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

Wednesday 30 September

Information Retrieval

KUAISHOU Explorer LLM-Rec Challenge 2026: Reasoning Generative Recommendation

Jiangxia Cao, Hao Peng, Wenlong Xu et al. (+97 more)

Generative recommendation, has been attracted a surge of attentions in industrial and academic research community, towards to build more smart system to build next-generation recommender. Under the significant developing wave of large language model, our team have been developed Semantic ID based OneRec/OneRec-V2. These models have been widely deployed in production and demonstrate the scaling potential of the autoregressive next-item prediction paradigm for industrial recommender systems. Building on the success of OneRec, we further explored a series of models, including OneRec-Think, OpenOneRec, and OneReason, that connect item Semantic IDs with natural language in a unified representation space and seek to unlock the potential of natural-language chain-of-thought (CoT) reasoning for recommendation. However, our preliminary works found that introducing reasoning CoT does not always improve the recommendation performance. To address this issue, OneReason strengthens the semantic alignment between items and language, introduces structured template-based supervision for interest reasoning, and applies advanced reinforcement learning techniques to make reasoning more beneficial to recommendation. As a frontier topic to building recommendation foundation models, we believe this topic has significant research value and hope to encourage more researchers to explore it together. To this end, together with the SIGIR 2026 community, we organized the KUAISHOU Explorer LLM-Rec Challenge 2026: Reasoning Generative Recommendation.
Read the full abstract

All authors Jiangxia Cao, Hao Peng, Wenlong Xu, Jiaxin Deng, Zhixin Ling, Xingmei Wang, Kun Shang, Can Tang, Zhihuai Cai, Jun Du, Fang Su, Xiaojuan Liu, Yiling Li, Chenglong Yu, Chongling Rao, Haixuan Gao, Haitao Xu, Jian Liang, Ruiming Tang, Chenglong Chu, Guohong Mu, Honghui Bao, Hui Wang, Jialong Chen, Jiao Ou, Muhao Wei, Peng Zhang, Renpu Liu, Ruochen Yang, Shugui Liu, Xinqi Jin, Yan Sun, Yifan Wang, Yingzhi He, Yufei Ye, Yusen Huo, Tingkuo Wang, Jihong Zhang, Lanxi Zhu, Pengyuan Liu, Zhipeng Yi, Luankang Zhang, Hang Lv, Xuyang Zhi, Tianyu Li, Bintao Wu, Chuang Ou, Siyue Su, Ziyuan Wang, Yuliang Sun, Baiyan Che, Feiyang Xu, Shiwen Zhang, Shiteng Cao, Chongcong Jiang, Yuan Fang, Xiangwu Yang, Hao Deng, Zijian Du, Pengxun Wang, Xiaoming Wang, Shun Qin, Yingqi Song, Tianyi Li, Naixiao Peng, Chenyu Zhou, Qiliang Jiang, Quan Zheng, Cheng Jin, Siying Zeng, Hongjia Xu, Junwu Hu, Teng Fu, Zhengkang Mei, Haijun Yu, Kai Li, Shengyang Zhou, Zhijia Wei, Siyi Xiong, Bo Liu, Zichun Guo, Zhubin Han, Jinpeng Fu, Bingqian Liu, Yuyi Wang, Yu Liu, Qinghai Tan, Ruijie Zhou, Zhuohang Li, Zhijia Zhong, Xiangnan He, Jirong Wen, Min Zhang, Wenwu Ou, Peng Jiang, Han Li, Kaiqiao Zhan, Yanan Niu, Lantao Hu, Kun Gai

Information Retrieval

When the Label Ignores the Request: Auditing Policy-Selected Targets in Synthetic Conversational Music Recommendation

Sanjeev Suresh

Synthetic dialogues generated by LLM pipelines now serve as complete conversational-recommendation benchmarks: an LLM listener talks to an LLM recommender, and the track logged next in the conversation becomes the official label for each turn. These policy-selected labels make large-scale evaluation reproducible, but they are proxies for what the simulated user asked. We audit the one place where label and request are directly comparable: turns where the user asks for an exact song by name. In the RecSys Challenge 2026 TalkPlay benchmark, using visible dialogue and catalog metadata alone, we find that the official label contradicts the user's exact-song request in half of the audited development turns. This matters beyond one benchmark: naming the desired item is the dominant intent in real music search, where deployed systems avoid substituting an alternative for an exactly named item, on the premise that it costs satisfaction. A small training-time supplement closes most of the gap: adding catalog-resolved request-satisfying targets to a small fraction of training turns yields a 53.3% relative gain in nDCG@20 on the 43 conflict turns while leaving the official metric intact, verified against a matched control that detects the same requests but trains only on official labels.
Read the full abstract

Information Retrieval · Cross-listed from cs.CL

Working Around the Compute Ceiling: Byte-Exact Memory in Galahad Makes LLM Reading a One-Time Cost LLM Reading a One-Time Cost

Sietse Schelpe

A transformer language model performs a bounded amount of computation per token, and recent work by Vishal Sikka, former CEO of Infosys, argues that this bound limits which tasks a model can carry out or verify (arXiv:2507.07505). We ask how much of the budget beneath that ceiling is spent on work the model has already done. Serving is stateless across requests: a model that answers a second question about a document recomputes the document's attention state from the first token. On seven real-world datasets, 98.7% of prompt tokens were text the model had already read. We present Galahad, a memory layer for vLLM, SGLang and llama.cpp that makes this reading a one-time cost. Taliesin saves the model's key-value (KV) state for a block of text and loads it on the next request that contains the same bytes, instead of recomputing it. Blaise keeps the documents themselves and passes the model only the section a question needs. On a recall test with 100 facts hidden in a 97,000-token corpus (Gemma 4 31B), Taliesin alone let the model attend to the whole corpus and answered 98 of 100 on llama.cpp at 3.0 s and 572 J per question, against 10 of 100, 9.3 s and 2,754 J for the same model without Galahad, which could hold only the last 12,000 tokens. With Blaise added, the model read about 668 tokens per question and answered 100 of 100 on all three runtimes at 0.59-0.64 s and 200-213 J; a tuned RAGFlow pipeline answered 77. Storing the corpus is a one-time cost of about 100 s and 28 kJ, whose energy is recovered after 13 questions. Restored state is bit-identical: all 262,144 output logits matched after restart, rehydration and hot-load. Galahad worked with all 30 models we tested under vLLM, and it fails closed: any load that does not pass its checks is recomputed. Together these results move LLM serving from stateless to stateful inference.
Read the full abstract

Information Retrieval

Generative End-to-end Ad Retrieval at Douyin

Shaowen Zeng, Yanhua Huang, Jiacheng Sun et al. (+8 more)

Generative retrieval reformulates recommendation as the generation of discrete item tokens. However, scaling this paradigm to real-world recommender systems reveals two critical bottlenecks: 1) Representation collapse, where the item tokenizer converges to degenerate results under continuous distribution shifts, fundamentally hindering stable end-to-end adaptation. 2) Item collisions, where the massive candidate pool causes distinct items to share identical token sequences, compromising the final retrieval precision. Crucially, these bottlenecks are inherently coupled: expanding codebook capacity to mitigate collisions inevitably exacerbates collapse. To address them simultaneously, we propose GEAR, an end-to-end framework that jointly optimizes the tokenizer, generator, and reranker. To mitigate representation collapse, we introduce BasisVQ, which re-parameterizes the codebook via an orthogonal basis to enable global gradient sharing and rigid spatial rotation of the latent space, effectively stabilizing gradient dynamics without ad-hoc heuristics. We further extend it to prefix-aware BasisRQ, substantially enhancing the codebook's expressiveness with the same asymptotic time complexity. To resolve item collisions, GEAR integrates a context-conditioned reranking head into the generative process, efficiently disambiguating colliding items with minimal computational overhead. By unifying stable tokenization and joint reranking within an end-to-end generative framework, GEAR establishes a fully differentiable and scalable paradigm. It currently serves hundreds of millions of daily active users on Douyin Ads, yielding substantial empirical improvements in extensive online A/B tests.
Read the full abstract

All authors Shaowen Zeng, Yanhua Huang, Jiacheng Sun, Jiarui Liu, Qian Dai, Zhikai Yang, Hancheng Li, Boya Wu, Tuoyu Zhang, Yekui Chen, Xiang Sun

Information Retrieval

Residual Trajectory Distillation for Generative Retrieval

Weihao Shen, Wei Chen, Fuwei Zhang et al. (+4 more)

Generative retrieval has emerged as a general retrieval paradigm, representing items with discrete Semantic IDs (SIDs) and retrieving them through autoregressive identifier generation. When SIDs are constructed with residual quantization (RQ), standard retrieval training supervises only the selected codes and discards the residual trajectories that produce them. The same hard code can nevertheless arise from different preferences over competing codewords, while the residual trajectory also contains information about subsequent quantization decisions. As a result, hard SID supervision collapses distinct quantization behaviors into identical targets and leaves information available during indexing unused in retrieval training. We introduce ResTD, a Residual Trajectory Distillation framework that transfers this discarded indexing information into retrieval training. Treating the frozen RQ indexer as a process teacher, it distills residual-induced codeword preferences into SID-decoding states. This supervision recovers distinctions hidden by hard assignments and allows earlier decoder states to capture information about subsequent quantization decisions before the corresponding SID suffix is generated. In this way, richer information from SID construction is incorporated into retrieval learning while preserving the original retrieval index and inference procedure. Experiments on multilingual e-commerce retrieval show consistent improvements over strong baselines and matched training controls. Controlled comparisons show that residual-derived targets outperform the tested codebook-only soft targets. Representation probes further show that future codebook preferences become more recoverable from earlier decoder states. ResTD can also be readily extended beyond retrieval to generative recommendation. Code is available at: https://github.com/Nevaeh7/iclr2027_ResTD.git.
Read the full abstract

All authors Weihao Shen, Wei Chen, Fuwei Zhang, Guojun Liu, Qingsong Hua, Wei Lin, Fuzhen Zhuang

Information Retrieval

Learning Multiresolution Relevance for Hierarchical Generative Retrieval

Weihao Shen, Wei Chen, Fuwei Zhang et al. (+4 more)

Generative retrieval with semantic identifiers (SIDs) makes successive decisions over a document hierarchy. Relevant documents for the same query may share coarse prefixes and diverge at finer depths, with branching patterns varying across queries. These paths reveal how relevance is distributed across successive refinements, yet standard full-SID supervision treats them as separate training targets. To make this allocation explicit, we formulate multiresolution relevance as consistent conditional distributions induced by a single document-level relevance measure across the SID hierarchy. We introduce RARS, Resolution-Aligned Relevance Supervision, which uses the resulting refinement-level distributions to supervise a shared query representation. RARS aggregates document relevance over prefixes and trains a prefix-conditioned predictor to allocate relevance among sibling branches. All relevance-bearing children participate in local competition, and each local loss is weighted by the relevance mass reaching its parent. This objective trains the query encoder to capture both the coarse structure shared by relevant documents and their finer branch allocations. The predictor is discarded after training, preserving standard autoregressive retrieval at inference. Experiments on three multilingual ESCI locales show consistent improvements over matched full-SID training under autoregressive decoding. RARS also outperforms grouped soft-target, decoder soft-target, and sampled-tree supervision under a common retrieval rule. The gains persist across alternative identifier structures and relevance definitions. Code is available at: https://github.com/Nevaeh7/RARS
Read the full abstract

All authors Weihao Shen, Wei Chen, Fuwei Zhang, Guojun Liu, Qingsong Hua, Wei Lin, Fuzhen Zhuang

Information Retrieval · Cross-listed from cs.CL

Argument Structure Prediction in Online Conversations: A Comparative Study of Modeling Paradigms and Task Architectures

Siddharth Bhargava, Sara Tonelli, Patricia Martín-Rodilla et al. (+1 more)

Argument structure prediction (ASP) constructs complete argument structures from discourse by identifying argumentative units and their relations. While recent work has explored diverse approaches—including unified neural models, multi-step pipelines, and prompt-based large language models (LLMs)—their relative trade-offs remain under-explored, particularly in dialogical settings. We present a systematic evaluation of ASP under strict schema constraints, comparing supervised fine-tuning and prompt-based LLMs across single- and multi-step task architectures, generating complete argument structures from dialogical input end-to-end. We benchmark them on three diverse dialogical corpora adapted from Inference Anchoring Theory into bipolar argument structures. Under a shared evaluation framework, we assess predictive performance, cross-domain generalization, schema compliance, and computational efficiency. Our results show that ASP remains a challenging task, with identifying argumentative relations emerging as the primary bottleneck, largely due to the implicit and context-dependent nature of dialogical argumentation. To facilitate future research, we release our data processing pipeline and end-to-end modeling framework for computational ASP on dialogical corpora.
Read the full abstract

All authors Siddharth Bhargava, Sara Tonelli, Patricia Martín-Rodilla, Javier Parapar

Information Retrieval · Cross-listed from cs.DB

O-Funnel: Lossless Structural Capture and Requirement-Driven Extraction from Drifting, Heterogeneous Documents

Osama Mustafa

Pulling a fixed set of fields out of documents that arrive in many formats and under drifting schemas is usually done with hand-written byte patterns, which break whenever a key is renamed, a value is reformatted, or a lookalike value appears first. We argue the cause is structural: one pattern must both describe the value and locate it among its surroundings. O-Funnel separates the two. It transcribes any XML, JSON, CSV, HTML or key-value text document into one typed tree over five constructors, gated by an oracle that rejects any capture that does not reconstruct its source. Each needed field is declared in the tree's own terms and located by fusing independent evidence (key, path, value shape, synonym, key spelling, record neighborhood, value profile), so the best-supported node wins and a missing field is reported with a reason. Data no requirement claims becomes residue that a funnel traces back to the requirements to learn new key aliases. On 34,989 real PubMed records, O-Funnel matches a hand-written parser (F1 1.00). After a five-element schema rename, the parser's regular expressions fall to 0.20 while O-Funnel stays at 1.00, with every capture verified complete. On constructed suites that isolate regex failure modes it raises F1 from 0.43 to 1.00, and from 0.80 to 0.94 after self-improvement; on held-out schema-matching instances it is competitive with classical matchers without training. O-Funnel is a dependency-free Python library (pip install ofunnel).
Read the full abstract

Information Retrieval

Routing Between Generative and Collaborative User Profiles: A Serving-Time Gate for Controllable Novelty

Milad Sabouri, Neeraj Sharma, Sardar Hamidian et al. (+1 more)

Large language models (LLMs) enable rich semantic user profiles for recommendation, but such profiles are more expensive to generate and are not necessarily desirable to deploy uniformly. We study whether LLM-generated profiles can instead be invoked selectively within a production recommendation pipeline. Using a real-world streaming dataset covering movies, TV shows, and sports content, we train a serving-time routing gate that assigns each user to either a collaborative sequential recommendation model or a recommendation model driven by an LLM-generated profile. The gate uses only serving-time features and learns to identify users for whom profile-based routing can increase Novelty@10 while preserving ranking relevance. A routing threshold controls how aggressively users are sent to the generative model, exposing a tunable novelty–relevance trade-off. At an overall NDCG-loss budget of 5%, the learned gate increases Novelty@10 by 6.5% while routing 12.5% of users, outperforming simple heuristic and random routing policies at comparable relevance cost. These results show that LLM-generated user profiles can serve as a controllable complement to collaborative recommendation, while results with non-generative semantic profiles indicate that the benefit stems from selective routing rather than LLM generation alone.
Read the full abstract

All authors Milad Sabouri, Neeraj Sharma, Sardar Hamidian, Shaghayegh Agah

Information Retrieval · Cross-listed from cs.CL

Evidence First, Arithmetic Second: A System Report and Failure Analysis for DocSem

Divya Godara and Sachin Gupta

EVICALC, our system for the DocSem shared task, achieved 8.61% joint accuracy on 1,730 tasks in the official final test evaluation. It reads a PDF, selects a passage, asks a language model to write an arithmetic expression, and evaluates that expression in local code. Saved intermediate results support inspection of failures. A separate public-validation run achieved 92.17% answer accuracy and 1.00 evidence F1. The configurations and metrics differ, so these scores are not a controlled comparison. Our manual, post-hoc analysis is descriptive: in one inspected case, optical character recognition (OCR) and block grouping merged the relevant passage into another block, and the system answered from unrelated text. An exploratory study of reading page images on 100 documents returned evidence identifiers for only 22 documents. These descriptive findings motivate further evaluation; they do not establish the causes of the overall score.
Read the full abstract

Information Retrieval

RouteRec: Behavior-Guided Sparse Routing for Sequential Recommendation

Junyeong Song and Jaemin Yoo

Sessionized interaction histories contain behavioral patterns that can improve sequential recommendation. However, existing models process all sessions through the same parameterized blocks, regardless of their behavioral differences. Mixture of Experts (MoE) enables conditional computation, but it leaves open what should guide expert allocation. We propose RouteRec, a sequential recommender that uses observed session behavior as the routing criterion. RouteRec summarizes four types of behavioral evidence from sessionized histories: interaction tempo, item-group focus, repetition and carryover, and popularity tendency. It uses these cues to route computation at macro, mid, and micro scopes. Cue-derived scores first select expert groups; within each selected group, the current backbone state then refines expert selection. Across six public datasets and 18 dataset-metric combinations, RouteRec ranks first in 12 and second in three, yielding the best overall average rank of 1.61 compared with 4.11 for the next-best baseline. Additional analyses suggest that the behavioral cues guide expert allocation beyond added capacity and produce routing patterns aligned with observed behavior. Our code is available at https://github.com/jy1559/RouteRec
Read the full abstract

Information Retrieval

When LLM-Inferred User Context Adds Value in Production Streaming Recommendation

Milad Sabouri, Neeraj Sharma, Sardar Hamidian et al. (+1 more)

Contextual information in recommender systems is shifting from static, predefined variables toward latent representations inferred from behavior. Large language models support this shift by rendering an unstructured interaction history as a natural-language summary, which yields a thematic user context that can be encoded and used in place of an aggregate profile. The conditions under which such generated profiles outperform aggregate embeddings have received limited characterization mainly at the domain level. We evaluate semantic user-profiling strategies on a production streaming platform, ranking against the full catalog. The evaluation covers a 2*2 design space crossing representation type (aggregate or LLM-generated) with contextual scope (holistic history or attention-fused short-term and long-term contexts). The relative ordering of the two representation types is conditional on the user's consumption regime. Aggregate profiles are consistently stronger under habitual consumption, which characterizes approximately four-fifths of the population, while LLM-generated profiles are stronger for exploratory users whose subsequent interactions diverge semantically from their history. We also observe a popularity-attractor effect in LLM-generated profiles, which modestly raises within-list diversity while substantially lowering catalog coverage and reducing novelty. These results indicate that a context-aware system can select a profiling strategy from the inferred consumption regime rather than applying one representation to all users.
Read the full abstract

All authors Milad Sabouri, Neeraj Sharma, Sardar Hamidian, Shaghayegh Agah

Information Retrieval

Text-Video Retrieval via Multi-Dimensional Saliency Assessment and Granularity-Aware Query Decomposition

Shuquan Wei, Xi Chen, Xu Chen et al. (+1 more)

Text-video retrieval, which aims to bridge visual and textual modalities by learning a joint embedding space, has become a crucial task in multimodal intelligence. Despite extensive efforts to mitigate visual redundancy, previous methods typically rely on a single-aspect criterion to assess visual importance, overlooking the multifaceted spatiotemporal nature of video. In addition, encoding text into a single global embedding to align with videos compresses temporal events and spatial entities into a unified representation space, further aggravating cross-modal misalignment. To address these issues, we propose MMTI, a method that jointly mitigates visual redundancy and enables multi-grained text-video interaction to achieve accurate multi-grained semantic alignment. Specifically, a key feature selection (KFS) mechanism adaptively identifies and aggregates informative frames and patches by jointly evaluating multi-dimensional saliency and learnable importance scores, effectively compacting dense visual features and mitigating visual redundancy. Furthermore, our proposed multi-grained text-video interaction module (TVIM) employs a dynamic gating mechanism to decompose the text query into sentence, frame, and patch queries (SFP), enabling multi-grained text-video alignment. Complementary alignment at different granularities is thereby achieved. Extensive experiments on four standard benchmarks demonstrate that our method outperforms state-of-the-art methods.
Read the full abstract

All authors Shuquan Wei, Xi Chen, Xu Chen, Xiangyang Jia

Information Retrieval · Cross-listed from cs.CY

Breaking News Out of the Filter Bubble: Generative AI Search Diversifies Collective Attention and Raises Shared Information Consumption

Heeseung Andrew Lee, Dokyun Lee, Gwanhoo Lee et al. (+1 more)

Generative AI search and AI overviews are transforming access to information and news, renewing concerns that readers will encounter a narrower range of topics and have less in common. We examine these concerns via a randomized field experiment with 37,561 readers at The Washington Post. Both groups searched the same archive, but treatment readers also received AI answers with article citations above conventional results. Measuring consumption across displayed answers and opened articles, we find that AI search expands the reach of widely read topics and increases overlap in readers' topic consumption. At the same time, consumption becomes less concentrated and shifts toward less-popular topics, both within readers and across the audience. AI answers account for most of the increase in shared information, delivering it without requiring article clicks and broadening exposure beyond the articles readers open. Cited articles also contribute to the shift toward less-popular topics. Readers shift from conventional-result clicks and browsing toward cited articles and follow-up searches. More frequent searching offsets lower article consumption per search, producing a small increase in article consumption per reader. Total information consumption per minute also rises. Generative AI search can thus diversify collective attention while strengthening the information readers have in common.
Read the full abstract

All authors Heeseung Andrew Lee, Dokyun Lee, Gwanhoo Lee, Dongwon Lee

Information Retrieval · Cross-listed from cs.CL

TRACE: Target-Aware Retrieval, Attributed Evidence, and Contract-Constrained Extraction for LitTraceQA

Sachin Gupta and Divya Godara

Finding a relevant paper is not the same as producing a verifiable answer from it. LitTraceQA requires canonical paper identifiers, exact evidence at the page or object level, and typed answers that match the evaluator. We call the separation between source access and scorer-visible correctness the grounding contract gap. TRACE - Target-Aware Retrieval, Attributed Evidence, and Contract-Constrained Extraction - addresses this gap with target-grouped retrieval, independent typed evidence localization, multimodal table extraction, schema-driven table construction, and fail-closed validation. It indexes 27,487 papers through passage, object, alias, citation, and dense representations while retaining the question target behind each signal. For tables, TRACE predicts the observation unit before extracting values and assembles rows with evaluator-compatible key normalization. Our audited selected clean-track artifact scores 0.760613 on the official 71-question test set, including 0.9728 paper F1, 0.6847 evidence F1, 0.9800 multiple-choice accuracy, 0.5423 table-row F1, and 0.3508 macro cell accuracy. On 11 public-development table records, a clean baseline and coordinate-aware visual fill obtain row F1 of 0.291 and 0.411, respectively; this diagnostic comparison includes fallback outputs and is not an official-test claim. Remaining errors chiefly concern locator, observation-unit, row-key, and source-value identity.
Read the full abstract

Information Retrieval

SkillSeek: Revisiting Agent Skill Retrieval at Marketplace Scale

Guanqun Yang, Wenlong Zhang, Tian Shi et al. (+1 more)

Anthropic's Agent Skills package reusable procedural know-how for an LLM agent into SKILL.md directories, and open-source aggregations have grown past 230,000 skills, making selection rather than authoring the bottleneck. The standing answer in the literature outsources selection to the agent itself: an LLM-mediated retrieval loop that rewrites queries and refines candidates inside the agent's decision loop, paying LLM tokens on every task. We present SkillSeek, an open-source two-stage skill retriever built from the standard IR recipe (a BGE-base bi-encoder feeding a small cross-encoder, exposed over MCP). Across a $4 \times 11$ grid of pool, backbone, and method on the 89-task SkillsBench benchmark, SkillSeek reaches observed parity with the LLM-mediated loop of Liu et al. at essentially no extra cost: plain bm25 alone records a pass rate at or above their refined loop on three of four settings, and a small cross-encoder covers the remaining difference on the fourth. A first-stage recall ceiling explains the pattern, and total per-trial spend drops from USD 51.30 to USD 27.54 (within fifty cents of the no-skill baseline). Under the SkillsBench tasks and OpenHands harness we tested, this positions the standard IR recipe as a strong default for agent-skill retrieval, with LLM-mediated alternatives a natural fit for cases where deterministic methods fall short.
Read the full abstract

All authors Guanqun Yang, Wenlong Zhang, Tian Shi, Ping Wang

Information Retrieval

PatchHolmes: Agentic Patch Retrieval via Listwise Selection

Guanqun Yang, Yingming Zhou, Jiangrui Zheng et al. (+2 more)

Patch retrieval, the task of finding the commit that fixes a known vulnerability, is the foundation of vulnerability management workflows, yet 60% to 63% of CVEs in the major advisory databases lack a patch link. We present PatchHolmes, a two-phase patch retrieval system that pairs a hybrid first-stage retriever with an agentic second-stage inspection loop. Unlike pointwise prior work that scores each candidate independently, the Phase 2 agent reads the top-100 listwise: it sees the full candidate list at once and selectively reads 3 to 10 commits through four budgeted tools before submitting a single best commit. On GitHubAD, PatchHolmes beats the pointwise binary classifier Favia by 25.34% Recall@1 and the retrieve-and-CoT baseline IRCoT by 31.40%, at one agent conversation per CVE versus Favia's ten; with the candidate set held identical, the agent adds 27.32% Recall@1 over taking the retriever's top candidate, and the same agent, transferred unchanged to PatchFinder_top10, lifts Recall@1 from PatchFinder's own top-1 pick (24.28%) to 39.86%. Swapping the LLM backbone within the Qwen family changes Recall@1 by under 1%, and a second model family (gpt-oss) stays far above the no-agent floor, so the gain comes from the listwise agent loop; the entire system runs on a frozen open-weight model over a local Git repository, without fine-tuning or external search APIs.
Read the full abstract

All authors Guanqun Yang, Yingming Zhou, Jiangrui Zheng, Shudong Hao, Xueqing Liu

Information Retrieval · Cross-listed from cs.AI

Learning to Route in Visual Space via Multi-Step Embedding Retrieval

Tianyu Chen, Mingyuan Zhou and Jiaxing Wu

LLM agents rely on retrieval tools to access external knowledge, yet visual agentic search remains severely bottlenecked by standard single-step retrievers. In current pipelines, the agent must issue text queries for every intermediate step, struggling when visual clues are difficult to describe or when the retriever fails to surface necessary intermediate evidence within its top results. We hypothesize that offloading multi-step navigation across the entire embedding space directly to the retrieval tool resolves this performance bottleneck. To study this systematically, we introduce VHOP, a flexible data generation framework and benchmark with five core difficulty levels testing both visual matching and search planning. Using this framework, we develop VHOP-Router, an end-to-end training pipeline—combining supervised fine-tuning, online imitation learning, and reinforcement learning—that transforms a standard embedding model into an autoregressive multi-step retriever. Operating directly in the visual latent space, VHOP-Router retrieves linked image chains in a single tool call without requiring the agent to formulate intermediate text queries. Experiments show VHOP-Router boosts retrieval performance from under 5% to 76.3%. In agentic search, it improves task success rates by 52.7% and reduces the average token length by 61% from 1886 to 728, whereas upgrading the agent yields only a 3.7% gain. Compared to a strong baseline where the agent retrieves the top 50 results per step, VHOP-Router maintains superior performance while reducing in-context images by $23\times$ and cutting the cumulative API payload by $35\times$. The models also generalize robustly to unseen difficulty levels and realistic test sets. Ultimately, VHOP and VHOP-Router provide an efficient and effective solution for visual agentic search that leaves native LLM capabilities entirely intact.
Read the full abstract

Tuesday 29 September

Information Retrieval

LIFT: A Lifecycle-aware Interaction Factorization Transformer for Unified Retrieval and Ranking

Keji Miao, Enhao Cheng, Yan Li et al. (+4 more)

Cascaded recommender systems use the same user history for retrieval and ranking, while the two stages have access to different information at different points of an interaction. We propose the Lifecycle-aware Interaction Factorization Transformer (LIFT), which decomposes each interaction into ordered Request, Item, Context, and Action states and models them as a causal sequence. Retrieval reads the Request state, while ranking reads the Context state, allowing both tasks to share history modeling while preserving stage-specific information. LIFT instantiates this representation with Role-Conditioned Attention and a lightweight Pre-LN Bias. On ML-20M and Taobao, LIFT achieves the highest Joint Score among the evaluated joint models, improving over the strongest baselines by 4.9% and 3.6%, respectively. Loss-weight sweeps show favorable retrieval–ranking trade-offs, while ablations and scaling analyses further examine lifecycle sequence construction, model components, and capacity settings.
Read the full abstract

All authors Keji Miao, Enhao Cheng, Yan Li, Qun Li, Qi Zhang, Jie Yuan, Xiaoyong Li

Information Retrieval

Exploring Forum Post Retrieval with Generative Modeling

Yang Li, Yaguang Liu, Heng Liu et al. (+14 more)

Generative recommendation (GR) has emerged as an alternative to embedding-based retrieval, building on the success of generative models in language and vision. We are exploring GR on Facebook Forum, a standalone application for medium-to-heavy users of Facebook Groups. Because Forum is a new surface, its own interaction data are too sparse to train a GR model from scratch. We address this with transfer along two axes: we train on a broader corpus of Facebook Groups engagements rather than Forum sessions alone, and we reuse hierarchical, prefix-based semantic IDs (SIDs) learned from cross-platform Facebook Feed data instead of fitting a Forum-specific tokenizer. A 3B-parameter instruction-tuned language model is then supervised-fine-tuned to generate SIDs directly from user context. We systematically ablate the design choices that matter most in practice, including SID construction, the composition and length of user history, and the inclusion of user-profile features. Our results show that cross-platform SIDs transfer to a new recommendation surface, and offer practical guidance for teams deploying GR on real-world social platforms.
Read the full abstract

All authors Yang Li, Yaguang Liu, Heng Liu, Samson Komo, Jane Kou, Yulian Zhou, Gang Yang, Shubhojeet Sarkar, Gaurav Chakravorty, Yujie Liu, Haipeng Chen, Yonghuan Yang, Deepti Chheda, Yamin Wang, Mike Plumpe, Rish Tandon, Shengbo Guo

Information Retrieval · Cross-listed from cs.AI

Component-Aware Feedback for Self-Evolving Programs

Ethan Lin, Jinming Nian and Yi Fang

LLM-guided evolutionary search can discover complex programs, but existing methods mostly only save candidate programs and fitness scores while discarding which component edits produced which fitness metric changes. Existing methods force the mutator LLM to infer the effect of prior edits from cluttered histories, making program search slow and unstable. This is especially true for locally servable LLMs to evolve multi-component systems. We introduce component-aware feedback, which compares each evaluated program with its parent, identifies the components that changed, and logs them with the associated metric differences into an attribution memory that later mutations read. The memory keeps each change in two reference frames, local against the parent it came from and global against the seed program, which shows both the immediate effect of a change and the cumulative progress made since the seed. We study this on LLM reranking, a multi-objective optimization problem where a multi-stage pipeline must balance quality against serving cost. Across twelve Bright datasets, our method reaches the strongest baseline's final quality after a median of one third of the search budget and ends 7.2% higher in held-out nDCG@10, and under a cost-aware objective it finds pipelines that are on average more accurate while using 11% fewer tokens per query, showing component-aware feedback to be a promising direction for more efficient self-evolving systems.
Read the full abstract

Information Retrieval

Re-ranking and Late Interaction Drive Retrieval Quality: A Controlled Comparison of RAG Strategies for Scientific Question Answering

Bhagyesh Rathi, Eshan Chawla and William B. Andreopoulos

Retrieval-Augmented Generation (RAG) is now the standard way to ground Large Language Models (LLMs) in external knowledge, yet the design space of retrieval pipelines is large and the trade-offs between variants are not well understood, especially on domain-specific corpora at realistic scale. In this work, we present a controlled comparison of six retrieval strategies for scientific question answering: (i) classic top-k dense retrieval, (ii) LLM-based query rephrasing, (iii) query rephrasing followed by LLM-based reranking, (iv) multi-query fusion via Reciprocal Rank Fusion (RRF), (v) an agentic tool-call pipeline in which the generator decides for itself whether to retrieve, and (vi) late-interaction retrieval with ColBERTv2. All six pipelines share the same generator (Meta-Llama/Llama-3.1-8B-Instruct), prompt, and evaluation protocol; the five single-vector pipelines additionally share SPECTER2 embeddings and a Chroma vector store; and all six retrieve from the full corpus of 463,971 arXiv papers dated 2024-2025. To support reproducible, large-scale evaluation, we also release a synthetic question dataset of 19,484 problem-statement and methodology questions generated by Llama-3.1-8B-Instruct from a random sample of 10,000 papers across academic domains (query generation succeeded for 9,742 of them), and every strategy is evaluated on this same query set. We describe the architecture and implementation of each pipeline, release the code and the synthetic question dataset, and evaluate each strategy with an LLM-as-a-judge protocol along multiple quality dimensions, together with direct gold-paper retrieval metrics. The result is an open testbed for studying the cost and quality trade-offs of RAG design choices on a research-literature corpus, and a basis for future work on faithfulness, retrieval robustness, and agentic retrieval.
Read the full abstract

Information Retrieval

AdaM-Rec: Adaptive Modality Routing for Multimodal Recommendation

Honghao Fu, Jiacheng Chen, Manxi Lin et al. (+7 more)

While recent multimodal recommender systems have demonstrated the effectiveness of incorporating visual and textual information to improve downstream performance, most existing methods rely on static modality fusion, assuming that the relative importance of textual and visual signals remains stable across recommendation scenarios. This design may not fully account for an important variation across recommendation requests: some queries require fine-grained visual cues, whereas others are better served by textual or functional semantics, in which case indiscriminate modality fusion brings in uninformative cues and impairs recommendation quality. To address this, we propose AdaM-Rec, an LLM-based framework for adaptive modality routing in multimodal recommendation, which enables dynamic calibration of reliance on textual and multimodal evidence for user-specific queries. Built on structured natural-language representations of items and user preferences, it estimates modality reliability using proxy recall tasks. Specifically, it generates pseudo-queries that match the granularity of the actual query while pointing to the user's positively interacted items as verifiable proxy targets, evaluating which modality yields better recall performance in analogous scenarios and optimizing the routing strategy in an agentic manner. It then performs routed recall with optimized strategy, enriches results with collaborative items, and ranks candidates by their relevance to both the query and user preferences. Experiments demonstrate that AdaM-Rec delivers strong performance against state-of-the-art baselines, highlighting the effectiveness and broader potential of adaptive control over modality reliance in multimodal recommendation.
Read the full abstract

All authors Honghao Fu, Jiacheng Chen, Manxi Lin, Junjun Zheng, Xiangheng Kong, Yiwei Wang, Xin Yu, Miao Xu, Yuning Jiang, Yujun Cai

Information Retrieval · Cross-listed from cs.CL

Doc2LoRA Provides Decodable Representations of Scientific Ideas

Chand Sahil Mansuri, Joel Zachariah and Sadamori Kojaku

Representing scientific papers as points in a space lets us search for similar papers and inquire about how fields relate to one another and drive innovation. Beyond search, the vector space of papers invites generation: mixing papers through simple vector operations creates new points, mirroring combinatorial novelty, the recombination of existing ideas into new ones. However, a mixed point often represents an idea no paper has yet realized, with no papers nearby to identify the idea. We propose representing each paper by a LoRA adapter generated by the Doc-to-LoRA hypernetwork. Every point in the space, including mixtures, thus represents a large language model (LLM) open to questions and instructions in natural language. On papers from the American Physical Society (APS), we instruct the LLM at the average of each subfield to name the field in a few words and obtain labels closer to the official names than the labels of five baselines, as judged by word overlap and a panel of five LLM judges. We also ask the LLMs at points between two APS papers to write an abstract and obtain descriptions shifting from one paper to the other in step with the mixing weight. While Doc-to-LoRA is trained for generation, a small invertible transform makes the embeddings competitive for search, on par with SPECTER2 and EmbeddingGemma and close to SBERT. Because the transform is invertible, every point in the transformed space still maps back to an LLM. The embeddings thus serve both search and generation, enabling researchers to question the idea at any point in the space as a starting point for generating new ideas.
Read the full abstract

Information Retrieval

TAGGRAPH: Tag-Augmented Graphs for Graph Retrieval of Agent Persistent Histories

Yu-Shu Chen, Yu-Jung Liang and Pengtao Xie

Long-term memory lets LLM agents recall past interactions and remain consistent across sessions, but memory systems are hard to compare because they often vary in representation, indexing, retrieval, and evaluation. We present a controlled evaluation framework based on shared 5W-style conversational memories. Localized graph configurations traverse a common base graph; AdaptiveGraph adds chronological edges and Personalized PageRank diffusion. We also evaluate BM25 over the same extracted notes and OpenClaw as a raw-input external reference. Retrieval rankings vary across memory settings. On LongMemEval-S, AdaptiveGraph is the strongest graph configuration at 0.844 MRR, but BM25 reaches 0.867 and OpenClaw 0.880. On ATANT Core, localized graph traversal outperforms diffusion and BM25, whereas BM25 leads the stress rounds. Reducing LongMemEval-S within the tested range does not reproduce the ATANT diffusion penalty, but the smallest tested store remains larger than ATANT Core, so store size cannot be ruled out. The penalty also persists under a permissive content-match criterion. Vocabulary normalization and extraction quality substantially affect graph retrieval, and missing extraction tags are common among top-five misses. Retrieval strategies should therefore be evaluated jointly with the memory setting and against strong lexical baselines.
Read the full abstract

Information Retrieval · Cross-listed from cs.CR

Privacy in Personalized AI Is a System Property, Not Just a Model Property

Guillaume Salha-Galvan and Jiaying Xu

In personalized AI applications, such as conversational assistants and recommender systems, users interact not with models in isolation but with broader systems that access, infer, and reuse user information across components and over time. While such use of user information is integral to personalization, it also raises important privacy questions. In this paper, we argue that individual model- or component-level analyses may not capture all privacy risks arising in such systems, motivating a system-level perspective on privacy. We distinguish and analyze four interconnected privacy-risk channels in personalized AI, and subsequently propose four requirements for system-level privacy evaluation, covering interaction trajectories, internal information flows, indirect leakage, and the privacy-utility trade-off. We argue for their systematic incorporation into privacy audits of personalized AI.
Read the full abstract

Information Retrieval · Cross-listed from cs.CV

Beyond the Timeline: Augmenting Long-Video Memory with Grounded Entity Biographies

Hui Ren, Lei Fan, Henry Pao et al. (+5 more)

Answering questions about long videos often requires connecting events involving the same objects across hours or days. Chronological descriptions and text-derived entities can leave physical identity unresolved: different objects may share a description, while observations of the same object remain disconnected across events. Retrieving relevant events therefore does not necessarily recover the "biography" of the particular entity a question concerns. To address this, we introduce Grounded Entity Biographies (GEB), a long-video memory framework that groups visually grounded observations of the same physical instance across clips into retrievable biographies while preserving the context of each moment. During question answering, the biography is retrieved alongside episodic evidence, allowing the model to follow an entity through events using identity links established during memory construction. Evaluations across four benchmarks, including day-long and week-long recordings, demonstrate improvements over prior memory frameworks in both multiple-choice and open-ended question answering. On EgoLifeQA, GEB achieves 72.0% accuracy, 4.4 percentage points above the best published result. Ablations show that grounded identity association and biography reading both contribute to the gains, which additional descriptions alone do not fully recover.
Read the full abstract

All authors Hui Ren, Lei Fan, Henry Pao, Han Guo, Zeeshan Zia, Ying Chen, Alexander Schwing, Gang Hua

Information Retrieval

Effective Dense Retrieval using Only In-Context Examples

Nour Jedidi, Abdul Basit Ali, Hang Li et al. (+1 more)

Turning decoder-only large language models (LLMs) into strong dense retrievers typically requires some form of retriever training. In this paper, we ask whether LLMs can instead be prompted to produce effective representations for dense retrieval given only a few in-context examples. To answer this, we introduce RICE (Representations from In-Context Examples), a simple "training-free" approach that extracts high-quality dense representations from LLMs. To do so, RICE conditions the LLM on examples that provide a shared context for query and document encoding. Our results demonstrate that RICE embeddings can substantially improve the accuracy of prompt-based LLM embeddings, establishing it as a simple method to build LLM-based dense retrievers that do not require training. We release our code at https://github.com/nourj98/RICE.
Read the full abstract

All authors Nour Jedidi, Abdul Basit Ali, Hang Li, Jimmy Lin

Information Retrieval · Cross-listed from cs.CL

Auditing Long-Term Memory Evaluation: Repeated Judging, Reader Variation, and Negative Controls

Christopher J. Chanhnourack

This report audits evaluation of a long-term-memory retrieval chain on the 500 LongMemEval-S development questions. Its strongest historical reader lane scores 479 and 475 under an adapted GPT-4o rubric; re-judging the same pass-1 answers changes three labels and yields 478. Fixed-answer knowledge-update re-scoring gives 70/72 under the upstream template and 69/72 under the modified template. Reader lanes span 93 to 479 on fixed packets; paired tests between the two strongest historical lanes establish neither superiority nor equivalence. A different-family reader, configured without client tools or operator files, scores 474, 1.0 percentage point below the headline pass (paired 95% interval [-3.0,+1.0]). Live reader request bodies were not retained. With the same requested reader label, route and judge snapshot, the full package scores 474 versus 454 for baseline sessions, a difference of +4.0 percentage points [95% interval +2.2,+6.0]. Eighteen of the 23 gains, and no losses, occur where baseline packets lacked listed evidence; this post-hoc split does not identify a component effect. In recovered LoCoMo data, token-F1 gains do not survive answer-line extraction. A negative control rejects a verifier that repairs three wrong drafts but breaks eleven correct ones. All questions were used to develop the components; no untouched holdout was evaluated. These findings do not establish a new leaderboard leader or transferable memory advantage. The A/D comparison has one pass per arm, including six reused identical-prompt outcomes, with no pinned reader snapshot; B/C and repeats remain unrun. Original headline requests cannot be reconstructed and stages 1–4 remain closed. Released artifacts support packet inspection and saved-verdict recounting and re-scoring; they do not reconstruct the method.
Read the full abstract

Information Retrieval · Cross-listed from cs.CL

BITEM at the NTCIR-19 R2C2 Task: Predicting Confidence from Agentic RAG Pipeline Signals

Julien Knafou, Luc Mottin, Alexandre Flament et al. (+3 more)

The BITEM team entered both subtasks of the NTCIR-19 R2C2 task with a single agentic pipeline, in which a model searches, reads and records evidence over a movie corpus while an orchestrator holds the record and rules on what may be submitted. A claim is admitted only once an entailment cascade has checked it against the passage it cites, and an answer is released only once enough checked evidence stands behind it. Each question is run three or four times, every pass retrieving from a corpus stripped of what the earlier passes have already seen. The confidence filed with each answer is computed by the orchestrator from what the run leaves behind and is never asked of the model, which is offered no way to rate itself. The two retrieval runs placed 4th and 5th of 22, pooling the passes was worth 0.0709 nDCG@20, and the gain was largest on the multi-hop and post-processing-heavy questions, where the organisers rank the pooled run top of the field. Sixteen of the 25 answer runs were built on passages these two runs supplied, 12 of them filed by other teams. HMR rewards a system whose confidence is high where it answers right and low where it answers wrong. The pipeline reached an accuracy of 0.9219, 6th of 25, while the confidence filed with those answers gave an HMR of 0.4915, 13th. A few rules crafted over those same recorded signals, with no further model call and no further retrieval, raise that to an accuracy of 0.9375, 5th, and an HMR of 0.6985, 9th. Ranking on HMR alone can reward a system for answering wrongly with low confidence, so we propose accHMR, the accuracy multiplied by HMR, which reports the reward in proportion to the accuracy, and on which the revised rules would have scored 0.6549, 5th. For future work, fitting a model on the numbers the pipeline already produces, rather than writing such rules by hand, would be a real step forward.
Read the full abstract

All authors Julien Knafou, Luc Mottin, Alexandre Flament, Paul van Rijen, Esteban Gaillac, Patrick Ruch