arXiv subjects

Xuanhe Zhou

Publications and source records attributed to Xuanhe Zhou.

At least 19 recordsLinked to original sources

arXiv2026

DeliverBench: Benchmarking AI Agents on Delivering Realistic Multi-Stage Professional Projects

LLM agents are judged by what they deliver, and in professional work what gets delivered is a project, not a task. A project pays off only if the whole package holds, and one weak part can limit the value of the rest. Yet existing benchmarks mostly test agents on one task at a time, leaving a gap between the capability we measure and the outcome that makes agents useful. To address this gap, we introduce DeliverBench, which tests whether agents can carry a project from brief to final delivery. Its 11 projects, spanning financial due diligence, legal contract drafting, and drug safety reporting, are reconstructed with 13 domain experts from real materials and chain 150 subtasks through 2-15 rounds of new materials and client feedback. Because no reference outputs are injected, agents inherit their own errors from one task to the next. Expert rubrics then score every checkpoint as well as the final package. Across seven model-harness systems, even the best system scores only 65.0 out of 100 on final delivery and passes 50.0% of subtasks at a 90-point threshold. The failures are often failures of carrying work forward: in one audit project, all seven systems addressed the review findings, but only one preserved traceability. Together, these results suggest that task-level capability does not simply compose into delivery, which also depends on keeping the work coherent as it evolves.

cs.AI↗

arXiv2026

SelfImprove-Bench: Evaluating Generalization in Self-Improving Agents

Recursively self-improving (RSI) systems are increasingly viewed as a promising means of accelerating progress toward artificial general intelligence. They aim to autonomously improve their capabilities by refining their working pipelines and recursively improving the strategies that guide subsequent refinements, with gains generalizing to unseen scenarios.However, existing evaluations lack reliable metrics to distinguish capability gains from scenario fitting, sustainable and extensible protocols for unseen tasks and difficulties, and fine-grained attribution of improvement to evolution traces. To this end, we propose SelfImprove-Bench,an RSI evaluation framework that organizes tasks into three primary capabilities (i.e., Exploring, Planning, Reasoning) as scenarios for guiding model evolution. We instantiated the tasks on games for controllability and reproducibility, and pairs them with scalable generation and orchestration driven by task templates and difficulty coefficients. Beyond task-level scores, SelfImprove-Bench organizes evaluation into generalization ladder levels G0 to G4 that measure how far gains transfer from training conditions. Experiments reveal that the evolutionary gains of existing RSI methods are inconsistent across generalization levels.

cs.AI↗

arXiv2026

MemT-1.0: Towards Memory-Native Evolution

Memory-native evolution requires making memory an intrinsic capability of foundation models, enabling them to continuously accumulate and utilize information. To this end, we introduce MemT-1.0, a new architecture of memory foundation models that internalize memory as part of model computation. Building on Metis, MemT-1.0 employs Gated DeltaNet-2 with a stable token-level memory update mechanism within each turn. We further introduce Mixture-of-Storage to scale native memory capacity. Following a deliberate backbone preparation, we develop a two-stage training pipeline consisting of continued pre-training and post-training, supported by 34B tokens of training data and efficient training and inference infrastructure. We release a model family comprising MemT-1.0-Nano and MemT-1.0-Flash, and conduct a comprehensive evaluation of memory and general capabilities. The results show that they outperform the parametric memory baselines on average and remain competitive with retrieval-augmented methods, while largely preserving general capabilities. At a history length of 128K tokens, MemT-1.0-Nano achieves approximately $1.86\times$ end-to-end inference speedup and a $66\times$ reduction in persistent storage relative to full context KV cache. By internalizing retrieved procedural experience, MemT-1.0 improves task success on agentic tasks, providing a practical step toward memory-native evolution.

cs.CL↗

arXiv2026

MemTrace: State-Consistent Memory for Long-Horizon Coding Agents

As coding agents take on long-horizon software evolution tasks spanning multiple files and stages, longer execution trajectories introduce two coupled challenges: (1) accumulated histories strain context budgets, and (2) repository changes can invalidate earlier execution evidence. Existing approaches address these challenges through techniques like larger context windows, compression, retrieval, or repository representations, but often fail to reconstruct a consistent task state after a context refresh or verify whether recalled evidence remains valid. Thus, we introduce MemTrace, a provenance-aware memory system that preserves execution history and aligns its reuse with the evolving task (e.g., iterative cross-file repair) and repository state. MemTrace stores history as immutable Memory Traces anchored to key information (e.g., files, symbols, tests), and organizes their execution order and dependencies in a Memory Trace Graph. When context is constrained, working memory retains only compact Memory Anchors, from which the agent can reconstruct the latest execution state and locate evidence relevant to its next action. Before restoring historical evidence, MemTrace checks its validity against the current repository state and retrieves only what the next action requires. Across three complementary long-horizon coding benchmarks, MemTrace consistently outperforms all fully evaluated baselines under the same backbone and harness, improving DeepSWE pass@1 by 21.2 points, SWE-EVO Resolved Rate by 4.4 points, and SWE-Milestone Score by 17.8 points under Codex CLI.

cs.AI↗

arXiv2026

Disk-Resident Graph ANN Search: An Experimental Evaluation

As data volumes grow while memory capacity remains limited, disk-resident graph-based approximate nearest neighbor (ANN) methods have become a practical alternative to memory-resident designs, shifting the bottleneck from computation to disk I/O. However, since their technical designs diverge widely across storage, layout, and execution paradigms, a systematic understanding of their fundamental performance trade-offs remains elusive. This paper presents a comprehensive experimental study of disk-resident graph-based ANN methods. First, we decompose such systems into five key technical components, i.e., storage strategy, disk layout, cache management, query execution, and update mechanism, and build a unified taxonomy of existing designs across these components. Second, we conduct fine-grained evaluations of representative strategies for each technical component to analyze the trade-offs in throughput, recall, and resource utilization. Third, we perform comprehensive end-to-end experiments and parameter-sensitivity analyses to evaluate overall system performance under diverse configurations. Fourth, our study reveals several non-obvious findings: (1) vector dimensionality fundamentally reshapes component effectiveness, necessitating dimension-aware design; (2) existing layout strategies exhibit surprisingly low I/O utilization (less than or equal to 15%); (3) page size critically affects feasibility and efficiency, with smaller pages preferred when layouts are carefully optimized; and (4) update strategies present clear workload-dependent trade-offs between in-place and out-of-place designs. Based on these findings, we derive practical guidelines for system design and configuration, and outline promising directions for future research.

cs.DB↗

arXiv2026

CRAFT: An Agentic Spreadsheet Form Filling System with Template Awareness

Spreadsheet form filling requires agents to consolidate external evidence, ground values to precise cells, and preserve irregular template structure. Errors in early edits can overwrite labels or misalign fields, undermining later decisions. We propose CRAFT, a template-aware agent framework that connects reflective validation to constrained local repair. Instead of treating reflection as a free-form request to regenerate the workbook, CRAFT grounds detected errors to spreadsheet regions, restores corrupted template state when necessary, and re-grounds plausible writable slots before subsequent edits. A Rectangle-Aware Slot Grounder (RASG) proposes writable cells, while label-slot hints and protected regions constrain subsequent edits. We introduce FormFillBench, with 327 forms across Instruction-Only and Multi-File tracks. Compared with the strongest baselines, CRAFT improves pair accuracy by 8.51 and 23.38 percentage points on these tracks, respectively. Component-removal experiments support structural adjudication and slot re-grounding within the pipeline, and the framework retains its relative advantage among the methods evaluated with a second backbone. The code and benchmark FormFillBench are available at https://github.com/Glllllly/CRAFT.

cs.AI↗

arXiv2026

Breaking the Environment Wall: A Unified Framework for Preparing and Evolving Agent-Native Environments

Many real-world tasks (e.g., office workflows, scientific experimentation) require LLM agents to interact repeatedly with their environments for context-dependent operations. However, such environments are often not agent-ready. First, information is often scattered and fragmented across the environment. Second, relevant evidence in the environment is often mixed with misleading information and conflicting versions. Third, environments evolve over time, introducing new noise and more challenging tasks. These challenges can substantially degrade performance for state-of-the-art AI agents (e.g., from 83.9% to 57.6%). To address these challenges, we propose Env-Rethink (a system with 27B post-trained model) that supports three main capabilities: (1) It adaptively builds Collection Maps (for organizing related files) and Event Logs (for contextualizing cross-data relationships) to supplement necessary context; (2) It further leverages the post-trained model (through offline trajectory learning) to identify underlying noise issues in the environment; (3) It ultimately evolves environments through virtual event histories that alter environmental states and evidence relationships, producing more tricky ones for further agent improvement. Experiments show that Env-Rethink can effectively improve downstream task performance (with a 15.1 percentage-point increase in mean rubric pass rate across nine models on 30 tasks).

cs.AI↗

arXiv2026

The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement

Recursive self-improvement (RSI) enables AI systems to turn experience and feedback into persistent changes that improve both their capabilities and the process of future improvement. We first use the Headroom-Closed Index (HCI) to reveal the problems of existing LLMs, then introduce the RSI concept and its development roadmap: from improvement-execution autonomy, improvement-strategy autonomy, experience-acquisition autonomy, and environment-adaptation autonomy, to recursive meta-improvement. Next we examine RSI across scenarios (e.g., scientific discovery, embodied intelligence, software engineering), highlighting their distinct requirements and development speeds. Drawing on diverse industry practices and preliminary empirical evidence, we connect RSI research with practical systems and identify key challenges to achieving genuine RSI.

cs.LG↗

arXiv2026

Data Agents: Agentic Data Systems

Traditional data systems face profound limitations in the AI era, relying on human-crafted pipelines, lacking semantic understanding of heterogeneous data, and operating through rigid, reactive processing. To address these challenges, we propose a new paradigm called the Data Agent, designed to manage, process, and analyze data with minimal human intervention. Data agents autonomously execute a wide range of data-related tasks, transforming traditional data systems by shifting from manual design to autonomous orchestration, from literal manipulation to semantic interpretation, and from reactive to proactive processing. Our Data Agent system includes six components: semantic data organization, semantic operators, agentic pipeline orchestration and optimization, feedback-driven refinement, memory management, and proactive adaptation. Building on this foundation, we also develop two specialized agents: the data analytics agent and the data science agent. Experiments on real benchmarks demonstrate significant performance gains of our data agent over state-of-the-art methods. We identify open challenges to guide future research in building fully autonomous data systems.

cs.DB↗

arXiv2026

Dial: A Knowledge-Grounded Dialect-Specific NL2SQL System

Enterprises commonly deploy heterogeneous database systems, each of which owns a distinct SQL dialect with different syntax rules, built-in functions, and execution constraints. However, most existing NL2SQL methods assume a single canonical dialect (e.g., SQLite) and struggle to produce queries that are both semantically correct and executable on target engines. Prompt-based approaches tightly couple intent reasoning with dialect syntax, rule-based translators often degrade native operators into generic constructs, and multi-dialect fine-tuning suffers from cross-dialect interference. In this paper, we present Dial, a knowledge-grounded framework for dialect-specific NL2SQL. Dial introduces: (1) a Dialect-Aware Logical Query Planning module that converts natural language into a dialect-aware logical query plan via operator-level intent decomposition and divergence-aware specification; (2) HINT-KB, a hierarchical intent-aware knowledge base that organizes dialect knowledge into i a Canonical Syntax Reference, ii a declarative function repository, and iii a procedural constraint repository; and (3) an execution-driven debugging and semantic verification loop that separates syntactic recovery from logic auditing to prevent semantic drift. We construct DS-NL2SQL, a benchmark covering six major database systems with 2,218 dialect-specific test cases. Experimental results show that Dial consistently improves translation accuracy by 10.25% and dialect feature coverage by 15.77% over state-of-the-art baselines.

cs.DB↗

arXiv2026

GRADE: Benchmarking Discipline-Informed Reasoning in Image Editing

Unified multimodal models target joint understanding, reasoning, and generation, but current image editing benchmarks are largely confined to natural images and shallow commonsense reasoning, offering limited assessment of this capability under structured, domain-specific constraints. In this work, we introduce GRADE, the first benchmark to assess discipline-informed knowledge and reasoning in image editing. GRADE comprises 520 carefully curated samples across 10 academic domains, spanning from natural science to social science. To support rigorous evaluation, we propose a multi-dimensional evaluation protocol that jointly assesses Discipline Reasoning, Visual Consistency, and Logical Readability. Extensive experiments on 20 state-of-the-art open-source and closed-source models reveal substantial limitations in current models under implicit, knowledge-intensive editing settings, leading to large performance gaps. Beyond quantitative scores, we conduct rigorous analyses and ablations to expose model shortcomings and identify the constraints within disciplinary editing. Together, GRADE pinpoints key directions for the future development of unified multimodal models, advancing the research on discipline-informed image editing and reasoning. Our benchmark and evaluation code are publicly released.

cs.CV↗

arXiv2026

DisciplineGen-1M: A Large-Scale Dataset for Multidisciplinary Visual Generation and Editing

Recent image generation and editing models can produce visually appealing natural images, yet they remain unreliable when the target image is a knowledge-intensive diagram whose correctness depends on disciplinary concepts, symbolic structure, and precise spatial relations. We introduce DisciplineGen-1M, a million-scale multidisciplinary dataset that supports text-to-image generation and image editing. It contains 1.2M samples spanning mathematics, physics, chemistry, biology, geography, computer science, economics, history, music, and sports. To construct the dataset, we design a scalable framework that combines structured rendering, OCR-based editing, specialized programmatic synthesis, and large-scale text-to-image filtering. These pipelines produce captions, editing instructions, structured annotations, and paired images with controllable semantic differences. Building on DisciplineGen-1M, we further introduce a discipline-informed reasoning-generation model for both text-to-image generation and image editing. Experiments on discipline-related benchmarks, GenExam and GRADE, show substantial improvements over open-source baselines, while evaluations on general reasoning-informed benchmarks, WISE and RISE, further indicate broader transfer. The results suggest that large-scale structured academic visual data is a key ingredient for moving image generation from aesthetic plausibility toward verifiable knowledge-grounded visual creation. We will publicly release our dataset, model, and source code of the data curation pipeline to ensure reproducibility and benefit future research.

cs.CV↗

arXiv2026

Argus: A General-Purpose Agentic Reasoning Runtime for Long-Horizon Tasks

Long-horizon reasoning requires an agentic runtime that can persist when evidence supports its current approach and pivot when measurements reveal failure, hidden constraints, or a misspecified objective. We present Argus, a persistent, self-evolving runtime in which Manager, Planner, Engineer, and Reviewer execute bounded missions over durable project state. Argus separates stable user intent from operational objectives, constraints, and verification criteria, and admits memories, skills, procedures, verifiers, routing decisions, and rejected routes only after role-owned review and, when available, task-native verification. Model weights remain fixed; self-evolution occurs through persistent runtime state and control policy, with autonomous execution between operator-owned escalation points. Across seven GPT-5.5 benchmark arenas, Argus achieves about 78% on SWE-Bench Pro versus 59% for Direct Copilot while using 1.41 times the aggregate tokens. After verification-gated self-evolution, mature SWE-Bench waves use 21% fewer solve-input tokens and 15% less active workflow time per task than startup waves, while recording 34 verifier recoveries and 22 strict review-loop rescues. Argus also reaches 76.8% on AARRI-Bench and a 28.0-point gap on mathematical data synthesis, with competitive GPU-kernel and language-model-training results. Beyond benchmarks, an optimized RWKV6 kernel was merged upstream; a multi-day mathematics campaign retained falsified routes and proof-backed frontier updates; and six paper pipelines completed 254 missions with 16 stage rollbacks. These results show that a fixed-weight, self-evolving harness can revise, recover, and accumulate verified approaches while producing structured trajectories for future supervised and reinforcement learning.

cs.AI↗

arXiv2026

TEngineDB-V: An OLAP-Native Vector Search System for Large-$k$ Workloads at Tencent

Vector search systems are essential infrastructure for modern data-driven applications. Large-$k$ analytical vector search, which retrieves $k=10^3$--$10^5$ results for analytics (e.g., aggregation, filtering, joins), is increasingly important for emerging workloads, including LLM data management and advertising analysis at Tencent. Existing systems remain inadequate: specialized vector databases often cap $k$ (e.g., $k \leq 10^4$) to satisfy tail-latency constraints and offer limited analytical support, while OLAP systems typically embed per-segment vector indexes as black boxes, causing severe read/compute amplification and preventing native query optimization. This paper presents TEngineDB-V, an OLAP-native vector search system for large-$k$ workloads. TEngineDB-V makes vector search a first-class analytical primitive in Tencent's OLAP engine through a global segment-decoupled index materialized as relational tables, eliminating scatter-gather execution, reducing amplification, and enabling native storage optimizations. It decomposes IVFPQ-based search into relational operators, integrates OLAP optimizations, and introduces DPPQ, which combines direction-aware quantization with hierarchical residual refinement to improve recall while preserving relational efficiency. TEngineDB-V further incorporates index-aware query rewriting and a distributed-aware cost model for efficient distributed execution. Experiments show that TEngineDB-V achieves up to a $145\times$ speedup over competitive systems such as StarRocks, and up to a $52\times$ improvement in 10-billion-scale production deployments.

cs.DB↗

arXiv2026

MinerU-Popo: Universal Post-Processing Model for Structured Document Parsing

VLM-based OCR models have become the de facto choice for document parsing, as they can accurately extract page-level elements (e.g., paragraphs within individual pages) together with their bounding boxes and textual content. However, downstream applications such as RAG require coherent document-level information, whereas these models often break cross-page continuity and fail to recover disrupted structures, such as paragraphs and tables truncated by page boundaries. Such relationships are not confined to a single page; instead, they require joint analysis of titles, paragraphs, tables, and images spanning multiple pages. A natural solution is therefore to reuse existing OCR outputs and reconstruct document-level logical structures through post-processing. To this end, we propose MinerU-Popo, a lightweight and universal framework for POst-Processing OCR outputs, which converts page-level results from diverse parsers into coherent document-level structures. MinerU-Popo decomposes the problem into four focused subtasks: text truncation recovery, table truncation recovery, title hierarchy reconstruction, and image-text association. To address these effectively, we build a task-oriented data engine with task-specific input filtering, and use the generated data (30K) to fine-tune a lightweight post-processing model (Qwen3-VL-4B). To support long documents, we introduce dynamic chunking with overlap-based synchronization, which aligns chunk-level outputs from the fine-tuned model and preserves global consistency. Finally, we assemble the aligned outputs into a tree-structured document representation, further enriched with node chunking and summaries for downstream retrieval and analysis. Empirical results show MinerU-Popo improves title-hierarchy TEDS by at least 20% across all five tested OCR models, improves RAG accuracy and reduces per-query latency.

cs.CV↗

arXiv2026

HiEviDR-Bench: A Benchmark for Hierarchical Evidence Aggregation in Deep Research

Deep research requires models to retrieve, connect, and synthesize evidence from large-scale heterogeneous sources to answer complex queries and produce analytical reports. Existing benchmarks mainly evaluate final outcomes, such as answer correctness, report quality, or citation alignment, while providing limited visibility into whether evidence is correctly selected, linked, and aggregated into supported claims and conclusions. To address this gap, we introduce HiEviDR-Bench, a benchmark for evaluating Hierarchical Evidence Aggregation in Deep Research. HiEviDR-Bench covers open-domain and academic-domain settings under both text-only and multimodal conditions, and represents each instance with an explicit evidence graph that captures evidence selection, cross-source linking, and aggregation from evidence to intermediate claims and final conclusions. Based on this formulation, we develop a traceability-oriented evaluation framework with five dimensions: report quality, evidence traceability, citation accuracy, claim verification, and answer correctness, together with a progressive gating mechanism for fine-grained error localization. HiEviDR-Bench contains 2,000 human-validated questions with evidence graphs across multiple difficulty levels. Experiments on 16 representative multimodal large language models show that, although many systems achieve strong report quality, their performance drops markedly on citation accuracy, claim construction, and answer correctness. Further analysis shows that the main bottlenecks lie in evidence identification and intermediate claim construction, revealing that strong surface-level report quality does not necessarily imply grounded multi-stage reasoning on our benchmark.

cs.IR↗

arXiv2026

UltraX: Refining Pre-Training Data at Scale with Adaptive Programmatic Editing

As available training data approaches its physical limit, gains from Scaling Laws have begun to diminish. Consequently, improving Large Language Models (LLMs) now depends less on data expansion and more on higher-quality data utilization. However, in the context of large-scale corpora, existing refinement methodologies face significant limitations in quality, efficiency, and reliability: Rule-based approaches are constrained by fixed heuristics and struggle with instance-level variations; LLM-based approaches improve quality but fail to meet the efficiency and reliability requirements of large-scale data processing. To address these challenges, we propose UltraX, a function-calling refinement framework for large-scale pre-training data that completes the editing function space by introducing insertion in addition to deletion and modification, enabling fine-grained instance-level editing. Specifically, UltraX builds a reliable program-supervision generation pipeline. In this pipeline, dataset-adaptive prompt optimization first guides an expert LLM to produce high-quality end-to-end refined texts, and Line Alignment Mapping and Dynamic Context Replacement then convert original-refined text pairs into structured program supervision. Meanwhile, UltraX improves supervision quality and stabilizes the training distribution with low-confidence example filtering and ratio-controlled sampling by operation combination. During inference and execution, it normalizes and validates model outputs through sliding-window prediction, global operation aggregation, and systematic post-processing, improving the stability and reliability of large-scale execution. Experiments show that UltraX achieves the highest average performance across all corpora and also matches or surpasses baselines with fewer training tokens, demonstrating stronger data efficiency and refinement reliability.

cs.CL↗

arXiv2026

OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers

Optimizer selection for large-scale model training has become a system-level design decision constrained jointly by compute, memory, tuning budget, and task diversity, yet the landscape of over one hundred methods remains fragmented. We therefore present OmniOpt, a unified survey and benchmark cookbook of optimizers for the research community. OmniOpt rests on four coupled components. First, we treat every optimizer update as a structured transformation through a five-stage meta-pipeline, and show that most methods engage only one or two of these stages. Second, we use norm-constrained linear minimization oracles (LMOs) to unify different optimizers. Third, these two views ground a dual-dimension taxonomy, one dimension assigning each method to a mechanism family and the other recording the measurable training objectives it aims to improve. Fourth, and at the core of this paper, we instantiate the full taxonomy in a unified cross-domain benchmark spanning representative optimizers, model scales, and training regimes from language model pretraining to image classification, systematically analyzing each method family across multiple effect objectives and laying out their trade-offs. OmniOpt thus supplies the research community with an operational coordinate system for selecting optimizers under explicit mechanism and objective assumptions, and charts a direction for the future development of the optimizer community.

cs.LG↗