arXiv subjects

Yuanfeng Song

Publications and source records attributed to Yuanfeng Song.

At least 19 recordsLinked to original sources

arXiv2026

SkillLens: Visual Skill Cards for Retrieval-Augmented GUI Action Prediction and On-Policy Distillation

Computer-using agents can perceive rich software interfaces, yet their decisions often lack visual procedural memory: they may recognize individual controls without identifying which familiar workflow is active, which control matters next, or what evidence would confirm progress. Raw interaction traces preserve such information but are long and noisy to condition on, whereas text-only skills often omit the visual state that makes a procedure applicable. We introduce Visual Skill Cards (VSCs), a state-conditioned memory representation that binds reusable procedures with applicability cues, visual evidence, and verification signals. SkillLens constructs VSCs from heterogeneous interaction experience through Trace-to-Visual-Skill-Card and, at inference time, retrieves relevant cards and selectively expands only the evidence needed by a fixed visual-language model executor for grounded GUI action prediction. The same representation also supports CardDistill, which uses VSC evidence as privileged teacher context to train a student that acts without runtime card retrieval. Across Multimodal-Mind2Web and WebLINX-BrowserGym, SkillLens improves the frozen GPT-5.4-mini executor by +11.6 points in Step SR and +2.9 points in Overall, respectively; CardDistill further improves the corresponding student-only Qwen3-VL-2B metrics by +12.0 and +3.2 points.

cs.AI↗

arXiv2026

Can Coding Agents Solve Repository-Level Issues with Rendered Code? An Exploratory Study of Visual Representations

Visual modality has recently been explored as a way to compress textual tokens, including rendering code as images for static code understanding. We study whether this representation can serve as operational context for agentic coding, where an agent must navigate repositories, edit source files, and verify executable patches. Using SWE-bench Verified, we evaluate rendered code in repository-level repair workflows and introduce controlled agent settings to separate unguided repository exploration from more structured repair stages. Our results show a mixed picture. Rendered code consistently reduces prompt-token cost, but the savings do not increase linearly with the nominal visual compression ratio. It largely preserves end-to-end repair accuracy, but does not overcome the performance limits of the underlying model or agent architecture, and can become unstable under aggressive compression. Further analysis suggests that visual code is most useful when raw source reading is a major bottleneck; once repository localization is structured, much of the remaining cost comes from patch--test trial-and-error, where visual compression has limited leverage. Overall, our study positions rendered code as a viable but conditional compression mechanism for realistic coding agents.

cs.HC↗

arXiv2026

SrDetection: A Self-Referential Framework for Data Leakage Detection in Code Large Language Models

Evaluating code large language models (Code LLMs) requires reliable detection of data leakage, where benchmark performance is artificially inflated by exposure to benchmark data during pre-training. Existing approaches either assume access to proprietary training corpora, rely on brittle heuristics such as timestamp filtering, or use external reference sets with manually tuned, non-generalizable thresholds. To address these limitations, we introduce \textbf{SrDetection}, a unified \textbf{s}elf-\textbf{r}eferential leakage detection framework for both gray-box (access to model logits) and black-box (access to model outputs) settings. SrDetection generates semantically equivalent variants of a benchmark sample and detects leakage by contrasting the model's behavior on the original versus its variants, flagging cases where the original is disproportionately easier for the model. We further design a controlled leakage detection testbed and evaluate SrDetection in this environment. Across different models and training stages, SrDetection improves average F1 by 21.52 points in the gray-box setting and 14.46 points in the black-box setting over strong baselines, demonstrating robust, threshold-independent leakage detection. Finally, a gray-box study of 15 widely used Code LLMs on four popular benchmarks reveals benchmark-specific leakage patterns beyond prior overlap-based analyses\footnote{\footnotesize Source code and data are available at https://github.com/SMinL/SrDetectionCode

cs.CL↗

arXiv2026

Self-Evolving Deep Research via Joint Generation and Evaluation

Large Language Models (LLMs) have become increasingly adopted in daily applications, with deep research standing out as a particularly important capability. Unlike traditional question-answering (QA) tasks, deep research report generation lacks definitive ground-truth, making reward design inherently unverifiable and limiting effective reinforcement learning. Existing approaches mitigate this challenge with LLM-as-a-judge and query-dependent evaluation rubrics, but they still rely on static evaluators that cannot adapt their standards as the solver improves, leading to insufficient and eventually saturated optimization pressure. We address this limitation with a \textbf{s}elf-evolving \textbf{co}-evolutionary training framework for deep \textbf{re}search evaluation and generation (SCORE), which tightly couples an evaluator and a solver in a shared-parameter learning process. Rather than treating generation and evaluation as isolated modules, we leverage their intrinsic connection to enable joint improvement within a single shared-parameter model. To restrict this process, we introduce a meta-harness, which dynamically controls the evaluation environment based on solver performance, encouraging valid evaluation dimensions and sufficiently deep evaluator search. Extensive experiments on deep research benchmarks demonstrate consistent improvement in report generation quality, showing that co-evolving evaluation and generation is a promising direction for training open-ended research agents.

cs.CL↗

arXiv2026

Towards Reliable Agentic Progressive Text-to-Visualization with Verification Rules

Text-to-Visualization (Text-to-Vis) translates natural language queries into visualization query languages, enabling non-expert users to perform data analysis. However, most existing methods follow a one-shot paradigm that requires users to specify all visualization details in a single round, often leading to cognitive overload and incorrect visualizations. In this paper, we propose PMVis, a progressive multi-turn paradigm for text-to-vis, where users' intents are refined through multi-turn interactions. To support research in this paradigm, we construct PMVisBench, the first dataset designed to capture the progressive and iterative nature of real-world user queries. It is built through VQL simplification and NLQ reconstruction, with explicit rule constraints to ensure each intermediate VQL remains valid and meaningful. Building upon PMVis, we further introduce PMVisAgent, an agent-based framework that simulates realistic user-system dialogues. PMVisAgent consists of a User, a System, and a Validation Agent that performs verification and repair via a ReAct-style tool-use loop to mitigate error accumulation across rounds, with explicit interaction and verification rules to ensure reliability of the multi-agent system. Extensive experiments on PMVisBench demonstrate that PMVisAgent significantly outperforms state-of-the-art text-to-vis baselines. It achieves up to 17.57\% and 23.21\% improvements in execution accuracy in single-table and multi-table settings, respectively, while ablation studies confirm the importance of combining progressive interaction with clarification. The code is available at https://github.com/wxxv/PMVis.

cs.DB↗

arXiv2026

FedProxy: Federated Fine-Tuning of LLMs via Proxy SLMs and Heterogeneity-Aware Fusion

Federated fine-tuning of Large Language Models (LLMs) is obstructed by a trilemma of challenges: protecting LLMs intellectual property (IP), ensuring client privacy, and mitigating performance loss on heterogeneous data. Existing methods like Offsite-Tuning (OT) secure the LLMs IP by having clients train only lightweight adapters, yet our analysis reveals they suffer from a fundamental performance bottleneck, leaving a significant gap compared to centralized training. To bridge this gap, we introduce FedProxy, a new federated adaptation framework. FedProxy replaces weak adapters with a unified, powerful Proxy Small Language Model (SLM), compressed from the proprietary LLM, to serve as a high-fidelity surrogate for collaborative fine-tuning. Our framework systematically resolves the trilemma through a three-stage architecture: (i) Efficient Representation via server-guided compression to create a resource-friendly proxy; (ii) Robust Optimization through an interference-mitigating aggregation strategy to handle data heterogeneity; and (iii) Effortless Fusion via a training-free "plug-in" mechanism to integrate learned knowledge back into the LLM. Experiments show FedProxy significantly outperforms OT methods and approaches centralized performance, establishing a new benchmark for secure and high-performance federated LLM adaptation.

cs.LG↗

arXiv2026

Monte Carlo Tree Search with Reasoning Path Refinement for Small Language Models in Conversational Text-to-NoSQL

NoSQL databases have been widely adopted in big data analytics, geospatial applications, and healthcare services, due to their flexibility and scalability. However, querying NoSQL databases requires specialized technical expertise, creating a high barrier for users. While recent studies have explored text-to-NoSQL problem, they primarily focus on single-turn interactions, ignoring the conversational nature of real-world queries. To bridge this gap, we introduce the Conversational Text-to-NoSQL task, which generates NoSQL queries given a natural language question, a NoSQL database, and the dialogue history. To address this task, we propose Stage-MCTS, a framework that endows small language models (SLMs) with NoSQL-specific reasoning capabilities by formulating query generation as a search problem. The framework employs Monte Carlo Tree Search (MCTS) guided by a rule-based reward to produce stepwise reasoning data, followed by progressive supervised fine-tuning (SFT) and self-training strategies. We further construct CoNoSQL, a cross-domain dataset with over 2,000 dialogues and 150 databases, to support evaluation. Experiments demonstrate that our approach outperforms state-of-the-art large reasoning models, improving execution value match (EVM) accuracy by up to 7.93%.

cs.DB↗

arXiv2026

MultiVis-Agent: A Multi-Agent Framework with Logic Rules for Reliable and Comprehensive Cross-Modal Data Visualization

Real-world visualization tasks involve complex, multi-modal requirements that extend beyond simple text-to-chart generation, requiring reference images, code examples, and iterative refinement. Current systems exhibit fundamental limitations: single-modality input, one-shot generation, and rigid workflows. While LLM-based approaches show potential for these complex requirements, they introduce reliability challenges including catastrophic failures and infinite loop susceptibility. To address this gap, we propose MultiVis-Agent, a logic rule-enhanced multi-agent framework for reliable multi-modal and multi-scenario visualization generation. Our approach introduces a four-layer logic rule framework that provides mathematical guarantees for system reliability while maintaining flexibility. Unlike traditional rule-based systems, our logic rules are mathematical constraints that guide LLM reasoning rather than replacing it. We formalize the MultiVis task spanning four scenarios from basic generation to iterative refinement, and develop MultiVis-Bench, a benchmark with over 1,000 cases for multi-modal visualization evaluation. Extensive experiments demonstrate that our approach achieves 75.63% visualization score on challenging tasks, significantly outperforming baselines (57.54-62.79%), with task completion rates of 99.58% and code execution success rates of 94.56% (vs. 74.48% and 65.10% without logic rules), successfully addressing both complexity and reliability challenges in automated visualization generation.

cs.CL↗

arXiv2025

MedInsightBench: Evaluating Medical Analytics Agents Through Multi-Step Insight Discovery in Multimodal Medical Data

In medical data analysis, extracting deep insights from complex, multi-modal datasets is essential for improving patient care, increasing diagnostic accuracy, and optimizing healthcare operations. However, there is currently a lack of high-quality datasets specifically designed to evaluate the ability of large multi-modal models (LMMs) to discover medical insights. In this paper, we introduce MedInsightBench, the first benchmark that comprises 332 carefully curated medical cases, each annotated with thoughtfully designed insights. This benchmark is intended to evaluate the ability of LMMs and agent frameworks to analyze multi-modal medical image data, including posing relevant questions, interpreting complex findings, and synthesizing actionable insights and recommendations. Our analysis indicates that existing LMMs exhibit limited performance on MedInsightBench, which is primarily attributed to their challenges in extracting multi-step, deep insights and the absence of medical expertise. Therefore, we propose MedInsightAgent, an automated agent framework for medical data analysis, composed of three modules: Visual Root Finder, Analytical Insight Agent, and Follow-up Question Composer. Experiments on MedInsightBench highlight pervasive challenges and demonstrate that MedInsightAgent can improve the performance of general LMMs in medical data insight discovery.

cs.AI↗

arXiv2025

DataGovBench: Benchmarking LLM Agents for Real-World Data Governance Workflows

Data governance ensures data quality, security, and compliance through policies and standards, a critical foundation for scaling modern AI development. Recently, large language models (LLMs) have emerged as a promising solution for automating data governance by translating user intent into executable transformation code. However, existing benchmarks for automated data science often emphasize snippet-level coding or high-level analytics, failing to capture the unique challenge of data governance: ensuring the correctness and quality of the data itself. To bridge this gap, we introduce DataGovBench, a benchmark featuring 150 diverse tasks grounded in real-world scenarios, built on data from actual cases. DataGovBench employs a novel "reversed-objective" methodology to synthesize realistic noise and utilizes rigorous metrics to assess end-to-end pipeline reliability. Our analysis on DataGovBench reveals that current models struggle with complex, multi-step workflows and lack robust error-correction mechanisms. Consequently, we propose DataGovAgent, a framework utilizing a Planner-Executor-Evaluator architecture that integrates constraint-based planning, retrieval-augmented generation, and sandboxed feedback-driven debugging. Experimental results show that DataGovAgent significantly boosts the Average Task Score (ATS) on complex tasks from 39.7 to 54.9 and reduces debugging iterations by over 77.9 percent compared to general-purpose baselines.

cs.AI↗

arXiv2025

OsmT: Bridging OpenStreetMap Queries and Natural Language with Open-source Tag-aware Language Models

Bridging natural language and structured query languages is a long-standing challenge in the database community. While recent advances in language models have shown promise in this direction, existing solutions often rely on large-scale closed-source models that suffer from high inference costs, limited transparency, and lack of adaptability for lightweight deployment. In this paper, we present OsmT, an open-source tag-aware language model specifically designed to bridge natural language and Overpass Query Language (OverpassQL), a structured query language for accessing large-scale OpenStreetMap (OSM) data. To enhance the accuracy and structural validity of generated queries, we introduce a Tag Retrieval Augmentation (TRA) mechanism that incorporates contextually relevant tag knowledge into the generation process. This mechanism is designed to capture the hierarchical and relational dependencies present in the OSM database, addressing the topological complexity inherent in geospatial query formulation. In addition, we define a reverse task, OverpassQL-to-Text, which translates structured queries into natural language explanations to support query interpretation and improve user accessibility. We evaluate OsmT on a public benchmark against strong baselines and observe consistent improvements in both query generation and interpretation. Despite using significantly fewer parameters, our model achieves competitive accuracy, demonstrating the effectiveness of open-source pre-trained language models in bridging natural language and structured query languages within schema-rich geospatial environments.

cs.CL↗

arXiv2025

InsightEval: An Expert-Curated Benchmark for Assessing Insight Discovery in LLM-Driven Data Agents

Data analysis has become an indispensable part of scientific research. To discover the latent knowledge and insights hidden within massive datasets, we need to perform deep exploratory analysis to realize their full value. With the advent of large language models (LLMs) and multi-agent systems, more and more researchers are making use of these technologies for insight discovery. However, there are few benchmarks for evaluating insight discovery capabilities. As one of the most comprehensive existing frameworks, InsightBench also suffers from many critical flaws: format inconsistencies, poorly conceived objectives, and redundant insights. These issues may significantly affect the quality of data and the evaluation of agents. To address these issues, we thoroughly investigate shortcomings in InsightBench and propose essential criteria for a high-quality insight benchmark. Regarding this, we develop a data-curation pipeline to construct a new dataset named InsightEval. We further introduce a novel metric to measure the exploratory performance of agents. Through extensive experiments on InsightEval, we highlight prevailing challenges in automated insight discovery and raise some key findings to guide future research in this promising direction.

cs.AI↗

arXiv2025

Beyond Query-Level Comparison: Fine-Grained Reinforcement Learning for Text-to-SQL with Automated Interpretable Critiques

Text-to-SQL, a pivotal natural language processing (NLP) task that converts textual queries into executable SQL, has seen substantial progress in recent years. However, existing evaluation and reward mechanisms used to train and assess the text-to-SQL models remain a critical bottleneck. Current approaches heavily rely on manually annotated gold SQL queries, which are costly to produce and impractical for large-scale evaluation. More importantly, most reinforcement learning (RL) methods in text-to-SQL leverage only the final binary execution outcome as the reward signal, a coarse-grained supervision that overlooks detailed structural and semantic errors from the perspective of rubrics. To address these challenges, we propose RuCo-C, a novel generative judge model for fine-grained, query-specific automatic evaluation using interpretable critiques without human intervention. Our framework first automatically generates query-specific evaluation rubrics for human-free annotation, linking them to interpretable critiques. Subsequently, it integrates densified reward feedback through a "progressive exploration" strategy during the RL training process, which dynamically adjusts the rewards to enhance the model's performance. Comprehensive experiments demonstrate that RuCo-C outperforms existing methods in text-to-SQL evaluation, yielding significant performance gains.

cs.CL↗

arXiv2025

DataSage: Multi-agent Collaboration for Insight Discovery with External Knowledge Retrieval, Multi-role Debating, and Multi-path Reasoning

In today's data-driven era, fully automated end-to-end data analytics, particularly insight discovery, is critical for discovering actionable insights that assist organizations in making effective decisions. With the rapid advancement of large language models (LLMs), LLM-driven agents have emerged as a promising paradigm for automating data analysis and insight discovery. However, existing data insight agents remain limited in several key aspects, often failing to deliver satisfactory results due to: (1) insufficient utilization of domain knowledge, (2) shallow analytical depth, and (3) error-prone code generation during insight generation. To address these issues, we propose DataSage, a novel multi-agent framework that incorporates three innovative features including external knowledge retrieval to enrich the analytical context, a multi-role debating mechanism to simulate diverse analytical perspectives and deepen analytical depth, and multi-path reasoning to improve the accuracy of the generated code and insights. Extensive experiments on InsightBench demonstrate that DataSage consistently outperforms existing data insight agents across all difficulty levels, offering an effective solution for automated data insight discovery.

cs.AI↗

arXiv2025

Beyond SELECT: A Comprehensive Taxonomy-Guided Benchmark for Real-World Text-to-SQL Translation

Text-to-SQL datasets are essential for training and evaluating text-to-SQL models, but existing datasets often suffer from limited coverage and fail to capture the diversity of real-world applications. To address this, we propose a novel taxonomy for text-to-SQL classification based on dimensions including core intents, statement types, syntax structures, and key actions. Using this taxonomy, we evaluate widely used public text-to-SQL datasets (e.g., Spider and Bird) and reveal limitations in their coverage and diversity. We then introduce a taxonomy-guided dataset synthesis pipeline, yielding a new dataset named SQL-Synth. This approach combines the taxonomy with Large Language Models (LLMs) to ensure the dataset reflects the breadth and complexity of real-world text-to-SQL applications. Extensive analysis and experimental results validate the effectiveness of our taxonomy, as SQL-Synth exhibits greater diversity and coverage compared to existing benchmarks. Moreover, we uncover that existing LLMs typically fall short in adequately capturing the full range of scenarios, resulting in limited performance on SQL-Synth. However, fine-tuning can substantially improve their performance in these scenarios. The proposed taxonomy has significant potential impact, as it not only enables comprehensive analysis of datasets and the performance of different LLMs, but also guides the construction of training data for LLMs.

cs.CL↗

arXiv2025

UniDataBench: Evaluating Data Analytics Agents Across Structured and Unstructured Data

In the real business world, data is stored in a variety of sources, including structured relational databases, unstructured databases (e.g., NoSQL databases), or even CSV/excel files. The ability to extract reasonable insights across these diverse source is vital for business success. Existing benchmarks, however, are limited in assessing agents' capabilities across these diverse data types. To address this gap, we introduce UniDataBench, a comprehensive benchmark designed to evaluate the performance of data analytics agents in handling diverse data sources. Specifically, UniDataBench is originating from real-life industry analysis report and we then propose a pipeline to remove the privacy and sensitive information. It encompasses a wide array of datasets, including relational databases, CSV files to NoSQL data, reflecting real-world business scenarios, and provides unified framework to assess how effectively agents can explore multiple data formats, extract valuable insights, and generate meaningful summaries and recommendations. Based on UniDataBench, we propose a novel LLM-based agent named ReActInsight, an autonomous agent that performs end-to-end analysis over diverse data sources by automatically discovering cross-source linkages, decomposing goals, and generating robust, self-correcting code to extract actionable insights. Our benchmark and agent together provide a powerful framework for advancing the capabilities of data analytics agents in real-world applications.

cs.DB↗

arXiv2025

Towards Visualizing Electronic Medical Records via Natural Language Queries

Electronic medical records (EMRs) contain essential data for patient care and clinical research. With the diversity of structured and unstructured data in EHR, data visualization is an invaluable tool for managing and explaining these complexities. However, the scarcity of relevant medical visualization data and the high cost of manual annotation required to develop such datasets pose significant challenges to advancing medical visualization techniques. To address this issue, we propose an innovative approach using large language models (LLMs) for generating visualization data without labor-intensive manual annotation. We introduce a new pipeline for building text-to-visualization benchmarks suitable for EMRs, enabling users to visualize EMR statistics through natural language queries (NLQs). The dataset presented in this paper primarily consists of paired text medical records, NLQs, and corresponding visualizations, forming the first large-scale text-to-visual dataset for electronic medical record information called MedicalVis with 35,374 examples. Additionally, we introduce an LLM-based approach called MedCodeT5, showcasing its viability in generating EMR visualizations from NLQs, outperforming various strong text-to-visualization baselines. Our work facilitates standardized evaluation of EMR visualization methods while providing researchers with tools to advance this influential field of application. In a nutshell, this study and dataset have the potential to promote advancements in eliciting medical insights through visualization.

cs.DB↗

arXiv2025

Graph-Reward-SQL: Execution-Free Reinforcement Learning for Text-to-SQL via Graph Matching and Stepwise Reward

Reinforcement learning (RL) has been widely adopted to enhance the performance of large language models (LLMs) on Text-to-SQL tasks. However, existing methods often rely on execution-based or LLM-based Bradley-Terry reward models. The former suffers from high execution latency caused by repeated database calls, whereas the latter imposes substantial GPU memory overhead, both of which significantly hinder the efficiency and scalability of RL pipelines. To this end, we propose a novel reward model framework for RL-based Text-to-SQL named Graph-Reward-SQL, which employs the GMNScore outcome reward model. We leverage SQL graph representations to provide accurate reward signals while significantly reducing time cost and GPU memory usage. Building on this foundation, we further introduce StepRTM, a stepwise reward model that provides intermediate supervision over Common Table Expression (CTE) subqueries. This encourages both functional correctness and readability of SQL. Extensive comparative and ablation experiments on standard benchmarks, including Spider and BIRD, demonstrate that our method consistently outperforms existing reward models.

cs.LG↗