arXiv subjects

Ge Yu

Publications and source records attributed to Ge Yu.

At least 37 records · Page 2Linked to original sources

arXiv2026

Towards Autonomous Graph Data Analytics with Analytics-Augmented Generation

This paper argues that reliable end-to-end graph data analytics cannot be achieved by retrieval- or code-generation-centric LLM agents alone. Although large language models (LLMs) provide strong reasoning capabilities, practical graph analytics for non-expert users requires explicit analytical grounding to support intent-to-execution translation, task-aware graph construction, and reliable execution across diverse graph algorithms. We envision Analytics-Augmented Generation (AAG) as a new paradigm that treats analytical computation as a first-class concern and positions LLMs as knowledge-grounded analytical coordinators. By integrating knowledge-driven task planning, algorithm-centric LLM-analytics interaction, and task-aware graph construction, AAG enables end-to-end graph analytics pipelines that translate natural-language user intent into automated execution and interpretable results.

cs.DB↗

arXiv2026

UNIKIE-BENCH: Benchmarking Large Multimodal Models for Key Information Extraction in Visual Documents

Key Information Extraction (KIE) from real-world documents remains challenging due to substantial variations in layout structures, visual quality, and task-specific information requirements. Recent Large Multimodal Models (LMMs) have shown promising potential for performing end-to-end KIE directly from document images. To enable a comprehensive and systematic evaluation across realistic and diverse application scenarios, we introduce UNIKIE-BENCH, a unified benchmark designed to rigorously evaluate the KIE capabilities of LMMs. UNIKIE-BENCH consists of two complementary tracks: a constrained-category KIE track with scenario-predefined schemas that reflect practical application needs, and an open-category KIE track that extracts any key information that is explicitly present in the document. Experiments on 15 state-of-the-art LMMs reveal substantial performance degradation under diverse schema definitions, long-tail key fields, and complex layouts, along with pronounced performance disparities across different document types and scenarios. These findings underscore persistent challenges in grounding accuracy and layout-aware reasoning for LMM-based KIE. All codes and datasets are available at https://github.com/NEUIR/UNIKIE-BENCH.

cs.CV↗

arXiv2026

Lang2Act: Fine-Grained Visual Reasoning through Self-Emergent Linguistic Toolchains

Visual Retrieval-Augmented Generation (VRAG) enhances Vision-Language Models (VLMs) by incorporating external visual documents to address a given query. Existing VRAG frameworks usually depend on rigid, pre-defined external tools to extend the perceptual capabilities of VLMs, typically by explicitly separating visual perception from subsequent reasoning processes. However, this decoupled design can lead to unnecessary loss of visual information, particularly when image-based operations such as cropping are applied. In this paper, we propose Lang2Act, which enables fine-grained visual perception and reasoning through self-emergent linguistic toolchains. Rather than invoking fixed external engines, Lang2Act collects self-emergent actions as linguistic tools and leverages them to enhance the visual perception capabilities of VLMs. To support this mechanism, we design a two-stage Reinforcement Learning (RL)-based training framework. Specifically, the first stage optimizes VLMs to self-explore high-quality actions for constructing a reusable linguistic toolbox, and the second stage further optimizes VLMs to exploit these linguistic tools for downstream reasoning effectively. Experimental results demonstrate the effectiveness of Lang2Act in substantially enhancing the visual perception capabilities of VLMs, achieving performance improvements of over 4%. All code and data are available at https://github.com/NEUIR/Lang2Act.

cs.AI↗

arXiv2026

MetaMem: Evolving Meta-Memory for Knowledge Utilization through Self-Reflective Symbolic Optimization

Existing memory systems enable Large Language Models (LLMs) to support long-horizon human-LLM interactions by persisting historical interactions beyond limited context windows. However, while recent approaches have succeeded in constructing effective memories, they often disrupt the inherent logical and temporal relationships within interaction sessions, resulting in fragmented memory units and degraded reasoning performance. In this paper, we propose MetaMem, a novel framework that augments memory systems with a self-evolving meta-memory, aiming to teach LLMs how to effectively utilize memorized knowledge. During meta-memory optimization, MetaMem iteratively distills transferable knowledge utilization experiences across different tasks by self-reflecting on reasoning processes and performing actions to update the current meta-memory state. The accumulated meta-memory units serve as explicit knowledge utilization experiences, guiding the LLM to systematically identify and integrate critical evidence from scattered memory fragments. Extensive experiments demonstrate the effectiveness of MetaMem, which significantly outperforms strong baselines by over 3.6%. All codes and datasets are available at https://github.com/OpenBMB/MetaMem.

cs.CL↗

arXiv2026

Teaching LLMs to Learn Tool Trialing and Execution through Environment Interaction

Equipping Large Language Models (LLMs) with external tools enables them to solve complex real-world problems. However, the robustness of existing methods remains a critical challenge when confronting novel or evolving tools. Existing trajectory-centric paradigms primarily rely on memorizing static solution paths during training, which limits the ability of LLMs to generalize tool usage to newly introduced or previously unseen tools. In this paper, we propose ToolMaster, a framework that shifts tool use from imitating golden tool-calling trajectories to actively learning tool usage through interaction with the environment. To optimize LLMs for tool planning and invocation, ToolMaster adopts a trial-and-execution paradigm, which trains LLMs to first imitate teacher-generated trajectories containing explicit tool trials and self-correction, followed by reinforcement learning to coordinate the trial and execution phases jointly. This process enables agents to autonomously explore correct tool usage by actively interacting with environments and forming experiential knowledge that benefits tool execution. Experimental results demonstrate that ToolMaster significantly outperforms existing baselines in terms of generalization and robustness across unseen or unfamiliar tools. All code and data are available at https://github.com/NEUIR/ToolMaster.

cs.SE↗

arXiv2026

Long-Chain Reasoning Distillation via Adaptive Prefix Alignment

Large Language Models (LLMs) have demonstrated remarkable reasoning capabilities, particularly in solving complex mathematical problems. Recent studies show that distilling long reasoning trajectories can effectively enhance the reasoning performance of small-scale student models. However, teacher-generated reasoning trajectories are often excessively long and structurally complex, making them difficult for student models to learn. This mismatch leads to a gap between the provided supervision signal and the learning capacity of the student model. To address this challenge, we propose Prefix-ALIGNment distillation (P-ALIGN), a framework that fully exploits teacher CoTs for distillation through adaptive prefix alignment. Specifically, P-ALIGN adaptively truncates teacher-generated reasoning trajectories by determining whether the remaining suffix is concise and sufficient to guide the student model. Then, P-ALIGN leverages the teacher-generated prefix to supervise the student model, encouraging effective prefix alignment. Experiments on multiple mathematical reasoning benchmarks demonstrate that P-ALIGN outperforms all baselines by over 3%. Further analysis indicates that the prefixes constructed by P-ALIGN provide more effective supervision signals, while avoiding the negative impact of redundant and uncertain reasoning components. All code is available at https://github.com/NEUIR/P-ALIGN.

cs.CL↗

arXiv2026

SEEK: Steering LLM Reasoning for RAG via Internal Reasoning Sketches

Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by incorporating external knowledge into the generation process. Benefiting from the reasoning capabilities of LLMs, existing methods have leveraged such capabilities to enable iterative knowledge acquisition and accumulation, thereby better supporting answer generation. However, as the reasoning trajectory grows, the accumulated knowledge and previously generated queries may interfere with subsequent retrieval decisions, resulting in sub-queries with repetitive intents and redundant knowledge acquisition. To address this issue, we propose SEEK, a sketch-guided knowledge acquisition framework for RAG. SEEK first prompts the LLM to construct a structured steering sketch for the given question. It consists of multiple groups of steering gists, with each gist followed by a slot for knowledge filling. Guided by these steering gists, SEEK iteratively retrieves and refines knowledge, and fills the corresponding slots to complete the sketch. The completed sketch is then used as contextual input for final answer generation. Experimental results show that SEEK achieves better performance than baseline models across multiple tasks. Further analyses demonstrate that SEEK can generate more diverse sub-queries, reduce redundant retrieval, and achieve a better balance between external knowledge utilization and internal knowledge conflict mitigation. All codes are available at https://github.com/OpenBMB/PAGER.

cs.CL↗

arXiv2026

Revealing the Attention Floating Mechanism in Masked Diffusion Models

Masked diffusion models (MDMs), which leverage bidirectional attention and a denoising process, are narrowing the performance gap with autoregressive models (ARMs). However, their internal attention mechanisms remain under-explored. This paper investigates the attention behaviors in MDMs, revealing the phenomenon of Attention Floating. Unlike ARMs, where attention converges to a fixed sink, MDMs exhibit dynamic, dispersed attention anchors that shift across denoising steps and layers. Further analysis reveals its Shallow Structure-Aware, Deep Content-Focused attention mechanism: shallow layers utilize floating tokens to build a global structural framework, while deeper layers allocate more capability toward capturing semantic content. Empirically, this distinctive attention pattern provides a mechanistic explanation for the strong in-context learning capabilities of MDMs, allowing them to double the performance compared to ARMs in knowledge-intensive tasks. All codes and datasets are available at https://github.com/NEUIR/Attention-Floating.

cs.LG↗

arXiv2025

MSC-180: A Benchmark for Automated Formal Theorem Proving from Mathematical Subject Classification

Automated Theorem Proving (ATP) represents a core research direction in artificial intelligence for achieving formal reasoning and verification, playing a significant role in advancing machine intelligence. However, current large language model (LLM)-based theorem provers suffer from limitations such as restricted domain coverage and weak generalization in mathematical reasoning. To address these issues, we propose MSC-180, a benchmark for evaluation based on the MSC2020 mathematical subject classification. It comprises 180 formal verification problems, 3 advanced problems from each of 60 mathematical branches, spanning from undergraduate to graduate levels. Each problem has undergone multiple rounds of verification and refinement by domain experts to ensure formal accuracy. Evaluations of state-of-the-art LLM-based theorem provers under the pass@32 setting reveal that the best model achieves only an 18.89% overall pass rate, with prominent issues including significant domain bias (maximum domain coverage 41.7%) and a difficulty gap (significantly lower pass rates on graduate-level problems). To further quantify performance variability across mathematical domains, we introduce the coefficient of variation (CV) as an evaluation metric. The observed CV values are 4-6 times higher than the statistical high-variability threshold, indicating that the models still rely on pattern matching from training corpora rather than possessing transferable reasoning mechanisms and systematic generalization capabilities. MSC-180, together with its multi-dimensional evaluation framework, provides a discriminative and systematic benchmark for driving the development of next-generation AI systems with genuine mathematical reasoning abilities.

cs.AI↗

arXiv2025

DGAI: Decoupled On-Disk Graph-Based ANN Index for Efficient Updates and Queries

On-disk graph-based indexes are favored for billion-scale Approximate Nearest Neighbor Search (ANNS) due to their high performance and cost-efficiency. However, existing systems typically rely on a coupled storage architecture that co-locates vectors and graph topology, which introduces substantial redundant I/O during index updates, thereby degrading usability in dynamic workloads. In this paper, we propose a decoupled storage architecture that physically separates heavy vectors from the lightweight graph topology. This design substantially improves update performance by reducing redundant I/O during updates. However, it introduces I/O amplification during ANNS, leading to degraded query efficiency.To improve query performance within the update-friendly architecture, we propose two techniques co-designed with the decoupled storage. We develop a similarity-aware dynamic layout that optimizes data placement online so that redundantly fetched data can be reused in subsequent search steps, effectively turning read amplification into useful prefetching. In addition, we propose a two-stage query mechanism enhanced by hierarchical PQ, which uses hierarchical PQ to rapidly and accurately identify promising candidates and performs exact refinement on raw vectors for only a small number of candidates. This design significantly reduces both the I/O and computational cost of the refinement stage. Overall, DGAI achieves resource-efficient updates and low-latency queries simultaneously. Experimental results demonstrate that \oursys improves update speed by 8.17x for insertions and 8.16x for deletions, while reducing peak query latency under mixed workloads by 67\% compared to state-of-the-art baselines.

cs.DB↗

arXiv2025

Mitigating Judgment Preference Bias in Large Language Models through Group-Based Polling

Large Language Models (LLMs) as automatic evaluators, commonly referred to as LLM-as-a-Judge, have also attracted growing attention. This approach plays a vital role in aligning LLMs with human judgments, providing accurate and reliable assessments. However, LLM-based judgment models often exhibit judgment preference bias during the evaluation phase, tending to favor responses generated by themselves, undermining the reliability of their judgments. This paper introduces the Group-Based Polling Optimization (Genii), an unsupervised multi-agent collaborative optimization framework that mitigates the inherent judgment preference bias of judgment models. Specifically, Genii integrates various LLM-based judgment models into a multi-agent system and simulates the interactive client-server polling mechanism to optimize each client agent unsupervisedly. Our experiments demonstrate that Genii outperforms supervised models trained on annotated judgment data, while requiring no human-labeled annotations. Genii consistently improves performance across different client agents during the polling, even when weaker models act as server agents. Further analysis reveals that Genii effectively mitigates judgment preference bias of LLM-based judgment models, demonstrating its effectiveness. All codes are available at https://github.com/NEUIR/Genii.

cs.CL↗

arXiv2025

GeoLayer: Towards Low-Latency and Cost-Efficient Geo-Distributed Graph Stores with Layered Graph

The inherent connectivity and dependency of graph-structured data, combined with its unique topology-driven access patterns, pose fundamental challenges to conventional data replication and request routing strategies in geo-distributed cloud storage systems. In this paper, we propose GeoLayer, a geo-distributed graph storage framework that jointly optimizes graph replica placement and pattern request routing. We first construct a latency-aware layered graph architecture that decomposes the graph topology into multiple layers, aiming to reduce the decision space and computational complexity of the optimization problem, while mitigating the impact of network heterogeneity in geo-distributed environments. Building on the layered graph, we introduce an overlap-centric replica placement scheme to accommodate the diversity of graph pattern accesses, along with a directed heat diffusion model that captures heat conduction and superposition effects to guide data allocation. For request routing, we develop a stepwise layered routing strategy that performs progressive expansion over the layered graph to efficiently retrieve the required data. Experimental results show that, compared to state-of-the-art replica placement and routing schemes, GeoLayer achieves a 1.34x - 3.67x improvement in response times for online graph pattern requests and a 1.28x - 3.56x speedup in offline graph analysis performance.

cs.DB↗

arXiv2025

RIROS: A Parallel RTL Fault SImulation FRamework with TwO-Dimensional Parallelism and Unified Schedule

With the rapid development of safety-critical applications such as autonomous driving and embodied intelligence, the functional safety of the corresponding electronic chips becomes more critical. Ensuring chip functional safety requires performing a large number of time-consuming RTL fault simulations during the design phase, significantly increasing the verification cycle. To meet time-to-market demands while ensuring thorough chip verification, parallel acceleration of RTL fault simulation is necessary. Due to the dynamic nature of fault propagation paths and varying fault propagation capabilities, task loads in RTL fault simulation are highly imbalanced, making traditional singledimension parallel methods, such as structural-level parallelism, ineffective. Through an analysis of fault propagation paths and task loads, we identify two types of tasks in RTL fault simulation: tasks that are few in number but high in load, and tasks that are numerous but low in load. Based on this insight, we propose a two-dimensional parallel approach that combines structurallevel and fault-level parallelism to minimize bubbles in RTL fault simulation. Structural-level parallelism combining with workstealing mechanism is used to handle the numerous low-load tasks, while fault-level parallelism is applied to split the high-load tasks. Besides, we deviate from the traditional serial execution model of computation and global synchronization in RTL simulation by proposing a unified computation/global synchronization scheduling approach, which further eliminates bubbles. Finally, we implemented a parallel RTL fault simulation framework, RIROS. Experimental results show a performance improvement of 7.0 times and 11.0 times compared to the state-of-the-art RTL fault simulation and a commercial tool.

cs.AR↗

arXiv2025

GoVector: An I/O-Efficient Caching Strategy for High-Dimensional Vector Nearest Neighbor Search

Graph-based high-dimensional vector indices have become a mainstream solution for large-scale approximate nearest neighbor search (ANNS). However, their substantial memory footprint often requires storage on secondary devices, where frequent on-demand loading of graph and vector data leads to I/O becoming the dominant bottleneck, accounting for over 90\% of query latency. Existing static caching strategies mitigate this issue only in the initial navigation phase by preloading entry points and multi-hop neighbors, but they fail in the second phase where query-dependent nodes must be dynamically accessed to achieve high recall. We propose GoVector, an I/O-efficient caching strategy tailored for disk-based graph indices. GoVector combines (1) a static cache that stores entry points and frequently accessed neighbors, and (2) a dynamic cache that adaptively captures nodes with high spatial locality during the second search phase. To further align storage layout with similarity-driven search patterns, GoVector reorders nodes on disk so that similar vectors are colocated on the same or adjacent pages, thereby improving locality and reducing I/O overhead. Extensive experiments on multiple public datasets show that GoVector achieves substantial performance improvements. At 90% recall, it reduces I/O operations by 46% on average, increases query throughput by 1.73x, and lowers query latency by 42% compared to state-of-the-art disk-based graph indexing systems.

cs.DB↗

arXiv2025

Chunks as Arms: Multi-Armed Bandit-Guided Sampling for Long-Context LLM Preference Optimization

Long-context modeling is critical for a wide range of real-world tasks, including long-context question answering, summarization, and complex reasoning tasks. Recent studies have explored fine-tuning Large Language Models (LLMs) with synthetic data to enhance their long-context capabilities. However, the effectiveness of such approaches is often limited by the low diversity and factual inconsistencies in the generated data. To address these challenges, we propose LongMab, a novel framework that leverages a Multi-Armed Bandit (MAB) rollout strategy to identify the most informative chunks from the given long context for sampling high-quality and diverse responses and constructing preference data pairs for Direct Preference Optimization (DPO) training. Specifically, we treat context chunks as arms of MAB, select chunks based on their expected reward scores to input into LLMs to generate responses, and iteratively update these scores based on reward feedback. Both exploration and exploitation during the rollout process enable the LLM to focus on the most relevant context segments, thereby generating and collecting high-quality and diverse responses. Experimental results on both Llama and Qwen show the effectiveness of LongMab by achieving more than a 4% improvement on long-context reasoning benchmarks. All data and code will be released on https://github.com/NEUIR/LongMab-PO.

cs.CL↗

arXiv2025

Legal$\Delta$: Enhancing Legal Reasoning in LLMs via Reinforcement Learning with Chain-of-Thought Guided Information Gain

Legal Artificial Intelligence (LegalAI) has achieved notable advances in automating judicial decision-making with the support of Large Language Models (LLMs). However, existing legal LLMs still struggle to generate reliable and interpretable reasoning processes. They often default to fast-thinking behavior by producing direct answers without explicit multi-step reasoning, limiting their effectiveness in complex legal scenarios that demand rigorous justification. To address this challenge, we propose Legal$\Delta$, a reinforcement learning framework designed to enhance legal reasoning through chain-of-thought guided information gain. During training, Legal$\Delta$ employs a dual-mode input setup-comprising direct answer and reasoning-augmented modes-and maximizes the information gain between them. This encourages the model to acquire meaningful reasoning patterns rather than generating superficial or redundant explanations. Legal$\Delta$ follows a two-stage approach: (1) distilling latent reasoning capabilities from a powerful Large Reasoning Model (LRM), DeepSeek-R1, and (2) refining reasoning quality via differential comparisons, combined with a multidimensional reward mechanism that assesses both structural coherence and legal-domain specificity. Experimental results on multiple legal reasoning tasks demonstrate that Legal$\Delta$ outperforms strong baselines in both accuracy and interpretability. It consistently produces more robust and trustworthy legal judgments without relying on labeled preference data. All code and data will be released at https://github.com/NEUIR/LegalDelta.

cs.CL↗

arXiv2025

Advancing Knowledge Tracing by Exploring Follow-up Performance Trends

Intelligent Tutoring Systems (ITS), such as Massive Open Online Courses, offer new opportunities for human learning. At the core of such systems, knowledge tracing (KT) predicts students' future performance by analyzing their historical learning activities, enabling an accurate evaluation of students' knowledge states over time. We show that existing KT methods often encounter correlation conflicts when analyzing the relationships between historical learning sequences and future performance. To address such conflicts, we propose to extract so-called Follow-up Performance Trends (FPTs) from historical ITS data and to incorporate them into KT. We propose a method called Forward-Looking Knowledge Tracing (FINER) that combines historical learning sequences with FPTs to enhance student performance prediction accuracy. FINER constructs learning patterns that facilitate the retrieval of FPTs from historical ITS data in linear time; FINER includes a novel similarity-aware attention mechanism that aggregates FPTs based on both frequency and contextual similarity; and FINER offers means of combining FPTs and historical learning sequences to enable more accurate prediction of student future performance. Experiments on six real-world datasets show that FINER can outperform ten state-of-the-art KT methods, increasing accuracy by 8.74% to 84.85%.

cs.CY↗

arXiv2025

Automated Formalization via Conceptual Retrieval-Augmented LLMs

Interactive theorem provers (ITPs) require manual formalization, which is labor-intensive and demands expert knowledge. While automated formalization offers a potential solution, it faces two major challenges: model hallucination (e.g., undefined predicates, symbol misuse, and version incompatibility) and the semantic gap caused by ambiguous or missing premises in natural language descriptions. To address these issues, we propose CRAMF, a Concept-driven Retrieval-Augmented Mathematical Formalization framework. CRAMF enhances LLM-based autoformalization by retrieving formal definitions of core mathematical concepts, providing contextual grounding during code generation. However, applying retrieval-augmented generation (RAG) in this setting is non-trivial due to the lack of structured knowledge bases, the polymorphic nature of mathematical concepts, and the high precision required in formal retrieval. We introduce a framework for automatically constructing a concept-definition knowledge base from Mathlib4, the standard mathematical library for the Lean 4 theorem prover, indexing over 26,000 formal definitions and 1,000+ core mathematical concepts. To address conceptual polymorphism, we propose contextual query augmentation with domain- and application-level signals. In addition, we design a dual-channel hybrid retrieval strategy with reranking to ensure accurate and relevant definition retrieval. Experiments on miniF2F, ProofNet, and our newly proposed AdvancedMath benchmark show that CRAMF can be seamlessly integrated into LLM-based autoformalizers, yielding consistent improvements in translation accuracy, achieving up to 62.1% and an average of 29.9% relative improvement.

cs.AI↗