Tootfinder

Poster: ChatIYP: Enabling Natural Language Access to the Internet Yellow Pages Database
Vasilis Andritsoudis, Pavlos Sermpezis, Ilias Dimitriadis, Athena Vakali
https://arxiv.org/abs/2509.19411

Poster: ChatIYP: Enabling Natural Language Access to the Internet Yellow Pages Database
The Internet Yellow Pages (IYP) aggregates information from multiple sources about Internet routing into a unified, graph-based knowledge base. However, querying it requires knowledge of the Cypher language and the exact IYP schema, thus limiting usability for non-experts. In this paper, we propose ChatIYP, a domain-specific Retrieval-Augmented Generation (RAG) system that enables users to query IYP through natural language questions. Our evaluation demonstrates solid performance on simple quer…

QAgent: A modular Search Agent with Interactive Query Understanding
Yi Jiang, Lei Shen, Lujie Niu, Sendong Zhao, Wenbo Su, Bo Zheng
https://arxiv.org/abs/2510.08383 https://

QAgent: A modular Search Agent with Interactive Query Understanding
Large language models (LLMs) excel at natural language tasks but are limited by their static parametric knowledge, especially in knowledge-intensive task. Retrieval-augmented generation (RAG) mitigates this by integrating external information. However, (1) traditional RAG struggles with complex query understanding, and (2) even search agents trained with reinforcement learning (RL), despite their promise, still face generalization and deployment challenges. To address these limitations, we prop…

from my link log —
Pipelined Relational Query Language, PRQL: a simple, powerful, pipelined SQL replacement.
https://prql-lang.org/book/
saved 2025-11-05 https://

Query-Specific GNN: A Comprehensive Graph Representation Learning Method for Retrieval Augmented Generation
Yuchen Yan, Zhihua Liu, Hao Wang, Weiming Li, Xiaoshuai Hao
https://arxiv.org/abs/2510.11541 …

Query-Specific GNN: A Comprehensive Graph Representation Learning Method for Retrieval Augmented Generation
Retrieval-augmented generation (RAG) has demonstrated its ability to enhance Large Language Models (LLMs) by integrating external knowledge sources. However, multi-hop questions, which require the identification of multiple knowledge targets to form a synthesized answer, raise new challenges for RAG systems. Under the multi-hop settings, existing methods often struggle to fully understand the questions with complex semantic structures and are susceptible to irrelevant noise during the retrieval…

📈 #LogsQL query language provides fast full-text search, advanced analytics, and data extraction/transformation at query time. Can be combined with Unix tools like grep, less, sort, and jq for log analysis.
🎯 Optimized for high cardinality fields like trace_id, user_id, and ip addresses. Supports logs with hundreds of fields (wide events), multitenancy, out-of-order ingestion, live taili…

CardRewriter: Leveraging Knowledge Cards for Long-Tail Query Rewriting on Short-Video Platforms
Peiyuan Gong, Feiran Zhu, Yaqi Yin, Chenglei Dai, Chao Zhang, Kai Zheng, Wentian Bao, Jiaxin Mao, Yi Zhang
https://arxiv.org/abs/2510.10095

CardRewriter: Leveraging Knowledge Cards for Long-Tail Query Rewriting on Short-Video Platforms
Short-video platforms have rapidly become a new generation of information retrieval systems, where users formulate queries to access desired videos. However, user queries, especially long-tail ones, often suffer from spelling errors, incomplete phrasing, and ambiguous intent, resulting in mismatches between user expectations and retrieved results. While large language models (LLMs) have shown success in long-tail query rewriting within e-commerce, they struggle on short-video platforms, where p…

Imagine ChatGPT but instead of predicting text it just linked you to the to 3 documents most-influential on the probabilities that would have been used to predict that text.
Could even generate some info about which parts of each would have been combined how.
There would still be issues with how training data is sourced and filtered, but these could be solved by crawling normally respecting robots.txt and by paying filterers a fair wage with a more relaxed work schedule and mental health support.
The energy issues are mainly about wild future investment and wasteful query spam, not optimized present-day per-query usage.
Is this "just search?"
Yes, but it would have some advantages for a lot of use cases, mainly in synthesizing results across multiple documents and in leveraging a language model more fully to find relevant stuff.
When we talk about the harms of current corporate LLMs, the opportunity cost of NOT building things like this is part of that.
The equivalent for art would have been so amazing too! "Here are some artists that can do what you want, with examples pulled from their portfolios."
It would be a really cool coding assistant that I'd actually encourage my students to use (with some guidelines).
#AI #GenAI #LLMs

Query-Centric Graph Retrieval Augmented Generation
Yaxiong Wu, Jianyuan Bo, Yongyue Zhang, Sheng Liang, Yong Liu
https://arxiv.org/abs/2509.21237 https://a…

Query-Centric Graph Retrieval Augmented Generation
Graph-based retrieval-augmented generation (RAG) enriches large language models (LLMs) with external knowledge for long-context understanding and multi-hop reasoning, but existing methods face a granularity dilemma: fine-grained entity-level graphs incur high token costs and lose context, while coarse document-level graphs fail to capture nuanced relations. We introduce QCG-RAG, a query-centric graph RAG framework that enables query-granular indexing and multi-hop chunk retrieval. Our query-cen…

Accelerating LLM Inference with Precomputed Query Storage
Jay H. Park, Youngju Cho, Choungsol Lee, Moonwook Oh, Euiseong Seo
https://arxiv.org/abs/2509.25919 https://

Accelerating LLM Inference with Precomputed Query Storage
Large language model (LLM) inference often suffers from high latency, particularly in resource-constrained environments such as on-device or edge deployments. To address this challenge, we present StorInfer, a novel storage-assisted LLM inference system that accelerates response time by precomputing and storing predictable query-response pairs offline. When a user query semantically matches a precomputed query, StorInfer bypasses expensive GPU inference and instantly returns the stored response…

Implementing Semantic Join Operators Efficiently
Immanuel Trummer
https://arxiv.org/abs/2510.08489 https://arxiv.org/pdf/2510.08489

Implementing Semantic Join Operators Efficiently
Semantic query processing engines often support semantic joins, enabling users to match rows that satisfy conditions specified in natural language. Such join conditions can be evaluated using large language models (LLMs) that solve novel tasks without task-specific training. Currently, many semantic query processing engines implement semantic joins via nested loops, invoking the LLM to evaluate the join condition on row pairs. Instead, this paper proposes a novel algorithm, inspired by the bl…

PrediQL: Automated Testing of GraphQL APIs with LLMs
Shaolun Liu, Sina Marefat, Omar Tsai, Yu Chen, Zecheng Deng, Jia Wang, Mohammad A. Tayebi
https://arxiv.org/abs/2510.10407 h…

PrediQL: Automated Testing of GraphQL APIs with LLMs
GraphQL's flexible query model and nested data dependencies expose APIs to complex, context-dependent vulnerabilities that are difficult to uncover using conventional testing tools. Existing fuzzers either rely on random payload generation or rigid mutation heuristics, failing to adapt to the dynamic structures of GraphQL schemas and responses. We present PrediQL, the first retrieval-augmented, LLM-guided fuzzer for GraphQL APIs. PrediQL combines large language model reasoning with adaptive fee…

Unlike keyword search,
semantic search lets you search using natural language.
It looks beyond exact matches to understand the meaning and intent behind your query.
This means it can surface relevant precedents even when they're phrased differently
—something keyword searches often miss.
Semantic search is currently available through an API, but we're already working to bring it to the website—stay tuned!
And don't worry, keyword search isn…

Agentic generative AI for media content discovery at the national football league
Henry Wang, Sirajus Salekin, Jake Lee, Ross Claytor, Shinan Zhang, Michael Chi
https://arxiv.org/abs/2510.07297

Agentic generative AI for media content discovery at the national football league
Generative AI has unlocked new possibilities in content discovery and management. Through collaboration with the National Football League (NFL), we demonstrate how a generative-AI based workflow enables media researchers and analysts to query relevant historical plays using natural language rather than traditional filter-and-click interfaces. The agentic workflow takes a user query as input, breaks it into elements, and translates them into the underlying database query language. Accuracy and l…

Extending ResourceLink: Patterns for Large Dataset Processing in MCP Applications
Scott Frees
https://arxiv.org/abs/2510.05968 https://arxiv.org/pdf/2510.0…

Extending ResourceLink: Patterns for Large Dataset Processing in MCP Applications
Large language models translate natural language into database queries, yet context window limitations prevent direct deployment in reporting systems where complete datasets exhaust available tokens. The Model Context Protocol specification defines ResourceLink for referencing external resources, but practical patterns for implementing scalable reporting architectures remain undocumented. This paper presents patterns for building LLM-powered reporting systems that decouple query generation from…

Polars is a lightning fast DataFrame library/in-memory query engine with parallel execution and cache efficiency. And now you can use is with the tidyverse syntax: #rstats

More Efficient Tidyverse Code, Using Polars in the Background
Polars is a cross-language tool for manipulating very large data. However, one drawback is that the R implementation has a syntax that will look odd to many R users who are not used to Python syntax. The objective of tidypolars is to improve the ease-of-use of Polars in R by providing tidyverse syntax to polars.

Query-Kontext: An Unified Multimodal Model for Image Generation and Editing
Yuxin Song, Wenkai Dong, Shizun Wang, Qi Zhang, Song Xue, Tao Yuan, Hu Yang, Haocheng Feng, Hang Zhou, Xinyan Xiao, Jingdong Wang
https://arxiv.org/abs/2509.26641

Query-Kontext: An Unified Multimodal Model for Image Generation and Editing
Unified Multimodal Models (UMMs) have demonstrated remarkable performance in text-to-image generation (T2I) and editing (TI2I), whether instantiated as assembled unified frameworks which couple powerful vision-language model (VLM) with diffusion-based generator, or as naive Unified Multimodal Models with an early fusion of understanding and generation modalities. We contend that in current unified frameworks, the crucial capability of multimodal generative reasoning which encompasses instructio…

A Simple but Effective Elaborative Query Reformulation Approach for Natural Language Recommendation
Qianfeng Wen, Yifan Liu, Justin Cui, Joshua Zhang, Anton Korikov, George-Kirollos Saad, Scott Sanner
https://arxiv.org/abs/2510.02656

A Simple but Effective Elaborative Query Reformulation Approach for Natural Language Recommendation
Natural Language (NL) recommender systems aim to retrieve relevant items from free-form user queries and item descriptions. Existing systems often rely on dense retrieval (DR), which struggles to interpret challenging queries that express broad (e.g., "cities for youth friendly activities") or indirect (e.g., "cities for a high school graduation trip") user intents. While query reformulation (QR) has been widely adopted to improve such systems, existing QR methods tend to focus only on expandin…

RAVEN: Realtime Accessibility in Virtual ENvironments for Blind and Low-Vision People
Xinyun Cao, Kexin Phyllis Ju, Chenglin Li, Venkatesh Potluri, Dhruv Jain
https://arxiv.org/abs/2510.06573

RAVEN: Realtime Accessibility in Virtual ENvironments for Blind and Low-Vision People
As virtual 3D environments become prevalent, equitable access is crucial for blind and low-vision (BLV) users who face challenges with spatial awareness, navigation, and interactions. To address this gap, previous work explored supplementing visual information with auditory and haptic modalities. However, these methods are static and offer limited support for dynamic, in-context adaptation. Recent work in generative AI enables users to query and modify 3D scenes via natural language, introducin…

SAGE-LD: Towards Scalable and Generalizable End-to-End Language Diarization via Simulated Data Augmentation
Sangmin Lee, Woongjib Choi, Jihyun Kim, Hong-Goo Kang
https://arxiv.org/abs/2510.00582

SAGE-LD: Towards Scalable and Generalizable End-to-End Language Diarization via Simulated Data Augmentation
In this paper, we present a neural spoken language diarization model that supports an unconstrained span of languages within a single framework. Our approach integrates a learnable query-based architecture grounded in multilingual awareness, with large-scale pretraining on simulated code-switching data. By jointly leveraging these two components, our method overcomes the limitations of conventional approaches in data scarcity and architecture optimization, and generalizes effectively to real-wo…

VL-KnG: Visual Scene Understanding for Navigation Goal Identification using Spatiotemporal Knowledge Graphs
Mohamad Al Mdfaa, Svetlana Lukina, Timur Akhtyamov, Arthur Nigmatzyanov, Dmitrii Nalberskii, Sergey Zagoruyko, Gonzalo Ferrer
https://arxiv.org/abs/2510.01483

VL-KnG: Visual Scene Understanding for Navigation Goal Identification using Spatiotemporal Knowledge Graphs
Vision-language models (VLMs) have shown potential for robot navigation but encounter fundamental limitations: they lack persistent scene memory, offer limited spatial reasoning, and do not scale effectively with video duration for real-time application. We present VL-KnG, a Visual Scene Understanding system that tackles these challenges using spatiotemporal knowledge graph construction and computationally efficient query processing for navigation goal identification. Our approach processes vid…

AutoMaAS: Self-Evolving Multi-Agent Architecture Search for Large Language Models
Bo Ma, Hang Li, ZeHua Hu, XiaoFan Gui, LuYao Liu, Simon Liu
https://arxiv.org/abs/2510.02669 ht…

AutoMaAS: Self-Evolving Multi-Agent Architecture Search for Large Language Models
Multi-agent systems powered by large language models have demonstrated remarkable capabilities across diverse domains, yet existing automated design approaches seek monolithic solutions that fail to adapt resource allocation based on query complexity and domain requirements. This paper introduces AutoMaAS, a self-evolving multi-agent architecture search framework that leverages neural architecture search principles to automatically discover optimal agent configurations through dynamic operator …

On Theoretical Interpretations of Concept-Based In-Context Learning
Huaze Tang, Tianren Peng, Shao-lun Huang
https://arxiv.org/abs/2509.20882 https://arxiv…

On Theoretical Interpretations of Concept-Based In-Context Learning
In-Context Learning (ICL) has emerged as an important new paradigm in natural language processing and large language model (LLM) applications. However, the theoretical understanding of the ICL mechanism remains limited. This paper aims to investigate this issue by studying a particular ICL approach, called concept-based ICL (CB-ICL). In particular, we propose theoretical analyses on applying CB-ICL to ICL tasks, which explains why and when the CB-ICL performs well for predicting query labels in…

SQUARE: Semantic Query-Augmented Fusion and Efficient Batch Reranking for Training-free Zero-Shot Composed Image Retrieval
Ren-Di Wu, Yu-Yen Lin, Huei-Fang Yang
https://arxiv.org/abs/2509.26330

SQUARE: Semantic Query-Augmented Fusion and Efficient Batch Reranking for Training-free Zero-Shot Composed Image Retrieval
Composed Image Retrieval (CIR) aims to retrieve target images that preserve the visual content of a reference image while incorporating user-specified textual modifications. Training-free zero-shot CIR (ZS-CIR) approaches, which require no task-specific training or labeled data, are highly desirable, yet accurately capturing user intent remains challenging. In this paper, we present SQUARE, a novel two-stage training-free framework that leverages Multimodal Large Language Models (MLLMs) to enha…

TASP: Topology-aware Sequence Parallelism
Yida Wang (Capital Normal University, Infinigence-AI), Ke Hong (Tsinghua University, Infinigence-AI), Xiuhong Li (Infinigence-AI), Yuanchao Xu (Capital Normal University), Wenxun Wang (Tsinghua University), Guohao Dai (Infinigence-AI, Shanghai Jiao Tong University), Yu Wang (Tsinghua University)
https://

TASP: Topology-aware Sequence Parallelism
Long-context large language models (LLMs) face constraints due to the quadratic complexity of the self-attention mechanism. The mainstream sequence parallelism (SP) method, Ring Attention, attempts to solve this by distributing the query into multiple query chunks across accelerators and enable each Q tensor to access all KV tensors from other accelerators via the Ring AllGather communication primitive. However, it exhibits low communication efficiency, restricting its practical applicability. …

Poseidon: A OneGraph Engine
Brad Bebee, \"Umit V. \c{C}ataly\"urek, Olaf Hartig, Ankesh Khandelwal, Simone Rondelli, Michael Schmidt, Lefteris Sidirourgos, Bryan Thompson
https://arxiv.org/abs/2510.11166

Poseidon: A OneGraph Engine
We present the Poseidon engine behind the Neptune Analytics graph database service. Customers interact with Poseidon using the declarative openCypher query language, which enables requests that seamlessly combine traditional querying paradigms (such as graph pattern matching, variable length paths, aggregation) with algorithm invocations and has been syntactically extended to facilitate OneGraph interoperability, such as the disambiguation between globally unique IRIs (as exposed via RDF) vs. l…

Replaced article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[2/3]:
- Query-Level Uncertainty in Large Language Models
Lihu Chen, Gerard de Melo, Fabian M. Suchanek, Ga\"el Varoquaux

Doc2Query : Topic-Coverage based Document Expansion and its Application to Dense Retrieval via Dual-Index Fusion
Tzu-Lin Kuo, Wei-Ning Chiu, Wei-Yun Ma, Pu-Jen Cheng
https://arxiv.org/abs/2510.09557

Doc2Query++: Topic-Coverage based Document Expansion and its Application to Dense Retrieval via Dual-Index Fusion
Document expansion (DE) via query generation tackles vocabulary mismatch in sparse retrieval, yet faces limitations: uncontrolled generation producing hallucinated or redundant queries with low diversity; poor generalization from in-domain training (e.g., MS MARCO) to out-of-domain data like BEIR; and noise from concatenation harming dense retrieval. While Large Language Models (LLMs) enable cross-domain query generation, basic prompting lacks control, and taxonomy-based methods rely on domain-…

Differentially Private Synthetic Text Generation for Retrieval-Augmented Generation (RAG)
Junki Mori, Kazuya Kakizaki, Taiki Miyagawa, Jun Sakuma
https://arxiv.org/abs/2510.06719

Differentially Private Synthetic Text Generation for Retrieval-Augmented Generation (RAG)
Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by grounding them in external knowledge. However, its application in sensitive domains is limited by privacy risks. Existing private RAG methods typically rely on query-time differential privacy (DP), which requires repeated noise injection and leads to accumulated privacy loss. To address this issue, we propose DP-SynRAG, a framework that uses LLMs to generate differentially private synthetic RAG databases. Unlike prior…

The silence of the weights: an investigation of structural pruning strategies for attention-based audio signal architectures
Andrea Diecidue, Carlo Alberto Barbano, Piero Fraternali, Mathieu Fontaine, Enzo Tartaglione
https://arxiv.org/abs/2509.26207

The silence of the weights: an investigation of structural pruning strategies for attention-based audio signal architectures
Transformer-based models have become the state of the art across multiple domains, from natural language processing to machine listening, thanks to attention mechanisms. However, the attention layers require a large number of parameters and high-end hardware for both training and inference. We propose a novel pruning technique targeted explicitly at the attention mechanism, where we decouple the pruning of the four layers in the attention block, namely: query, keys, values and outputs' projecti…

ARUQULA -- An LLM based Text2SPARQL Approach using ReAct and Knowledge Graph Exploration Utilities
Felix Brei, Lorenz B\"uhmann, Johannes Frey, Daniel Gerber, Lars-Peter Meyer, Claus Stadler, Kirill Bulert
https://arxiv.org/abs/2510.02200

ARUQULA -- An LLM based Text2SPARQL Approach using ReAct and Knowledge Graph Exploration Utilities
Interacting with knowledge graphs can be a daunting task for people without a background in computer science since the query language that is used (SPARQL) has a high barrier of entry. Large language models (LLMs) can lower that barrier by providing support in the form of Text2SPARQL translation. In this paper we introduce a generalized method based on SPINACH, an LLM backed agent that translates natural language questions to SPARQL queries not in a single shot, but as an iterative process of e…

From Reasoning LLMs to BERT: A Two-Stage Distillation Framework for Search Relevance
Runze Xia, Yupeng Ji, Yuxi Zhou, Haodong Liu, Teng Zhang, Piji Li
https://arxiv.org/abs/2510.11056

From Reasoning LLMs to BERT: A Two-Stage Distillation Framework for Search Relevance
Query-service relevance prediction in e-commerce search systems faces strict latency requirements that prevent the direct application of Large Language Models (LLMs). To bridge this gap, we propose a two-stage reasoning distillation framework to transfer reasoning capabilities from a powerful teacher LLM to a lightweight, deployment-friendly student model. In the first stage, we address the limitations of general-purpose LLMs by constructing a domain-adapted teacher model. This is achieved thro…

TaoSR-SHE: Stepwise Hybrid Examination Reinforcement Learning Framework for E-commerce Search Relevance
Pengkun Jiao, Yiming Jin, Jianhui Yang, Chenhe Dong, Zerui Huang, Shaowei Yao, Xiaojiang Zhou, Dan Ou, Haihong Tang
https://arxiv.org/abs/2510.07972

TaoSR-SHE: Stepwise Hybrid Examination Reinforcement Learning Framework for E-commerce Search Relevance
Query-product relevance analysis is a foundational technology in e-commerce search engines and has become increasingly important in AI-driven e-commerce. The recent emergence of large language models (LLMs), particularly their chain-of-thought (CoT) reasoning capabilities, offers promising opportunities for developing relevance systems that are both more interpretable and more robust. However, existing training paradigms have notable limitations: SFT and DPO suffer from poor generalization on l…

From NL2SQL to NL2GeoSQL: GeoSQL-Eval for automated evaluation of LLMs on PostGIS queries
Shuyang Hou, Haoyue Jiao, Ziqi Liu, Lutong Xie, Guanyu Chen, Shaowen Wu, Xuefeng Guan, Huayi Wu
https://arxiv.org/abs/2509.25264

From NL2SQL to NL2GeoSQL: GeoSQL-Eval for automated evaluation of LLMs on PostGIS queries
In recent years, large language models (LLMs) have achieved remarkable progress in natural language understanding and structured query generation (NL2SQL). However, extending these advances to GeoSQL tasks in the PostGIS environment remains challenging due to the complexity of spatial functions, geometric data types, and execution semantics. Existing evaluations primarily focus on general relational databases or Google Earth Engine code generation, leaving a lack of systematic benchmarks tailor…

BESPOKE: Benchmark for Search-Augmented Large Language Model Personalization via Diagnostic Feedback
Hyunseo Kim, Sangam Lee, Kwangwook Seo, Dongha Lee
https://arxiv.org/abs/2509.21106

BESPOKE: Benchmark for Search-Augmented Large Language Model Personalization via Diagnostic Feedback
Search-augmented large language models (LLMs) have advanced information-seeking tasks by integrating retrieval into generation, reducing users' cognitive burden compared to traditional search systems. Yet they remain insufficient for fully addressing diverse user needs, which requires recognizing how the same query can reflect different intents across users and delivering information in preferred forms. While recent systems such as ChatGPT and Gemini attempt personalization by leveraging user h…

Bridging Language Gaps: Advances in Cross-Lingual Information Retrieval with Multilingual LLMs
Roksana Goworek, Olivia Macmillan-Scott, Eda B. \"Ozyi\u{g}it
https://arxiv.org/abs/2510.00908

Bridging Language Gaps: Advances in Cross-Lingual Information Retrieval with Multilingual LLMs
Cross-lingual information retrieval (CLIR) addresses the challenge of retrieving relevant documents written in languages different from that of the original query. Research in this area has typically framed the task as monolingual retrieval augmented by translation, treating retrieval methods and cross-lingual capabilities in isolation. Both monolingual and cross-lingual retrieval usually follow a pipeline of query expansion, ranking, re-ranking and, increasingly, question answering. Recent adv…

Mixture of Thoughts: Learning to Aggregate What Experts Think, Not Just What They Say
Jacob Fein-Ashley, Dhruv Parikh, Rajgopal Kannan, Viktor Prasanna
https://arxiv.org/abs/2509.21164

Mixture of Thoughts: Learning to Aggregate What Experts Think, Not Just What They Say
Open-source Large Language Models (LLMs) increasingly specialize by domain (e.g., math, code, general reasoning), motivating systems that leverage complementary strengths across models. Prior multi-LLM approaches either (i) route a query to one or a few experts and generate independently, (ii) aggregate outputs from each model via costly multi-turn exchanges, or (iii) fuse weights into a single model-typically requiring architectural homogeneity. We introduce Mixture of Thoughts (MoT), a simple…

Play by the Type Rules: Inferring Constraints for LLM Functions in Declarative Programs
Parker Glenn, Alfy Samuel, Daben Liu
https://arxiv.org/abs/2509.20208 https://

Play by the Type Rules: Inferring Constraints for LLM Functions in Declarative Programs
Integrating LLM powered operators in declarative query languages allows for the combination of cheap and interpretable functions with powerful, generalizable language model reasoning. However, in order to benefit from the optimized execution of a database query language like SQL, generated outputs must align with the rules enforced by both type checkers and database contents. Current approaches address this challenge with orchestrations consisting of many LLM-based post-processing calls to ensu…

CoDA: Agentic Systems for Collaborative Data Visualization
Zichen Chen, Jiefeng Chen, Sercan \"O. Arik, Misha Sra, Tomas Pfister, Jinsung Yoon
https://arxiv.org/abs/2510.03194

CoDA: Agentic Systems for Collaborative Data Visualization
Deep research has revolutionized data analysis, yet data scientists still devote substantial time to manually crafting visualizations, highlighting the need for robust automation from natural language queries. However, current systems struggle with complex datasets containing multiple files and iterative refinement. Existing approaches, including simple single- or multi-agent systems, often oversimplify the task, focusing on initial query parsing while failing to robustly manage data complexity…

Automated Discovery of Test Oracles for Database Management Systems Using LLMs
Qiuyang Mang, Runyuan He, Suyang Zhong, Xiaoxuan Liu, Huanchen Zhang, Alvin Cheung
https://arxiv.org/abs/2510.06663

Automated Discovery of Test Oracles for Database Management Systems Using LLMs
Since 2020, automated testing for Database Management Systems (DBMSs) has flourished, uncovering hundreds of bugs in widely-used systems. A cornerstone of these techniques is test oracle, which typically implements a mechanism to generate equivalent query pairs, thereby identifying bugs by checking the consistency between their results. However, while applying these oracles can be automated, their design remains a fundamentally manual endeavor. This paper explores the use of large language mode…

TaoSR-AGRL: Adaptive Guided Reinforcement Learning Framework for E-commerce Search Relevance
Jianhui Yang, Yiming Jin, Pengkun Jiao, Chenhe Dong, Zerui Huang, Shaowei Yao, Xiaojiang Zhou, Dan Ou, Haihong Tang
https://arxiv.org/abs/2510.08048

TaoSR-AGRL: Adaptive Guided Reinforcement Learning Framework for E-commerce Search Relevance
Query-product relevance prediction is fundamental to e-commerce search and has become even more critical in the era of AI-powered shopping, where semantic understanding and complex reasoning directly shape the user experience and business conversion. Large Language Models (LLMs) enable generative, reasoning-based approaches, typically aligned via supervised fine-tuning (SFT) or preference optimization methods like Direct Preference Optimization (DPO). However, the increasing complexity of busin…

QueryGym: Step-by-Step Interaction with Relational Databases
Haritha Ananthakrishanan, Harsha Kokel, Kelsey Sikes, Debarun Bhattacharjya, Michael Katz, Shirin Sohrabi, Kavitha Srinivas
https://arxiv.org/abs/2509.21674

QueryGym: Step-by-Step Interaction with Relational Databases
We introduce QueryGym, an interactive environment for building, testing, and evaluating LLM-based query planning agents. Existing frameworks often tie agents to specific query language dialects or obscure their reasoning; QueryGym instead requires agents to construct explicit sequences of relational algebra operations, ensuring engine-agnostic evaluation and transparent step-by-step planning. The environment is implemented as a Gymnasium interface that supplies observations -- including schema …

Learning Compact Representations of LLM Abilities via Item Response Theory
Jianhao Chen, Chenxu Wang, Gengrui Zhang, Peng Ye, Lei Bai, Wei Hu, Yuzhong Qu, Shuyue Hu
https://arxiv.org/abs/2510.00844

Learning Compact Representations of LLM Abilities via Item Response Theory
Recent years have witnessed a surge in the number of large language models (LLMs), yet efficiently managing and utilizing these vast resources remains a significant challenge. In this work, we explore how to learn compact representations of LLM abilities that can facilitate downstream tasks, such as model routing and performance prediction on new benchmarks. We frame this problem as estimating the probability that a given model will correctly answer a specific query. Inspired by the item respon…

Reasoning by Exploration: A Unified Approach to Retrieval and Generation over Graphs
Haoyu Han, Kai Guo, Harry Shomer, Yu Wang, Yucheng Chu, Hang Li, Li Ma, Jiliang Tang
https://arxiv.org/abs/2510.07484

Reasoning by Exploration: A Unified Approach to Retrieval and Generation over Graphs
Reasoning over structured graphs remains a fundamental challenge for Large Language Models (LLMs), particularly when scaling to large graphs. Existing approaches typically follow the retrieval-augmented generation (RAG) paradigm: first retrieving subgraphs relevant to the query and then generating answers conditioned on the retrieved subgraphs. However, such two-phase pipelines often struggle to faithfully incorporate graph structure, since the generation process is ultimately constrained by th…

Drawing Conclusions from Draws: Rethinking Preference Semantics in Arena-Style LLM Evaluation
Raphael Tang, Crystina Zhang, Wenyan Li, Carmen Lai, Pontus Stenetorp, Yao Lu
https://arxiv.org/abs/2510.02306

Drawing Conclusions from Draws: Rethinking Preference Semantics in Arena-Style LLM Evaluation
In arena-style evaluation of large language models (LLMs), two LLMs respond to a user query, and the user chooses the winning response or deems the "battle" a draw, resulting in an adjustment to the ratings of both models. The prevailing approach for modeling these rating dynamics is to view battles as two-player game matches, as in chess, and apply the Elo rating system and its derivatives. In this paper, we critically examine this paradigm. Specifically, we question whether a draw genuinely m…

Learning Compact Representations of LLM Abilities via Item Response Theory
Jianhao Chen, Chenxu Wang, Gengrui Zhang, Peng Ye, Lei Bai, Wei Hu, Yuzhong Qu, Shuyue Hu
https://arxiv.org/abs/2510.00844

Learning Compact Representations of LLM Abilities via Item Response Theory
Recent years have witnessed a surge in the number of large language models (LLMs), yet efficiently managing and utilizing these vast resources remains a significant challenge. In this work, we explore how to learn compact representations of LLM abilities that can facilitate downstream tasks, such as model routing and performance prediction on new benchmarks. We frame this problem as estimating the probability that a given model will correctly answer a specific query. Inspired by the item respon…

F2LLM Technical Report: Matching SOTA Embedding Performance with 6 Million Open-Source Data
Ziyin Zhang, Zihan Liao, Hang Yu, Peng Di, Rui Wang
https://arxiv.org/abs/2510.02294 …

F2LLM Technical Report: Matching SOTA Embedding Performance with 6 Million Open-Source Data
We introduce F2LLM - Foundation to Feature Large Language Models, a suite of state-of-the-art embedding models in three sizes: 0.6B, 1.7B, and 4B. Unlike previous top-ranking embedding models that require massive contrastive pretraining, sophisticated training pipelines, and costly synthetic training data, F2LLM is directly finetuned from foundation models on 6 million query-document-negative tuples curated from open-source, non-synthetic datasets, striking a strong balance between training cos…

PARROT: A Benchmark for Evaluating LLMs in Cross-System SQL Translation
Wei Zhou, Guoliang Li, Haoyu Wang, Yuxing Han, Xufei Wu, Fan Wu, Xuanhe Zhou
https://arxiv.org/abs/2509.23338

PARROT: A Benchmark for Evaluating LLMs in Cross-System SQL Translation
Large language models (LLMS) have shown increasing effectiveness in Text-to-SQL tasks. However, another closely related problem, Cross-System SQL Translation (a.k.a., SQL-to-SQL), which adapts a query written for one database system (e.g., MySQL) into its equivalent one for another system (e.g., ClickHouse), is of great practical importance but remains underexplored. Existing SQL benchmarks are not well-suited for SQL-to-SQL evaluation, which (1) focus on a limited set of database systems (ofte…

Study on LLMs for Promptagator-Style Dense Retriever Training
Daniel Gwon, Nour Jedidi, Jimmy Lin
https://arxiv.org/abs/2510.02241 https://arxiv.org/pdf/25…

Study on LLMs for Promptagator-Style Dense Retriever Training
Promptagator demonstrated that Large Language Models (LLMs) with few-shot prompts can be used as task-specific query generators for fine-tuning domain-specialized dense retrieval models. However, the original Promptagator approach relied on proprietary and large-scale LLMs which users may not have access to or may be prohibited from using with sensitive data. In this work, we study the impact of open-source LLMs at accessible scales ($\leq$14B parameters) as an alternative. Our results demonstr…