Searcharxiv⌕ Search

arXiv subjects

Maarten de Rijke

Publications and source records attributed to Maarten de Rijke.

At least 37 records · Page 2Linked to original sources
arXiv2026

Can Small Agents Collaborate to Beat a Single Large Language Model?

Recent progress in language modeling has largely relied on scaling model size, yet larger models do not reliably improve performance on tasks requiring multi-step reasoning and tool use. Multi-agent collaboration offers a potential alternative, raising a key question: can well-organized systems built from smaller models outperform much larger language models? We address this question using a minimally designed multi-agent system with a single orchestrator and a small set of specialized sub-agents with restricted communication. On tool-intensive benchmarks spanning factual retrieval, multi-hop reasoning, scientific question answering, and mathematical problem solving, we conduct controlled comparisons between small multi-agent systems and large single-agent models. We find that small multi-agent systems can outperform substantially larger single-agent models, even when the latter have direct access to tools. Reasoning at the orchestrator yields the largest gains, while enabling reasoning in sub-agents provides limited or negative benefits. Overall system performance is driven primarily by orchestrator capacity rather than sub-agent capacity. These results suggest that improved agentic performance depends more on architectural orchestration than on raw model scaling.

cs.MA↗
arXiv2026

SubSearch: Intermediate Rewards for Unsupervised Guided Reasoning in Complex Retrieval

Large language models (LLMs) are probabilistic in nature and perform more reliably when augmented with external information. As complex queries often require multi-step reasoning over the retrieved information, with no clear or predetermined reasoning path, they remain challenging. Recent approaches train models using reinforcement learning on the model's outcome, showing promise in improving how models handle complex information. We introduce SubSearch, a specialized framework that shifts from outcome-only supervision to intermediate reward signals that incentivize planning high-quality reasoning. Unlike previous work on process reward modeling, which focuses on training a separate reward model with annotated trajectories by either human annotators or large LLM judges, SubSearch directly optimizes the generator using intrinsic process rewards, which we define as internally-derived rewards, eliminating the need for external supervision, and moving towards autonomous information-intensive reasoning. Experiments on seven benchmarks show that rewarding intermediate reasoning steps with intrinsic rewards leads to more robust reasoning traces in both QA and multi-hop QA datasets over using only outcome rewards. SubSearch can help in building reasoning traces that allow agents to better integrate search engines for complex query answering, while offering a data-efficient alternative to supervised process modeling.

cs.IR↗
arXiv2026

Cold-Starts in Generative Recommendation: A Reproducibility Study

Cold-start recommendation remains a central challenge in dynamic, open-world platforms, requiring models to recommend for newly registered users (user cold-start) and to recommend newly introduced items to existing users (item cold-start) under sparse or missing interaction signals. Recent generative recommenders built on pre-trained language models (PLMs) are often expected to mitigate cold-start by using item semantic information (e.g., titles and descriptions) and test-time conditioning on limited user context. However, cold-start is rarely treated as a primary evaluation setting in existing studies, and reported gains are difficult to interpret because key design choices, such as model scale, identifier design, and training strategy, are frequently changed together. In this work, we present a systematic reproducibility study of generative recommendation under a unified suite of cold-start protocols.

cs.IR↗
arXiv2026

LiRA: A Multi-Agent Framework for Reliable and Readable Literature Review Generation

The rapid growth of scientific publications has made it increasingly difficult to keep literature reviews comprehensive and up-to-date. Though prior work has focused on automating retrieval and screening, the writing phase of systematic reviews remains largely under-explored, especially with regard to readability and factual accuracy. To address this, we present LiRA (Literature Review Agents), a multi-agent collaborative workflow which emulates the human literature review process. LiRA utilizes specialized agents for content outlining, subsection writing, editing, and reviewing, producing cohesive and comprehensive review articles. Evaluated on SciReviewGen and a proprietary ScienceDirect dataset, LiRA outperforms current baselines such as AutoSurvey and MASS-Survey in writing and citation quality, while maintaining competitive similarity to human-written reviews. We further evaluate LiRA in real-world scenarios using document retrieval and assess its robustness to reviewer model variation. Our findings highlight the potential of agentic LLM workflows, even without domain-specific tuning, to improve the reliability and usability of automated scientific writing.

cs.CL↗
arXiv2026

Multi-Step Semantic Reasoning in Generative Retrieval

Generative retrieval (GR) models encode a corpus within model parameters and generate relevant document identifiers directly for a given query. While this paradigm shows promise in retrieval tasks, existing GR models struggle with complex queries in numerical contexts, such as those involving semantic reasoning over financial reports, due to limited reasoning capabilities. This limitation leads to suboptimal retrieval accuracy and hinders practical applicability. We propose ReasonGR, a framework designed to enhance multi-step semantic reasoning in numerical contexts within GR. ReasonGR employs a structured prompting strategy combining task-specific instructions with stepwise reasoning guidance to better address complex retrieval queries. Additionally, it integrates a reasoning-focused adaptation module to improve the learning of reasoning-related parameters. Experiments on the FinQA dataset, which contains financial queries over complex documents, demonstrate that ReasonGR improves retrieval accuracy and consistency, indicating its potential for advancing GR models in reasoning-intensive retrieval scenarios.

cs.IR↗
arXiv2026

ERASE -- A Real-World Aligned Benchmark for Unlearning in Recommender Systems

Machine unlearning (MU) enables the removal of selected training data from trained models, to address privacy compliance, security, and liability issues in recommender systems. Existing MU benchmarks poorly reflect real-world recommender settings: they focus primarily on collaborative filtering, assume unrealistically large deletion requests, and overlook practical constraints such as sequential unlearning and efficiency. We present ERASE, a large-scale benchmark for MU in recommender systems designed to align with real-world usage. ERASE spans three core tasks -- collaborative filtering, session-based recommendation, and next-basket recommendation -- and includes unlearning scenarios inspired by real-world applications, such as sequentially removing sensitive interactions or spam. The benchmark covers seven unlearning algorithms, including general-purpose and recommender-specific methods, across nine public datasets and nine state-of-the-art models. We execute ERASE to produce more than 600 GB of reusable artifacts, such as extensive experimental logs and more than a thousand model checkpoints. Crucially, the artifacts that we release enable systematic analysis of where current unlearning methods succeed and where they fall short. ERASE showcases that approximate unlearning can match retraining in some settings, but robustness varies widely across datasets and architectures. Repeated unlearning exposes weaknesses in general-purpose methods, especially for attention-based and recurrent models, while recommender-specific approaches behave more reliably. ERASE provides the empirical foundation to help the community assess, drive, and track progress toward practical MU in recommender systems.

cs.IR↗
arXiv2026

A Simple and Effective Reinforcement Learning Method for Text-to-Image Diffusion Fine-tuning

Reinforcement learning (RL)-based fine-tuning has emerged as a powerful approach for aligning diffusion models with black-box objectives. Proximal policy optimization (PPO) is a popular choice of method for policy optimization. While effective in terms of performance and sample complexity, PPO is highly sensitive to hyper-parameters and involves substantial computational overhead. REINFORCE, on the other hand, mitigates some implementation complexities such as high memory overhead and sensitive hyper-parameter tuning, but has suboptimal performance due to high variance and crucially sample inefficiency, which is the primary notion of efficiency we study in this work. While the variance of the REINFORCE can be reduced by sampling multiple actions per input prompt and using a baseline correction term, it still suffers from sample inefficiency. To address these challenges, we systematically analyze the sample efficiency-effectiveness trade-off between REINFORCE and PPO, and propose leave-one-out PPO ( LOOP), a novel RL for diffusion fine-tuning method. LOOP combines variance reduction techniques from REINFORCE, such as sampling multiple actions per input prompt and a baseline correction term, with the robustness and sample efficiency of PPO via clipping and importance sampling. Our results demonstrate that LOOP effectively improves diffusion models on various black-box objectives, and achieves a better balance between sample efficiency and final performance.

cs.LG↗
arXiv2026

Reason to Retrieve: Enhancing Query Understanding through Decomposition and Interpretation

Query understanding (QU) aims to accurately infer user intent to improve document retrieval. It plays a vital role in modern search engines. While large language models (LLMs) have made notable progress in this area, their effectiveness has primarily been studied on short, keyword-based queries. With the rise of AI-driven search, long-form queries with complex intent become increasingly common, but they are underexplored in the context of LLM-based QU. To address this gap, we introduce ReDI, a reasoning-enhanced query understanding method through decomposition and interpretation. ReDI uses the reasoning and understanding capabilities of LLMs within a three-stage pipeline. (i) It decomposes a complex query into a set of targeted sub-queries to capture the user intent. (ii) It enriches each sub-query with detailed semantic interpretations to enhance the retrieval of intent-document matching. And (iii), after independently retrieving documents for each sub-query, ReDI uses a fusion strategy to aggregate the results and obtain the final ranking. We collect a large-scale dataset of real-world complex queries from a commercial search engine and distill the query understanding capabilities of DeepSeek-R1 into small models for practical application. Experiments on public benchmarks, including BRIGHT and BEIR, show that ReDI consistently outperforms strong baselines in both sparse and dense retrieval paradigms, demonstrating its effectiveness. We release our code, generated sub-queries, and interpretations at https://github.com/youngbeauty250/ReDI.

cs.IR↗
arXiv2026

Contrastive Learning for Diversity-Aware Product Recommendations in Retail

Recommender systems often struggle with long-tail distributions and limited item catalog exposure, where a small subset of popular items dominates recommendations. This challenge is especially critical in large-scale online retail settings with extensive and diverse product assortments. This paper introduces an approach to enhance catalog coverage without compromising recommendation quality in the existing digital recommendation pipeline at IKEA Retail. Drawing inspiration from recent advances in negative sampling to address popularity bias, we integrate contrastive learning with carefully selected negative samples. Through offline and online evaluations, we demonstrate that our method improves catalog coverage, ensuring a more diverse set of recommendations yet preserving strong recommendation performance.

cs.IR↗
arXiv2026

Do Images Clarify? A Study on the Effect of Images on Clarifying Questions in Conversational Search

Conversational search systems increasingly employ clarifying questions to refine user queries and improve the search experience. Previous studies have demonstrated the usefulness of text-based clarifying questions in enhancing both retrieval performance and user experience. While images have been shown to improve retrieval performance in various contexts, their impact on user performance when incorporated into clarifying questions remains largely unexplored. We conduct a user study with 73 participants to investigate the role of images in conversational search, specifically examining their effects on two search-related tasks: (i) answering clarifying questions and (ii) query reformulation. We compare the effect of multimodal and text-only clarifying questions in both tasks within a conversational search context from various perspectives. Our findings reveal that while participants showed a strong preference for multimodal questions when answering clarifying questions, preferences were more balanced in the query reformulation task. The impact of images varied with both task type and user expertise. In answering clarifying questions, images helped maintain engagement across different expertise levels, while in query reformulation they led to more precise queries and improved retrieval performance. Interestingly, for clarifying question answering, text-only setups demonstrated better user performance as they provided more comprehensive textual information in the absence of images. These results provide valuable insights for designing effective multimodal conversational search systems, highlighting that the benefits of visual augmentation are task-dependent and should be strategically implemented based on the specific search context and user characteristics.

cs.CL↗
arXiv2026

Tutorial on Reasoning for IR & IR for Reasoning

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.

cs.IR↗
arXiv2026

Curriculum Approximate Unlearning for Session-based Recommendation

Approximate unlearning for session-based recommendation refers to eliminating the influence of specific training samples from the recommender without retraining of (sub-)models. Gradient ascent (GA) is a representative method to conduct approximate unlearning. However, there still exist dual challenges to apply GA for session-based recommendation. On the one hand, naive applying of GA could lead to degradation of recommendation performance. On the other hand, existing studies fail to consider the ordering of unlearning samples when simultaneously processing multiple unlearning requests, leading to sub-optimal recommendation performance and unlearning effect. To address the above challenges, we introduce CAU, a curriculum approximate unlearning framework tailored to session-based recommendation. CAU handles the unlearning task with a GA term on unlearning samples. Specifically, to address the first challenge, CAU formulates the overall optimization task as a multi-objective optimization problem, where the GA term for unlearning samples is combined with retaining terms for preserving performance. The multi-objective optimization problem is solved through seeking the Pareto-Optimal solution, which achieves effective unlearning with trivial sacrifice on recommendation performance. To tackle the second challenge, CAU adopts a curriculum-based sequence to conduct unlearning on batches of unlearning samples. The key motivation is to perform unlearning from easy samples to harder ones. To this end, CAU first introduces two metrics to measure the unlearning difficulty, including gradient unlearning difficulty and embedding unlearning difficulty. Then, two strategies, hard-sampling and soft-sampling, are proposed to select unlearning samples according to difficulty scores.

cs.IR↗
arXiv2026

OrLog: Resolving Complex Queries with LLMs and Probabilistic Reasoning

Resolving complex information needs that come with multiple constraints should consider enforcing the logical operators encoded in the query (i.e., conjunction, disjunction, negation) on the candidate answer set. Current retrieval systems either ignore these constraints in neural embeddings or approximate them in a generative reasoning process that can be inconsistent and unreliable. Although well-suited to structured reasoning, existing neuro-symbolic approaches remain confined to formal logic or mathematics problems as they often assume unambiguous queries and access to complete evidence, conditions rarely met in information retrieval. To bridge this gap, we introduce OrLog, a neuro-symbolic retrieval framework that decouples predicate-level plausibility estimation from logical reasoning: a large language model (LLM) provides plausibility scores for atomic predicates in one decoding-free forward pass, from which a probabilistic reasoning engine derives the posterior probability of query satisfaction. We evaluate OrLog across multiple backbone LLMs, varying levels of access to external knowledge, and a range of logical constraints, and compare it against base retrievers and LLM-as-reasoner methods. Provided with entity descriptions, OrLog can significantly boost top-rank precision compared to LLM reasoning with larger gains on disjunctive queries. OrLog is also more efficient, cutting mean tokens by $\sim$90\% per query-entity pair. These results demonstrate that generation-free predicate plausibility estimation combined with probabilistic reasoning enables constraint-aware retrieval that outperforms monolithic reasoning while using far fewer tokens.

cs.IR↗
arXiv2026

Unveiling and Simulating Short-Video Addiction Behaviors via Economic Addiction Theory

Short-video applications have attracted substantial user traffic. However, these platforms also foster problematic usage patterns, commonly referred to as short-video addiction, which pose risks to both user health and the sustainable development of platforms. Prior studies on this issue have primarily relied on questionnaires or volunteer-based data collection, which are often limited by small sample sizes and population biases. In contrast, short-video platforms have large-scale behavioral data, offering a valuable foundation for analyzing addictive behaviors. To examine addiction-aware behavior patterns, we combine economic addiction theory with users' implicit behavior captured by recommendation systems. Our analysis shows that short-video addiction follows functional patterns similar to traditional forms of addictive behavior (e.g., substance abuse) and that its intensity is consistent with findings from previous social science studies. To develop a simulator that can learn and model these patterns, we introduce a novel training framework, AddictSim. To consider the personalized addiction patterns, AddictSim uses a mean-to-adapted strategy with group relative policy optimization training. Experiments on two large-scale datasets show that AddictSim consistently outperforms existing training strategies. Our simulation results show that integrating diversity-aware algorithms can mitigate addictive behaviors well.

cs.IR↗
arXiv2026

The Unfairness of Multifactorial Bias in Recommendation

Popularity bias and positivity bias are two prominent sources of bias in recommender systems. Both arise from input data, propagate through recommendation models, and lead to unfair or suboptimal outcomes. Popularity bias occurs when a small subset of items receives most interactions, while positivity bias stems from the over-representation of high rating values. Although each bias has been studied independently, their combined effect, to which we refer to as multifactorial bias, remains underexplored. In this work, we examine how multifactorial bias influences item-side fairness, focusing on exposure bias, which reflects the unequal visibility of items in recommendation outputs. Through simulation studies, we find that positivity bias is disproportionately concentrated on popular items, further amplifying their over-exposure. Motivated by this insight, we adapt a percentile-based rating transformation as a pre-processing strategy to mitigate multifactorial bias. Experiments using six recommendation algorithms across four public datasets show that this approach improves exposure fairness with negligible accuracy loss. We also demonstrate that integrating this pre-processing step into post-processing fairness pipelines enhances their effectiveness and efficiency, enabling comparable or better fairness with reduced computational cost. These findings highlight the importance of addressing multifactorial bias and demonstrate the practical value of simple, data-driven pre-processing methods for improving fairness in recommender systems.

cs.IR↗
arXiv2026

Controlled Retrieval-augmented Context Evaluation for Long-form RAG

Retrieval-augmented generation (RAG) enhances large language models by incorporating context retrieved from external knowledge sources. While the effectiveness of the retrieval module is typically evaluated with relevance-based ranking metrics, such metrics may be insufficient to reflect the retrieval's impact on the final RAG result, especially in long-form generation scenarios. We argue that providing a comprehensive retrieval-augmented context is important for long-form RAG tasks like report generation and propose metrics for assessing the context independent of generation. We introduce CRUX, a \textbf{C}ontrolled \textbf{R}etrieval-a\textbf{U}gmented conte\textbf{X}t evaluation framework designed to directly assess retrieval-augmented contexts. This framework uses human-written summaries to control the information scope of knowledge, enabling us to measure how well the context covers information essential for long-form generation. CRUX uses question-based evaluation to assess RAG's retrieval in a fine-grained manner. Empirical results show that CRUX offers more reflective and diagnostic evaluation. Our findings also reveal substantial room for improvement in current retrieval methods, pointing to promising directions for advancing RAG's retrieval. Our data and code are publicly available to support and advance future research on retrieval.

cs.IR↗
arXiv2026

Re-Rankers as Relevance Judges

Using large language models (LLMs) to predict relevance judgments has shown promising results. Most studies treat this task as a distinct research line, e.g., focusing on prompt design for predicting relevance labels given a query and passage. However, predicting relevance judgments is essentially a form of relevance prediction, a problem extensively studied in tasks such as re-ranking. Despite this potential overlap, little research has explored reusing or adapting established re-ranking methods to predict relevance judgments, leading to potential resource waste and redundant development. To bridge this gap, we reproduce re-rankers in a re-ranker-as-relevance-judge setup. We design two adaptation strategies: (i) using binary tokens (e.g., "true" and "false") generated by a re-ranker as direct judgments, and (ii) converting continuous re-ranking scores into binary labels via thresholding. We perform extensive experiments on TREC-DL 2019 to 2023 with 8 re-rankers from 3 families, ranging from 220M to 32B, and analyse the evaluation bias exhibited by re-ranker-based judges. Results show that re-ranker-based relevance judges, under both strategies, can outperform UMBRELA, a state-of-the-art LLM-based relevance judge, in around 40% to 50% of the cases; they also exhibit strong self-preference towards their own and same-family re-rankers, as well as cross-family bias.

cs.IR↗
arXiv2026

Towards Two-Stage Counterfactual Learning to Rank

Counterfactual learning to rank (CLTR) aims to learn a ranking policy from user interactions while correcting for the inherent biases in interaction data, such as position bias. Existing CLTR methods assume a single ranking policy that selects top-K ranking from the entire document candidate set. In real-world applications, the candidate document set is on the order of millions, making a single-stage ranking policy impractical. In order to scale to millions of documents, real-world ranking systems are designed in a two-stage fashion, with a candidate generator followed by a ranker. The existing CLTR method for a two-stage offline ranking system only considers the top-1 ranking set-up and only focuses on training the candidate generator, with the ranker fixed. A CLTR method for training both the ranker and candidate generator jointly is missing from the existing literature. In this paper, we propose a two-stage CLTR estimator that considers the interaction between the two stages and estimates the joint value of the two policies offline. In addition, we propose a novel joint optimization method to train the candidate and ranker policies, respectively. To the best of our knowledge, we are the first to propose a CLTR estimator and learning method for two-stage ranking. Experimental results on a semi-synthetic benchmark demonstrate the effectiveness of the proposed joint CLTR method over baselines.

cs.IR↗