Peer Revenue Publish or profit

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science Information Retrieval

cs.IR Watch Information Retrieval

Saturday 26 September

Information Retrieval · Cross-listed from cs.AI

Beyond Dyadic Memory: Interaction-Aware Multimodal Memory with Adaptive Agentic Retrieval for Multi-Party Spoken Conversations

Wenxu Jia, Xize Cheng, Zihan Zhang et al. (+5 more)

Long-term memory enables agents to accumulate information and reason across sessions, yet existing research primarily focuses on dyadic text or image-text conversations, leaving long-term memory for multi-party spoken conversations underexplored. This setting requires preserving conversational content, identifying participants across sessions, and retaining who speaks to whom. To this end, we propose VoxPolyMem, an interaction-aware multimodal memory framework combining incremental speaker identification with a memory hierarchy comprising interaction memory, fact memory, and participant profiles. We formulate retrieval as sequential decision-making, where an agent rewrites queries and selects retrieval tools and memory layers based on accumulated evidence to address information gaps. We further introduce Evidence-Gain GRPO (EG-GRPO), which uses round-wise credit assignment to encourage complementary evidence acquisition. We also construct VoxPolyBench to evaluate memory evolution, personalized answering, memory retrieval and reasoning, and interaction reasoning and attribution in multi-party spoken conversations. VoxPolyMem achieves an overall score of 85.0 on VoxPolyBench, surpassing the strongest evaluated baseline by 23.6 points. On Mem-Gallery and H2HMem-Multi, it scores 89.6 and 74.4, respectively, exceeding the strongest evaluated public memory baselines by over 8 points each. These results highlight its potential for persistent, personalized assistance in multi-party multimodal interactions. Code and datasets are available at https://voxpolymem.github.io/VoxPolyBench/demo/
Read the full abstract

All authors Wenxu Jia, Xize Cheng, Zihan Zhang, Dongjie Fu, Linjun Li, Wenshi Chen, Yangyang Wu, Tao Jin

Information Retrieval

When Does Dense Retrieval Need Asymmetric Geometry? A Bias-Variance Theory of Shared and Dual Projections

Maojun Sun, Yancheng Yuan, Jian Huang et al. (+1 more)

Dense retrieval powers retrieval-augmented generation, semantic search, and question answering, yet the theoretical basis for choosing between shared and dual query-document projections remains unclear. We introduce a bias-variance theory for low-rank bilinear scoring. Shared projections induce positive-semidefinite operators, whereas dual projections realize arbitrary low-rank operators. We derive their exact approximation gap and prove a local Gaussian boundary: dual has lower risk exactly when squared directional signal exceeds the estimation cost of its additional degrees of freedom. This boundary motivates the Cross-fitted Asymmetry Risk Selector (CARS), which estimates reproducible directional signal from training pairs; its Gaussian counterpart admits exact selection-power and regret formulas. Guided by the theory, we run retrieval experiments across multiple datasets and embedding models. The mean Dual-minus-Shared NDCG@10 advantage more than doubles as query rotation increases from 0 degrees to 90 degrees. In the rank-sample-size grids, Shared wins 13 of 16 cells at n=32, whereas Dual wins all 32 cells at n=1024 and n=2048. Consistent with this shift, all 168 comparable operator-risk curves move toward Dual as training data grow. Compared to the two fixed-geometry baselines, CARS reduces held-out regret by 49-96% and achieves 90.1% mean geometry-selection accuracy.
Read the full abstract

All authors Maojun Sun, Yancheng Yuan, Jian Huang, Ruijian Han

Information Retrieval · Cross-listed from cs.LG

Graph Memory: Spectral Associative Memory via Dirichlet Energy

Zhaoyang Shi

Dense associative memories have traditionally focused on storing and retrieving vector-valued patterns. Many modern machine learning problems, however, are naturally graph-structured, requiring memory mechanisms for relational patterns, graph diffusion geometries, community structures, and graph-based inductive biases. We propose a spectral dense associative memory for storage and retrieval of graph data, extending the classical vector-valued memories. Retrieval is performed through a log-sum-exp energy induced by Dirichlet energy with spectral norm distances, producing a softmax-weighted average of the stored Laplacians that remains a valid graph Laplacian. We prove exponential storage capacity and exponentially decaying retrieval error. Beyond graph retrieval, we establish theoretical guarantees for spectral quantities central to graph learning, including eigenvalues, eigenspaces, and diffusion operators. Experiments on synthetic graph data, real-world airline network, protein conformation data and wearable sensor data demonstrate robust graph retrieval while preserving the graph geometry of the data. Our framework provides a new associative memory paradigm for graph-structured data and bridges dense associative memory with modern graph learning and generative AI.
Read the full abstract

Information Retrieval · Cross-listed from cs.LG

DP-Rec: Towards Dynamic Patching for Efficient Long-Sequence Recommendation

Dwipam Katariya, Thomas Caputo, Akshat Shreemali et al. (+6 more)

Transformers have redefined sequential recommendation by effectively modeling dynamic user behaviors and long-range dependencies. However, they remain inherently inefficient: standard architectures operate at a fixed rate, allocating comparable computation to every item in a user's history regardless of its information content. This leads to prohibitive computational overhead on long sequences and increased sensitivity to behavioral noise. To address this, practitioners often resort to lossy sequence compression, staged modeling, or truncation. This limits the model's ability to leverage the full context of long histories during inference. Inspired by the recent success of Byte Latent Transformer, we propose DP-Rec, a dynamic latent patching architecture for recommendation. DP-Rec shifts from item-level modeling to patch-level modeling by segmenting interaction sequences using contrastive entropy surprise to identify informative behavioral boundaries. A lightweight patch encoder compresses these temporally contextualized segments into a reduced set of dynamic latent behavior vectors, which are then processed by a larger latent transformer and decoded for next-item prediction. Extensive experiments show that, under constrained computational budgets, DP-Rec scales effectively to long sequences and achieves a superior efficiency-accuracy trade-off over both non-compressed and fixed-size compression baselines.
Read the full abstract

All authors Dwipam Katariya, Thomas Caputo, Akshat Shreemali, Juan Manuel Origgi, Nikita Seleznev, Pranab Mohanty, Kalanand Mishra, Nam Nguyen, James Montgomery

Information Retrieval · Cross-listed from cs.LG

Rethinking Cross-Channel Importance in Time-Series Forecasting

Yong-Hoon Choi, Kwang-Hyun Park and Youngjin Cho

Cross-channel modeling is central to multivariate time-series forecasting, yet channels that are statistically related, predictively useful, and actually used by a trained forecaster are often treated as if they defined the same notion of importance. We show that they need not coincide. Cross-channel dependency structures change substantially across future offsets, and horizon-adaptive source selection improves a controlled Ridge predictor in 21 of 32 dataset–prediction-length conditions, with a mean gain of $5.16\%$. This selected-set signal also transfers to a matched nonlinear predictor. Yet imposing the same horizon-specific source logic on iTransformer yields only 11 of 20 wins and a mean gain of $0.208\%$, with little alignment between controlled and neural gains. Functional interventions further show that strong forecasters use cross-channel information, while their source-reliance rankings agree little with controlled utility or with one another across iTransformer, TimesNet, and a cross-channel TimeMixer. As a constructive consequence, bounded post-hoc support improves a frozen channel-independent forecaster in 12 of 16 dataset–horizon conditions, with a positive aggregate bootstrap interval. Cross-channel importance should therefore be interpreted relative to the forecasting mechanism and question that define it: related $\neq$ useful $\neq$ used.
Read the full abstract

Friday 25 September

Information Retrieval

Do Evidence-Reading Diagnostics Improve Interface Selection in Small LLM Recommenders?

Han Chen and Yingrui Li

Behavioral tests measure how a language model reads evidence. We ask whether those measurements help choose a recommendation interface. We evaluate six small instruction-tuned checkpoints across four recommendation domains with chronological evaluation and 3,426 evaluation users. Each request ranks eight candidates. A baseline selector chooses among history-only prompting, prompting with collaborative evidence, and score fusion. It uses observable features and six stability prompts that vary wording and candidate order. An augmented selector adds features from six evidence-reading prompts that ask the model to compare support counts. An interface chosen once on development (validation) data for each domain and checkpoint scores 0.5524 NDCG@5, compared with 0.5447 for the baseline selector and 0.5428 for the augmented selector. Adding the diagnostic features changes NDCG@5 by -0.0019 (95% interval [-0.0046, 0.0004]). The interval includes zero, and its upper bound is below the analysis plan's 0.005 improvement target. Matching the selectors' hyperparameters also leaves the interval upper bound below that target. Evidence from retrieved similar users improves prompting by 0.0999 NDCG@5 over a control using randomly selected users matched for activity. The evidence-reading tests also reveal answer-position and tie-response biases. These results concern the tested selectors and candidate sets. They illustrate why diagnostic measurements should be evaluated by whether they improve recommendation choices beyond existing features and a fixed interface.
Read the full abstract

Information Retrieval · Cross-listed from cs.MA

On Evaluating and Improving Conversational Agents in Production

Kasra Hosseini, Wen-Sen Cheng, Marco-Andrea Buchmann et al. (+2 more)

We present a framework for evaluating and improving a large-scale, multi-agent shopping assistant in production, and report lessons from its use. Offline evaluation of such a system faces three obstacles. (i) A logged conversation cannot be replayed against a modified system, because a different response changes every turn that follows. (ii) The unchanged system itself varies from run to run. Its LLM components are stochastic, and in product search the available products, their prices, and the customer's personalization signals change. (iii) Aggregate quality scores combine distinct behaviors, so they show that quality has changed but not which behavior caused the change. Our framework addresses each obstacle in turn. For a reported behavior, an Evaluation Harness generates targeted assertions and a fixed cohort of customer scenarios. It then reproduces the behavior in a local instance of the assistant through grounded user simulation. Instead of replaying the log, the simulator writes new customer turns conditioned on the recorded messages and context. Repeated runs of the unchanged system form a stored baseline. An Improvement Orchestrator turns the assertion results into hypotheses, implements each as an isolated modification, and compares it with the baseline using paired percentile bootstrap intervals over scenario-level differences. When an investigation ends, the harness may propose revisions to future evaluations, subject to human approval and without altering past decisions. We report production investigations with this framework. Assertion profiles showed which positions of a product carousel a failure affected, and repeated runs distinguished a real improvement from run-to-run fluctuation. Audits of the evaluation itself found a judge that lacked the evidence it needed and a model setting that was configured but not applied.
Read the full abstract

All authors Kasra Hosseini, Wen-Sen Cheng, Marco-Andrea Buchmann, Emir Mulabegovic, Weiwei Cheng

Information Retrieval · Cross-listed from cs.AI

EngramRAG: Dynamic Usage-Weighted Topology and Synaptic Consolidation for Multi-Hop Agentic Memory

Bhavyateja Potineni, Lohit Giri, Anu Jain et al. (+2 more)

As autonomous LLM agents are deployed across multi-session environments, conventional memory architectures suffer from Associative Blindness (inability to traverse multi-hop relational dependencies), Scaffolding Amnesia (temporal decay evicting core persona invariants), and Static Topology Stagnation (immutable graphs ignoring usage dynamics). Grounded in Complementary Learning Systems (CLS) principles, we propose EngramRAG, an adaptive memory architecture coupling a low-latency Waking State reflex with an asynchronous background Dreaming State consolidation cycle. EngramRAG introduces: (1) Usage-Modulated Personalized PageRank (U-PPR), where transition probabilities adapt via Hebbian plasticity to promote persistent entities into high-centrality Epistemic Macro-Hubs; (2) Consolidation-Activated Topology Decay (CATD), which scales retention half-life by topological load-bearing weight rather than wall-clock recency, protected by a cold-start grace period (N_grace >= 4); (3) Directed SUPERSEDES DAG filtering to suppress obsolete state during fact mutations; and (4) Triple-source hybrid retrieval fusing dense vectors, BM25, and U-PPR via dynamic Reciprocal Rank Fusion (RRF). Evaluating on all 1,982 QA pairs across 10 long-term conversations in the LoCoMo benchmark, EngramRAG achieves +38.9% relative improvement in Recall@5 (53.21% vs. 38.29%, p < 0.001) and +43.1% in MRR (0.4203 vs. 0.2937) over dense vector RAG, significantly outperforming Okapi BM25 (48.66%) and isolated static graph retrieval (8.50%). On temporal reasoning, EngramRAG reaches 62.33% Recall@5 (+16.67 points over dense vectors). In controlled mutation tests, SUPERSEDES suppresses split-brain hallucinations from 70.0% to 0.0%, while 90-day simulations show 100.0% scaffolding retention under a 26.21ms interactive retrieval reflex.
Read the full abstract

All authors Bhavyateja Potineni, Lohit Giri, Anu Jain, Vadim Kutsyy, Rajasekhar Pentakota

Information Retrieval · Cross-listed from cs.CV

Amnesia by Design, Memory By Necessity: Persistent State for Document Intelligence

Souhail Bakkali and Ayoub Merimi

Modern Document AI reads contracts, extracts fields, reasons over tables, and grounds answers to page regions, then forgets everything. Processing an amendment the next day begins from scratch: no schema retained, no contradiction detected, no experience carried forward. This is a structural choice, not a scale failure: current systems are stateless functions. We call this the statelessness bottleneck. This bottleneck lies beyond parameter scaling, context extension, and retrieval augmentation: storage provides persistence and retrieval provides access, but neither consolidates observations into knowledge that improves future processing. This survey formalizes persistent evidence-grounded document state as a unifying framework, specifying the operations and invariants required to convert multimodal evidence into durable, provenance-linked state. We introduce a statefulness audit showing that ten representative benchmarks, coded against eight statefulness criteria, leave cross-session state evolution untested, and derive a longitudinal benchmark harness with five counterfactual metrics: Experience Gain, Cost Efficiency, Memory Harm, Forgetting Fidelity, Coverage Retention, to characterize the benefit, cost, risk, and governability of persistent document state. Document AI lacks mechanisms coupling persistent state to document-native structure, provenance, and temporal validity. The next era of Document AI will be defined by what systems retain across documents, sessions, and time.
Read the full abstract

Information Retrieval

Recipe-Matching, Not Equivalence

Ali Habibullah, Mohammad Alshiekh, Yazan Alshoibi et al. (+2 more)

MathNet-Retrieve asks a retriever to find, for a math problem, a document stating the same problem. An LLM under one fixed prompt writes each gold document and its near-miss distractors; LLM judges filter them. We call this procedure the "recipe", training on pairs built the same way "recipe-matching", and ask how much score it buys beyond the ability the benchmark claims to test. Two models from one base, matched in rows and settings, differ only in the training file: pairs written under the benchmark's published prompt by another vendor's LLM and judge, or computer-algebra-verified pairs with no LLM anywhere. The first leads by 45 R@1 points on the easy tier. By a non-LLM paraphrase control, half to two thirds of that gap comes from the pairs being LLM-written at all: LLM rewrites under two unrelated prompts, with the verified model's negatives, recover 30 and 22 of the 45 points; back-translations with the same negatives recover almost none. The remaining 15 to 25 points appear only under the benchmark's own prompt and vanish on real duplicates no generator wrote, the same problem in two languages. The hard tier rewards the recipe's pair structure, a deep rewrite against a minimal-edit near-miss: LLM rewrites alone score zero on it, attaching negatives unlocks it, and every negative that does so costs cross-language points; the sets scoring highest on it separate near-misses no LLM wrote worse than LLM rewrites with verified negatives. MELD also moves when a model trains on pairs built its way, without losing retention; on SABER-Math the registered attack fails, and the one gain, from its LLM-written summaries, is small but holds at a matched budget. Only on MathNet-Retrieve could we pin an inversion, benchmark score up and real retention down, to one edit of a training file. We release the generator-free duplicate evaluations, the near-miss test and three trained models.
Read the full abstract

All authors Ali Habibullah, Mohammad Alshiekh, Yazan Alshoibi, Salman Khan, Naeemullah Khan

Information Retrieval

Overview of the TREC 2025 Million Large Language Models track

Evangelos Kanoulas, Panagiotis Eustratiadis, Jamie Callan et al. (+5 more)

Agentic AI envisions ecosystems of intelligent agents collaboratively solving complex tasks with minimal human intervention. In such ecosystems, each agent possesses specialized expertise, making effective expert selection central to overall system performance. While most current approaches assume a small number of well-documented models, real-world expertise is far more diverse and cannot be adequately captured through static metadata or hand-written descriptions. We anticipate a future with millions of specialized language models (LLMs), each excelling in different domains or problem types. Rather than relying on predefined capability statements, we propose a retrieval-based paradigm in which an assistant agent infers expertise dynamically by examining models' observable behavior. Upon receiving a user query, the assistant ranks candidate LLMs based on demonstrated competence, enabling efficient and adaptive expert selection. The TREC Million LLM Track operationalizes this paradigm by shifting the retrieval target from documents to expert LLMs. Participants are given a discovery set consisting of queries, answers, and log-probabilities from more than one thousand LLMs and are challenged to infer meaningful expertise representations for each model. Given an unseen test query, systems must then rank the LLMs according to their expected performance, providing the first large-scale benchmark for expertise retrieval in agentic AI.
Read the full abstract

All authors Evangelos Kanoulas, Panagiotis Eustratiadis, Jamie Callan, Mark Sanderson, Yongkang Li, Jingfen Qiao, Gabrielle Poerwawinata, Vaishali Pal

Information Retrieval · Cross-listed from cs.LG

FARE: Deep Reinforcement Learning For Fair Exposure Constrained Uncertainty Aware Financial Content Personalization

Arundeep Chinta, Lucas Vinh Tran and Jay Katukuri

Content personalization systems in financial services must ensure fair exposure across diverse offerings-a requirement driven by contractual obligations and the need to prevent "rich-get-richer" dynamics where content with high click-through rate (CTR) dominates while other relevant products receive minimal visibility. Share of Voice (SOV) constraints, which guarantee each content category a target fraction of top-position exposure, address this by promoting product diversity and balanced user discovery. While re-ranking layers atop CTR models are common in practice, we propose two key novelties: (1) framing SOV-constrained ranking as a deep reinforcement learning problem analogous to constrained trade execution in algorithmic finance, and (2) explicitly incorporating CTR prediction uncertainty into the agent's state space and policy design-enabling larger ranking adjustments for high-uncertainty predictions where deviation from CTR-optimal ordering is less costly. We introduce FARE (Fair Ranking Executor), a modular uncertainty-aware execution layer that translates any black-box CTR model's predictions into SOV-fair rankings without retraining the underlying model. Our uncertainty-weighted proportional control policy (FARE-PC) and learned neural policies (FARE-ES, FARE-PPO) demonstrate that uncertainty-aware approaches can substantially reduce SOV deviation from fairness targets while minimizing engagement loss, with gradient-free evolution strategies outperforming policy gradient methods on synthetic data and the ordering reversing on KuaiRand-Pure.
Read the full abstract

Information Retrieval

Retail Product Search: A Practical Approach at Target

Darshan Sonagara, Qujiaheng Zhang, Ankit Singh et al. (+1 more)

Search is one of the most important features in e-commerce, directly driving customer engagement and business growth. A good product search system must show both relevant and desirable results. However, retail search presents unique challenges. User intent can range from exact matches to open-ended discovery. Search systems must also balance multiple goals, such as relevance, revenue, and profit, while keeping response times low. Traditional keyword-based methods often fall short in handling natural language or semantic queries. Vector search helps alleviate these issues, but it can miss key intent signals or return low-precision results. In this paper, we present the design of a hybrid search system at Target that combines lexical and vector search. We describe our approach to data processing, embedding training, precision control for the final result set, multi-channel result fusion (where we compared fusion strategies and adopted weighted interleaving), and the performance optimizations used to maintain low latency for production deployment. Our method improves offline evaluation metrics, and in online A/B testing it raised click-through rate by 0.97%, order conversion by 0.98%, and demand per visitor by 1.10% over lexical-only search, while roughly halving zero-result searches. The resulting system is deployed at scale and serves millions of guests daily.
Read the full abstract

All authors Darshan Sonagara, Qujiaheng Zhang, Ankit Singh, Alex Li

Information Retrieval

Enriching Sequential Recommendation with Graph Laplacian Positional Embeddings

Ekaterina Trushkova, Artur Gimranov and Anton Lysenko

Sequential recommenders typically rely on learnable positional embeddings to encode the order of user interactions. In this work, we ask whether this ordinal signal can be replaced by a structural one derived from the item space. We propose to use Laplacian positional embeddings in SASRec: we build an item co-occurrence graph from training interactions, compute eigenvectors of its symmetric normalized Laplacian, and use them as frozen graph-derived positional embeddings. The backbone architecture and training objective remain unchanged. Experiments on four public sequential-recommendation benchmarks show that this simple replacement improves SASRec performance on most ranking metrics and remains competitive with strong positional and temporal encoding baselines. These findings indicate that item-item graph structure can be an effective substitute for standard ordinal positional embeddings in sequential recommendation.
Read the full abstract

Information Retrieval

AgentRecommender: LLM Agents Enable Customizable Recommender Systems on the User Side

Ryoma Sato

Recommender systems have traditionally been developed for platforms. However, this has given rise to many phenomena that may be advantageous for platform lock-in but are a nuisance to users, such as clickbait, filter bubbles, and the spread of fake news. Recently, user-side recommender systems have been proposed as a new paradigm for solving this problem. If users deploy their own recommender systems, they are no longer at the mercy of the platform's interests. However, building a user-side recommender system is not trivial; in particular, customizing one for oneself requires additional data. We propose AgentRecommender, a method that leverages the investigation capability and internal knowledge of LLM agents to flexibly build user-side recommender systems without additional data. AgentRecommender allows users to easily create recommender systems tailored to their own preferences.
Read the full abstract

Information Retrieval

SPADE: Escaping the Popularity-Similarity Frontier to Measure Serendipitous Recommendations

Tobias Vente, Maarten Peirsman, Noah Daniëls et al. (+2 more)

Recommender systems engineer serendipity to foster active exploration and break predictable consumption cycles. The problem with existing offline beyond-accuracy metrics is that they often either isolate historical similarity or global popularity. We aim to design an evaluation metric that examines similarity, popularity, and actual user relevance. To achieve this, we introduce SPADE (Serendipitous Pareto Distance Evaluation). SPADE maps all items into a two-dimensional space to directly calculate a user-specific Pareto frontier of maximally popular and historically similar items. The final serendipity score is then computed by averaging the minimum Euclidean distance from this boundary strictly for the correctly recommended test-set items. Evaluating SPADE across five datasets and five baseline algorithms confirms its effectiveness; our results show that the metric successfully prevents algorithms from exploiting beyond-accuracy measures with irrelevant or non-personalized recommendations, reliably isolating serendipitous discoveries.
Read the full abstract

All authors Tobias Vente, Maarten Peirsman, Noah Daniëls, Hannu Toivonen, Bart Goethals

Information Retrieval · Cross-listed from cs.CL

CG-Probes: Recovering Guardrail Directions from Patient Query Embeddings

Marko Řeháček, Vítězslav Dušek, Martin Rusinko et al. (+1 more)

Patient-facing AI assistants promise valuable support to patients, but incoming queries can pose medical risks. To create guardrails, we work with oncologists to define three ordinal risk axes: Medical Urgency, Psychological Urgency, and Topic Sensitivity. We propose Clinical Guardrail Probes (CG-Probes) to measure the risks from query embeddings. We probe for each axis in the normalized embedding space of frozen embedders via the difference-in-means method, treating each axis as a potential linear direction. To train the probes, we cluster 79,658 Czech oncology search queries with BERTopic and use these clusters to generate pairs of queries with contrastive risk levels via few-shot prompting. We evaluate the approach on 200 queries (90 real, 110 synthetic), each graded by two oncologists, against two open-weight LLMs and a frontier LLM. We find that urgency-based axes are recoverable as linear directions, and the probes are competitive with open-weight LLMs (no significant differences in quadratic-weighted kappa) at a fraction of the latency. Each axis yields a scalar score that clinicians can inspect and use to set escalation thresholds. The pipeline requires only search logs, axis definitions, and black-box access to the embedding model, suggesting transferability across healthcare domains. Robust validation on new queries and axes remains future work.
Read the full abstract

All authors Marko Řeháček, Vítězslav Dušek, Martin Rusinko, Vít Nováček

Information Retrieval

KuaFu: Compressing Long User Behavior into Understanding at Billion Scale

Jiahao Hui, Lin Zhu, Yishen Hu et al. (+8 more)

Conversational agents, generative recommenders, and personalized advertising all rest on one capability: understanding each user from raw behavior. Prevailing industrial practice is task-specific: for each task, a relevant subsequence is extracted from the full history and a dedicated model trained on it. In production it hits two bottlenecks. First, even after filtering, a single-task sequence stays extremely long: content-interest summarization reads several hundred items per user, tens of thousands of tokens once serialized as prompt text. Second, profiles are refreshed routinely: a billion users weekly, roughly 100K QPM in aggregate, which under a fixed GPU budget sets a hard throughput floor. Compression is therefore mandatory, yet truncation or coarse compression can silently distort the profile, introducing four hallucination types (fabrication, omission, date misattribution, broken logic) that, with no way to evaluate the compressed representation itself, surface only as diffuse degradation in downstream metrics. We present KuaFu, a unified behavior-compression layer whose minimal unit is one behavior item. A two-axis projector compresses each item into 2-4 tokens of width 128-256 (about 10x along the token axis, 20x along width; per-item cache 10 KB to 0.5 KB), with fidelity-oriented four-stage training and layered intermediate evaluation. Across four production profiling tasks it matches or exceeds uncompressed single-task production models on all five headline metrics, raises per-GPU throughput by 37%-350%, and saves 190 GPUs. On public benchmarks it nearly always beats prior compressors at the same compression ratio (up to +17.7 EM on out-of-domain MRQA); on RecBench, a 4B model surpasses its 8B counterpart by 1.90 points. KuaFu has run on the Tencent advertising and recommendation platform for ten months, lifting overall GMV by 1.37%.
Read the full abstract

All authors Jiahao Hui, Lin Zhu, Yishen Hu, Jingdong Shu, Zetai Jiang, Xining Ran, Ben Tan, Yeshou Cai, Gong Chen, Haijie Gu, Jie Jiang

Information Retrieval

QReason: Query-Focused Decoupled Chain-of-Thought for Efficient Passage Reranking

Yang Zhang, Wenhan Liu, Qiannan Zhu et al. (+2 more)

Passage reranking plays a crucial role in information retrieval by refining the ordering of candidate passages to better reflect relevance. Existing listwise LLM rerankers with Chain-of-Thought (CoT) reasoning can handle complex queries effectively, but they suffer from substantial redundancy and high latency due to sliding-window strategies, which repeatedly generate highly similar CoTs. To address this, we propose QReason, a decoupled framework that separates query-focused reasoning from window-specific passage relevance assessment. Specifically, QReason introduces a dedicated rewriter that generates a ranking-oriented reasoning query once, capturing the query's core intent while avoiding redundant reasoning, and then reuses it across all windows with a non-reasoning reranker. The rewriter is trained via a two-stage process that first uses supervised fine-tuning with relevant-passage guidance through semantic evidence to produce deeply grounded, query-focused CoTs. It then applies reinforcement learning to align CoT generation with both the inference-time setting and the reranking objective, optimizing listwise metrics and passage-level discrimination to produce reusable reasoning chains for reranking. Experiments on the BRIGHT benchmark demonstrate that QReason significantly reduces redundant reasoning, achieves ranking performance comparable to or better than strong reasoning-based rerankers, and outperforms existing query rewriting models.
Read the full abstract

All authors Yang Zhang, Wenhan Liu, Qiannan Zhu, Mingming Li, Yuanfei Huang

Information Retrieval

RecToolBench: Benchmarking Recommendation-Specific Tool Orchestration under Fuzzy User Intent

Xiao Chen, Yicheng Zhao, Yingying Wu et al. (+4 more)

Recent advances in agentic recommender systems are shifting recommender systems from passive filtering engines to instruction-following agents that use external tools to resolve user intent. However, existing benchmarks often assume explicit user intent, simplified tool environments, or isolated function calls, leaving realistic tool orchestration for recommendation underexplored. To bridge this gap, we propose RecToolBench, a Model Context Protocol (MCP)-based benchmark for evaluating tool-using recommender agents under fuzzy user instructions. RecToolBench contains more than 1,200 executable tasks across three recommendation domains, 13 MCP servers, and 32 tools, spanning single-tool calls, parallel tool calls, sequential tool chains, and hybrid tool orchestration. We construct RecToolBench with a scalable synthesize–fuzzify–judge pipeline that generates executable fuzzy recommendation tasks, and evaluates agent trajectories using rule-based execution checks and rubric-based LLM evaluation. Experiments on representative LLMs show that syntactically valid tool calls do not guarantee successful recommendations. Models struggle with semantic parameter grounding, multi-step evidence integration, and grounded final recommendations, especially as orchestration complexity increases. Our results identify tool orchestration under fuzzy user intent as a major bottleneck for agentic recommender systems. Our data and code are available at https://github.com/ShawnChenn/RecToolBench.
Read the full abstract

All authors Xiao Chen, Yicheng Zhao, Yingying Wu, Zhendong Chu, Changyi Ma, Qingsong Wen, Xuan Song

Information Retrieval

Recommendation World Models for Future-State Control

Jinfeng Xu, Zheyu Chen, Ziyue Peng et al. (+6 more)

Sequential recommendation optimizes which items to rank, while each displayed slate also shapes subsequent feedback and user state. We study how a trained ranker can support decisions about these future consequences. We introduce UA-TWM, a utility-anchored world-model interface that constructs nearby slate actions, estimates their target-relevant consequences, and selects an alternative subject to utility constraints. The reference slate serves as a fallback when no alternative qualifies. A logged-replay instantiation combines utility and target-gain estimates with calibrated failure-risk prediction; a closed-loop instantiation uses one-step state-action prediction and updates its decisions after observed feedback. We evaluate transfer across twelve sequential backbones on MovieLens-25M and KuaiRand-Pure, and repeated target-directed interaction in KuaiSim. Attaching the interface improves Recall@20, NDCG@20, and future-state alignment for every matched logged backbone. Selection ablations reveal the utility and risk costs of aggressive target pursuit, while closed-loop diagnostics isolate the contribution of action-conditioned prediction. Local consequence modeling thus enables target-aware selection around a trained sequential ranker.
Read the full abstract

All authors Jinfeng Xu, Zheyu Chen, Ziyue Peng, Jianheng Tang, Zheng Lin, Jing Yang, Puzhen Wu, Zheng Xing, Victor C. M. Leung

Information Retrieval

Component Benchmark: Hierarchical Model Profiling for Large-scale Recommendation Systems

Dharak Kharod, Yuzhen Huang, Zhou Wang et al. (+11 more)

Large-scale recommendation models pose distinct, under-explored profiling challenges. Most recommendation model architectures are structurally heterogeneous, intermixing memory-bandwidth-bound operations, small compute-bound dense layers, dynamic shapes from jagged categorical features, and low-arithmetic-intensity operations. Recommendation models evolve rapidly as modeling engineers experiment with compositions, often written without visibility into hardware execution characteristics. Standard profiling tools offer either end-to-end throughput or operator-level traces, but cannot attribute performance to the submodules that practitioners reason about. We present Component Benchmark (CB), a profiling system that independently characterizes each submodule performance in a hierarchical manner, providing a tree-structured, interactive visualization that brings performance clarity to ML practitioners. At its core, CB provides a simple yet extensible, submodule-based benchmarking framework with a plugin architecture that enables hierarchical performance analysis. These large-scale recommendation models are TB-scale, run on thousands of GPUs and ingest 100B examples per day. We demonstrate CB's effectiveness on common open sourced models and discuss how CB has been leveraged to accelerate modern recommendation model performance analysis and optimization.
Read the full abstract

All authors Dharak Kharod, Yuzhen Huang, Zhou Wang, Jackie Xu, Fuzail Khan, Jacky Zhou, Hao Yan, Lidong Zhao, Xizhou Feng, Yvonne Liu, Karthik Jayaraman, Praveen Ramachandran, Vishwa Karia, Yashasvi Makin

Thursday 24 September

Information Retrieval · Cross-listed from cs.HC

Epstein Files Engine: Agentic Search for Investigative Journalism

Duy K. Nguyen, Teresa Mondría Terol, Dylan Freedman et al. (+1 more)

On Jan. 30, 2026, the U.S. Department of Justice released a mixed-media collection concerning Jeffrey Epstein, including about three million pages of PDFs. We describe the Epstein Files Engine, an A.I. agent The New York Times deployed to investigate the files. The Engine translated reporter questions into Google BigQuery SQL queries across three corpora: Epstein-related releases, the Times's archive and external, Epstein-related news headlines. It used an LLM to plan queries and returned citation-rich answers a reporter could verify and trust. More than 100 journalists used the Engine, and it contributed to at least 20 published stories. We report how reporters queried it and describe Diff, our text-and-visual duplicate matching method that amplified novelty signals and allowed the Engine to surface genuinely new information. We argue that newsroom agents serve newsrooms best not as autonomous writers, but as interfaces to source material and institutional knowledge.
Read the full abstract

All authors Duy K. Nguyen, Teresa Mondría Terol, Dylan Freedman, Zach Seward

Information Retrieval

Embedding Subspace Partitioning for Dynamic Multi-Objective Retrieval

Shaobo Zhang, Alice Leung, Yunxiang Ren et al. (+13 more)

Modern industrial recommender systems must optimize across competing objectives, balancing semantic relevance with business metrics such as engagement and revenue. While bi-encoders dominate large-scale retrieval due to their efficiency, they collapse these heterogeneous signals into a single static embedding space. This design creates a fundamental limitation: once trained, the retriever cannot adapt to shifting objective priorities at serving time without retraining. Moreover, joint optimization with multi-objective losses often induces interference between objectives, leading to suboptimal trade-offs. We propose Embedding Subspace Partitioning (ESP), a retrieval framework that decomposes the embedding into task-aware subspaces and replaces the single dot product with a weighted sum of per-subspace similarities, whose weights are tunable at serving time. For Transformer bi-encoders, ESP uses the model's native end-of-sequence token as a segment delimiter, with segment-aware attention masking and position encoding resets to guarantee subspace isolation in a single forward pass. Serving is performed via GPU-accelerated exhaustive kNN over one concatenated index, eliminating the need for per-objective Approximate Nearest Neighbor (ANN) infrastructure required by multi-head approaches. We evaluate ESP on an open-source benchmark built from MS MARCO. A single ESP model traces a broad Pareto frontier, consistently outperforming strong multi-task baselines across diverse operating points. In LinkedIn's job matching platform (70M+ weekly users), ESP enabled dynamic retrieval reconfiguration and delivered significant key business metric lifts.
Read the full abstract

All authors Shaobo Zhang, Alice Leung, Yunxiang Ren, Ping Liu, Yuchin Juan, Qianqi Shen, Benjamin Le, Jianqiang Shen, Chengming Jiang, Ko-Cheng Wang, Vidya Krishnamurthy, Caleb Johnson, Fedor Borisyuk, Luke Simon, Jingwei Wu, Wenjing Zhang

Information Retrieval · Cross-listed from cs.AI

T-RoPE: Time-Aware Rotary Position Embedding for Sequential Recommendation

Yang Liu, Noel Loo, Ali Khanafer et al. (+4 more)

Large-scale recommenders increasingly adopt the sequential generative recipe behind large language models, bringing the Transformer into recommendation along with design choices made for text, including Rotary Position Embedding (RoPE). In language models, RoPE encodes token indices for relative position reasoning, but in recommendation, an interaction index records only event order, saying nothing about elapsed time, behavioral cycles across scales, or calendar phase. We revisit this choice and propose T-RoPE, a time-aware RoPE for sequential generative recommendation that replaces index-only rotation with timestamp-based angles, learnable temporal coefficients, multiscale frequency banks, shifted query alignment, and non-stationary key rotation. We prove that standard RoPE, even on timestamps, remains time-translation invariant and cannot distinguish seasonal contexts, and that T-RoPE breaks this invariance while preserving the RoPE interface. Across five public benchmarks, T-RoPE achieves the best result on every metric on every dataset, improving over the strongest baseline by 78–130% in HR@10 on the sparse PixelRec data and 8–12% across metrics on Amazon Books. On an industrial-scale e-commerce dataset with more than 6B interactions, it improves every metric over the HSTU + Time RAB backbone by 13–82%, with ablations attributing the largest gains to multiscale frequencies ($+56\%$ NDCG@50) and non-stationary keys ($+4\%$). An online A/B test in the Shop app yields positive lifts in conversion rate ($+0.33\%$) and order count ($+0.63\%$). We also provide forward and backward algorithms whose added cost is linear in sequence length and head dimension, keeping time-aware RoPE practical for large generative recommenders.
Read the full abstract

All authors Yang Liu, Noel Loo, Ali Khanafer, Shuying Sun, Akshay Soni, Zhong Wu, Linjun Yang

Information Retrieval

Nearest but Not Dearest: Shared Curator-Feedback Infrastructure for Content-Only Search and Recommendation

Matt Sandler

A deployed B2B music-discovery platform serves both query-driven search (text prompts, vibe tags) and seed-driven recommendation (seed-track and artist stations) over one licensed catalog, one LAION-CLAP joint audio-text embedding space, one candidate-generation filter, and one ranking head – and neither path consumes end-listener behavioral signal. In this content-only regime, curator judgment is the principal feedback signal available, and offline cosine similarity predicts it poorly: 38% of cosine-nearest neighbors are rejected by curators. The rejections reveal a clean partition: a majority (55%) are sound failures the encoder could address (style, tempo, mood mismatch), and a substantial minority (37%) are context failures orthogonal to the waveform (wrong language, holiday content, devotional content, rights and lyric flags). We deploy this sound-vs-context decomposition as feedback infrastructure, routing each failure mode to the layer that can absorb it: context failures to a constraint filter at candidate generation, sound failures to an embedding reweighting head at the representation layer – both below the search/recommendation split, so a single curator loop maintains both experiences. On 1,200 curator judgments collected over two production rounds one month apart, the combined intervention reduces rejection rate from 38.17% to 28.83% (-24.5% relative, McNemar chi-squared = 22.4, p = 2.2e-6). An accounting decomposition attributes 4.08 pp of the drop to filter-eligible categories and 5.25 pp to the rest; the deployment was unblinded and compound, so this is a production accounting bound, not a causal estimate. We present this as an industrial case study rather than a validated general method, and close with lessons for content-only discovery: the failure partition is orthogonal to the paradigm partition, and corrections land in layers shared by both paradigms.
Read the full abstract

Information Retrieval · Cross-listed from cs.CL

REALMS: An AI-Assistant Conversational System for Real-Time Exact Audience Sizing over High-Dimensional Nested Profiles

Haixu Ma, Aditya Bansal, Shubham Lohiya et al. (+1 more)

Audience sizing is a critical component of digital marketing. It enables precise resource allocation, campaign planning, and performance optimization. Traditional approaches using skeleton audiences, sampling, or predictive modeling suffer from significant delays, estimation errors, and poor scalability over high-dimensional profile data. We present REALMS (Real-time Exact Audience sizing via LLM-based Multi-attribute Search), a conversational system for exact audience sizing deployed in production on an enterprise customer data platform. REALMS enables marketers to query massive profile stores with millions of profiles and thousands of attributes using natural language and receive precise counts in seconds. The system introduces three key components: (1) a categorical attribute retrieval mechanism using embedding-based vector search to dynamically identify relevant schema attributes without manual configuration; (2) an LLM-powered NL2SQL pipeline with template-based in-context learning for accurate query generation over complex nested schemas; and (3) schema standardization enabling industry-agnostic deployment across diverse enterprise environments. Evaluation on real enterprise data demonstrates strong recall for attribute retrieval, high SQL execution accuracy, and low latency, which enables real-time interactive audience insights where prior methods required hours.
Read the full abstract

All authors Haixu Ma, Aditya Bansal, Shubham Lohiya, Sumit Ranjan

Information Retrieval · Cross-listed from cs.LG

AutoResearch at Production Scale: Failure Modes and a Multi-Agent Framework

Aparajith Chandran, Juwon Kim, Saurav Jha et al. (+2 more)

Optimizing embedding systems for production recommendation pipelines demands systematic exploration that consumes disproportionate engineering effort at scale. We apply Andrej Karpathy's AutoResearch paradigm – a large language model that iteratively edits a training script and retains modifications that improve a held-out scalar metric – to automate this exploration. We report on twelve weeks of running this paradigm at production scale, where iterations consume hours of multi-GPU compute, evaluation involves competing criteria, and campaigns span weeks across many training jobs. Across two independently developed representation-learning systems for a book recommendation pipeline, we ran 220+ experiments and observed five recurring failure modes absent from the original setting: infrastructure fragility, agent memory decay, search-direction stagnation, iteration-cost asymmetry, and metric fixation. We contribute a three-principle scaffolding design – prevent, persist, redirect – that maps each failure mode to a structural remedy and whose instantiation scales with iteration cost. The framework produced a 1.82x Recall@6 lift and a 2.1x coherence lift over hand-tuned baselines, and the agent autonomously designed a text-only fallback that expanded catalog coverage by 5.8x. The two systems span nearly three orders of magnitude in per-iteration cost yet exhibit the same failure modes, suggesting these are structural properties of production-scale autonomous research rather than artifacts of either application.
Read the full abstract

All authors Aparajith Chandran, Juwon Kim, Saurav Jha, Pablo Castells, Florian Hottier

Information Retrieval · Cross-listed from cs.CL

Where Does Retrieval-Based Open-Ended Evaluation Fail? Automatic Taxonomy Induction from Long-Form Medical Answer Factuality Verification

Heyuan Huang, Jirui Dai, Alexandra DeLucia et al. (+5 more)

Retrieval-based factuality evaluation, where LLM-generated claims are verified against evidence from authoritative medical corpora, has become the dominant paradigm for scalable hallucination detection in high-stakes clinical settings. Despite the urgency of reliable and transparent medical fact verification, most systems measure performance with aggregate metrics like F1, which obscure where and why failures occur. Existing RAG diagnostics require gold answers or annotated gold evidence, neither of which exists in this regime. We introduce two comprehensive taxonomies, grounded in a case study on the open-ended MedExpert dataset and 3 closed-ended datasets, decomposing failures into retrieval-stage errors along five quality dimensions, and verifier-reasoning errors into six consecutive steps. We adapt an automatic pattern induction pipeline using LLM-as-Judge to label evidence quality and classify verifier reasoning errors at scale, and then stress-test our findings across 4 retrieval methods and 6 frontier verifier models. Our analysis reveals that scaling model size, adding reasoning effort, expanding to authoritative web sources, and applying medical fine-tuning do not resolve these failure modes, demonstrating that they represent fundamental limitations of the retrieve-then-verify paradigm in open-ended medical settings rather than artifacts of outdated systems. We release our code and data at https://anonymous.4open.science/r/Medical_RAG_eval-4AB5 for the full reproducibility of our results.
Read the full abstract

All authors Heyuan Huang, Jirui Dai, Alexandra DeLucia, Sonal Joshi, Mahsa Yarmohammadi, Jie Gao, Bernal Jiménez Gutiérrez, Mark Dredze

Information Retrieval · Cross-listed from cs.CL

Return or Revise? Learning When Revision Helps Retrieval-Augmented QA

Nicholas Kashani Motlagh, Tim Anderson, Jeremy Gwinnup et al. (+1 more)

We consider the decision of whether to return an existing draft answer or revise it using retrieved evidence, as in answer-revision systems. Draft confidence estimates whether the current answer is correct, but the decision requires estimating the effect of a specified revision. For offline training and evaluation, we grade both the returned draft and its candidate revision under the same correctness judge, which makes repair, harm, and the gap to an oracle observable. We call this paired effect its recoverability, and we train policies to predict it before revision. On 25,870 held-out open-domain questions across three revision setups, a scorer trained on the paired outcome has greater area under the accuracy–revision-rate curve than a matched draft-correctness scorer in all nine Llama setup–seed fits, and gains 0.23–0.68 accuracy points on average at development-selected thresholds, a difference significant across training runs only for dense retrieval. The resulting policy improves on always revising and on average closes more than a third of the oracle gap, although it still applies 38–46% of the harmful revisions. When a draft-free standard-RAG answer is also available, however, choosing between the draft and that answer is stronger by about two points for Llama and four for OLMo, and adding candidate revision as a third option yields no significant gain. Recoverability describes one revision; its value as an available action also depends on the alternatives.
Read the full abstract

All authors Nicholas Kashani Motlagh, Tim Anderson, Jeremy Gwinnup, Grant Erdmann