methodologies.
| Time | Session | Speaker(s) | Duration |
|---|---|---|---|
| Part I — Introduction & Motivation | |||
| 09:00 – 09:15 | Why reasoning is central to information retrieval; overview of tutorial's objectives, structure, and relevance to IR community. | Mohanna | 15 min |
| Part II — Reasoning: Definition & its challenges in IR | |||
| 09:15 – 09:45 | Definition of reasoning in IR; Empirical and theoretical challenges in IR. | Maarten | 30 min |
| Part III — Methodological Families | |||
| 09:45 – 10:30 | LLM-based Approaches: Inference-time strategies and optimization for reasoning with LLMs; LLMs + Reinforcement Learning (RL). | Panagiotis/Mohanna | 45 min |
| 10:30 – 10:45 | Neuro-Symbolic Reasoning: Logical foundations of IR, Neuro-symbolic solutions with solvers and (probabilistic) logical programming. | Arjen | 15 min |
| 10:45 – 11:00 | Probabilistic and Bayesian Frameworks: Bayesian reasoning and uncertainty modeling in IR. | Panagiotis/Arjen | 15 min |
| 11:00 – 11:15 | Alternative Representations and Optimization Models: Enhanced (e.g., geometric, set-compositional) representation spaces; Iterative inference in the latent space. | Mohanna/Panagiotis | 15 min |
| Part IV — Bridging Current Methodologies & Future Directions | |||
| 11:15 – 11:45 | Comparative analysis of existing reasoning paradigms along key dimensions: representational adequacy, inference verifiability, and computational viability. | Maarten | 30 min |
| 11:45 – 12:00 | Identification of open research challenges, gaps across methodological lines, and opportunities for future work on reasoning-centric IR systems. | Arjen | 15 min |
Below are the key references discussed in this tutorial, organized by topic.
