arXiv subjects

Zhi Jin

Publications and source records attributed to Zhi Jin.

At least 19 recordsLinked to original sources

arXiv2026

ASNER: Software Architecture Recovery with Adaptive Semantic Neighborhoods and Evidence-Grounded Refinement

Automated software architecture recovery provides architectural context for software engineering and repository-level LLM agents. Existing methods combine structural and semantic signals, but functional relatedness does not necessarily imply shared architectural responsibility. Fixed thresholds or Top-K neighborhoods also ignore repository scale and local similarity distributions, introducing errors that propagate through clustering. Unconstrained LLM refinement may further alter correct assignments without sufficient evidence. We propose ASNER (Adaptive Semantic Neighborhoods and Evidence-Grounded Refinement for Software Architecture Recovery), based on responsibility-aware, project-adaptive relation modeling and evidence-grounded boundary verification. ASNER derives structured file responsibilities with an LLM, constructs semantic neighborhoods that adapt to repository scale and local similarity distributions, and augments a static dependency graph with selected semantic relations and weak directory cues. Community detection recovers the component backbone. A Responsibility-Ownership-Aware (ROA) Agent then examines uncertain boundary files using project-level responsibilities and traceable code evidence, changing assignments only when supported. Experiments on 12 open-source projects spanning C, C++, Java, and Python show that ASNER achieves the best macro-average on all five metrics on the common benchmark, improving ARI and c2c@66 over GAER-GAT by 19.5% and 32.9%, respectively. A downstream evaluation shows that ASNER-guided LocAgent improves file-, module-, and function-level code localization, demonstrating the value of its architectural context for repository-level software engineering tasks.

cs.SE↗

arXiv2026

Parallel Thinking for Large Language Model with Path Diversity

Parallel thinking has emerged as a promising paradigm for enhancing the reasoning capabilities of Large Language Models (LLMs) by exploring multiple reasoning paths simultaneously. However, we identify that parallel thinking via Reinforcement Learning (RL) typically suffers from the mode collapse of reasoning paths, where parallel thinking trajectories degenerate into similar ones. This homogeneity undermines the fundamental motivation of parallel thinking, that is, maintaining multiple hypotheses concurrently to prevent premature loss into a suboptimal solution. In this paper, we propose Diverse Parallel Thinking (DPT), a simple yet effective RL approach for parallel thinking designed to encourage path diversity. DPT rewards the model to develop distinct reasoning strategies by penalizing the prefix similarity of parallel thinking paths, thereby enhancing a more comprehensive exploration of the reasoning space. We conduct various experiments and analyses across multiple reasoning benchmarks to demonstrate the effectiveness of DPT. Results show that DPT successfully outperforms previous parallel thinking methods, achieving state-of-the-art performance over baselines. We validate path diversity as a key element to improve parallel thinking. Our code is available at https://github.com/JiaruQian/DPT.

cs.AI↗

arXiv2026

Rethinking Generalization in Knowledge Graph Embedding: An Empirical Study and Sparse Peak Regularization

Knowledge graphs (KGs) provide structured representations of entities and relations, and underpin data management and Web applications such as search, recommendation, and question answering. Since Web-scale KGs such as Freebase and Wikidata are inherently incomplete, knowledge graph embedding (KGE) maps entities and relations into continuous vector spaces and is widely used to infer missing facts through link prediction. Despite extensive progress in KGE model design, the role of regularization has been less systematically examined, especially beyond tensor-decomposition models. The primary contribution of this paper is a comprehensive empirical study of regularization for KGE from the perspective of generalization. Across translation-based, tensor-decomposition-based, GNN-based, temporal, and multimodal KGE models, we show that overfitting is common across model families and that appropriate regularization can substantially improve both generalization and predictive performance. Motivated by these findings, we further propose Sparse Peak Regularization (SPR), a simple and model-agnostic regularizer that introduces rank-based selective sparsity into the regularization target. SPR concentrates the penalty on dominant high-energy embedding components, which contribute most to the embedding norm and overfitting risk, while leaving low-energy components unpenalized so that weak but useful signals are not unnecessarily suppressed. Experiments on eight benchmark datasets and diverse KGE models show that SPR achieves the best results in nearly all settings compared with existing regularizers such as N3, DURA, and ER. These results show that regularization deserves more systematic attention in KGE, and that selective regularization is an effective and broadly applicable strategy for improving the generalization of KGE models.

cs.LG↗

arXiv2026

Agentic Reverse Engineering: From I/O to Code with Discovery Agent

The automatic synthesis of a program from any form of specification is regarded as a holy grail of computer science. Fueled by LLMs, NL2Code has achieved tremendous success, yet the fundamentally more challenging task of synthesizing programs from input-output behavior, which we refer to as IO2Code, remains largely unsolved. Whereas NL2Code can exploit the semantic alignment between natural language and code acquired during pretraining, IO2Code requires recovering underlying principles from concrete computational behavior, navigating a vast and underspecified hypothesis space. To address this, we propose DIO-Agent, a discovery agent that performs agentic reverse engineering from input-output behavior to code. Our method frames IO2Code as an evolutionary search over discrete program space, in which an LLM serves as the mutation operator and concrete error signals from execution guide each mutation. To prevent the search from wandering into structurally complex yet incorrect dead ends, we introduce the Transformation Priority Premise as a mutation prior that biases the LLM toward the simplest hypothesis consistent with current evidence, progressively escalating from constants to conditionals to iteration only when simpler constructs are insufficient. To facilitate systematic study, we further construct an IO2CodeBench spanning multiple difficulty levels. Extensive experiments show that DIO-Agent consistently outperforms both traditional program-by-example method and SOTA evolution-agent baselines across all difficulty levels and various LLMs, while substantially surpassing test-time scaling strategies with equivalent sampling budgets.

cs.LG↗

arXiv2026

RAP-WAM: Learning World-Action Models through Predictive Rehearsal and Action Perturbations

Recent world action models draw on video generation priors to jointly predict future observations and robot actions. Adapting these priors to control requires determining how future predictions should guide policy learning. RAP-WAM combines predictive Rehearsal and Action Perturbations (RAP) with future-supervised queries and Coupled Action Projection for policy learning. Predictive rehearsal trains on model-generated inputs while retaining recorded targets, and accumulates recurring errors into a spatial prior. We perturb actions and measure changes in video predictions. Action-response-based spatiotemporal credit assignment combines these responses, prediction error, and the rehearsal prior to allocate visual supervision; spatially aggregating the responses determines supervision intensity across future action steps. No separate scoring network or deployment-time probe is required. The base learns from a video-pretrained backbone without intermediate pretraining on external embodied data. We evaluate the fixed base and its agent-refined, task-conditioned system. On 42 RoboDojo tasks, their average success rates are 12.85% and 15.62%, with Scores of 17.86 and 20.59. Across 15 real-robot tasks, the complete system achieves 89.00% task-macro-average success, exceeding the strongest of five baselines by 37.67 percentage points. Across 315 fixed-output simulation windows, 45.21% of response-top20 positions fall outside error-top20, revealing information beyond prediction error. Videos and further details are available on the project website: https://rapwam.github.io/.

cs.AI↗

arXiv2026

BAT3R: Robust Online 3D Reconstruction with Bayesian Adaptive State Updates

Feed-forward transformer models have driven remarkable progress in 3D vision,yet their quadratic complexity renders them impractical for long video sequences. Streaming 3D reconstruction addresses this bottleneck by processing frames sequen?tially with constant memory. However, existing recurrent architectures inevitably suffer from progressive degradation over long sequences, as they fail to account for the intrinsic reliability of observations and the accumulated confidence of the historical state, leading to severe error accumulation. To address these issues, we introduce BAT3R, a training-free Bayesian adaptation framework comprising two synergistic modules: State Innovation Gating (SIG) and Bayesian-guided Adaptive State Updating (BASU). SIG acts as a distributional regularizer that anchors state evolution to its geometric initialization, effectively arresting representational drift during long-term inference. Building on this, BASU reformulates state update as a recursive Bayesian inference process within a Kalman filtering framework. By jointly modeling the temporal reliability of observations via information-theoretic gain and spatial relevance via cross-attention maps, BASU achieves an asymmetric spatio-temporal state fusion: well-consolidated historical regions are protected from redundant updates, while genuinely novel scene content is aggressively incor?porated. Extensive experiments on standard benchmarks (7-Scenes, TUM, ScanNet, KITTI, etc.) demonstrate that BAT3R consistently outperforms state-of-the-art online 3D reconstruction methods, with the most significant gains observed on long sequences and complex scenes.

cs.CV↗

arXiv2026

CONTRA: Discovering and Qualifying Behavior-Changing Questions for Selective Clarification in LLM Code Generation

Coding agents can generate code that appears correct but implements behavior the user never intended. This mismatch can arise when an agent silently resolves underspecified requirements through its own assumptions. As subsequent development builds on these assumptions, correcting the resulting behavior can become increasingly costly. Early clarification can help prevent such mismatches, but unnecessary questions can interrupt developers and slow down development. Existing methods struggle to identify key clarification questions while avoiding unnecessary ones. Therefore, we propose CONTRA, a training-free method that combines broad question discovery with semantic and execution-based question qualification. CONTRA first generates candidate questions and filters out those unrelated to required behavior or already resolved by the requirement. For each remaining question, it generates programs conditioned on two plausible answers and checks for stable behavioral differences on shared inputs. It then uses the interaction history to select among qualified questions or stop asking. Experiments on ClarifyCodeBench show that CONTRA achieves the highest F1 with all four coding agents, exceeding the best baseline macro-average F1 by 13.88 percentage points. With the same LLM and evaluation protocol, CONTRA also achieves higher clarification recall and F1 than the coding harnesses Claude Code and OpenHands. To support practical use, we also implement CONTRA as a Claude Code plugin that integrates selective clarification into everyday development.

cs.SE↗

arXiv2026

EvoIR-Agent: Self-Evolving Image Restoration Agentic System via Experience-Driven Learning

Multimodal Large Language Model (MLLM)-driven image restoration agent demonstrates effectiveness in degradation coupling scenarios by flexibly selecting tools and determining removal orders. However, its zero-shot planning often fails without experience, necessitating severe trial-and-error overhead to achieve satisfactory outcomes. Currently, two paradigms are employed to address this issue, yet a dilemma persists: Training-based methods embed intrinsic experience into parameters, achieving high inference efficiency but lacking compatibility with new tools or degradations. In contrast, training-free methods utilize explicit experience storage for compatibility but still incur trial-and-error overhead due to naive experience. To resolve the dilemma, we propose EvoIR-Agent, which first systematically formulates the experience components of a training-free image restoration agent. Subsequently, a hierarchical experience pool is constructed, which enables coarse-to-fine guidance for diverse tools and removal orders. Furthermore, a self-evolving mechanism is introduced to update the pool from scratch using accumulated records, thereby greatly improving performance and efficiency. Extensive experiments reveal that EvoIR-Agent achieves a significant lead in the full reference metrics and yields a Pareto-optimal balance, which outperforms state-of-the-art methods in performance and is 61% more efficient.

cs.CV↗

arXiv2026

COMPASS: Predicting the Relationship of Multiple Patches for Vulnerabilities with LLMs

Modern software heavily relies on code reuse, so upstream vulnerability fixes do not automatically propagate to downstream codebases. Downstream maintainers must manually adopt patches to eliminate known risks. In practice, a single vulnerability often corresponds to multiple patches, which greatly complicates downstream patch adoption because different patch relationships imply different adoption strategies. To address this challenge, we first manually inspect large-scale multi-patch vulnerabilities (about 1K) in the real world and interview experienced developers, summarizing six typical types of patch relationships, i.e., Merge, Mirror, Better Solution, Fixing-of-Fixing, Collaboration, and Separation. Based on these observations, we propose COMPASS, an automated approach that predicts the relationships of multiple vulnerability patches with large language models. Given a CVE as input, COMPASS follows a four-phase pipeline that (i) identifies the patch group and pre-scans explicit relationships, (ii) performs individual patch analysis, (iii) infers relationship instances via a hierarchy-guided prompt, and (iv) validates completeness and consistency of the inferred results. As output, COMPASS reports the predicted relationships within the patch group and visualizes them as a relationship graph. We evaluate COMPASS on a benchmark of 300 multi-patch CVEs and compare it against mainstream learning-based and LLM baselines. Results show that our method achieves strong and consistent prediction effectiveness and outperforms SOTA by 85.04% on average. We publicly release an online querying website to support community reuse of patch relationships knowledge: https://patch-relation.com.

cs.SE↗

arXiv2026

CalibHyper: Chance-Corrected Relational Hypergraphs for Few-Shot Molecular Property Prediction

Molecular property prediction is central to drug development and materials discovery, but experiments are costly and labeled data are scarce. Context-aware methods use auxiliary assay labels to support few-shot prediction, and recent work supervises property relations with label agreement. However, label agreement is sensitive to class marginals and does not directly capture dependence between properties. We propose CalibHyper, a chance-corrected relational hypergraph method based on the joint label distribution. CalibHyper subtracts an independence baseline from the ordered four-state label distribution and shrinks the residual according to the number of joint observations. A swap-equivariant relation head estimates these residuals, which choose the auxiliary properties for each molecule and set the sign and weight of their hyperedge messages. On thirteen datasets from five benchmarks, in both 1-shot and 10-shot settings, CalibHyper and its ablation settings achieve ROC-AUC competitive with the strongest reported results.

cs.LG↗

arXiv2026

ClarifyCodeBench: Evaluating LLMs on Clarifying Ambiguous Requirements for Code Generation

Large Language Models have emerged as programming assistants. However, the efficacy of code generation is constrained by the quality of input requirements, which are frequently ambiguous, incomplete, or underspecified. While LLMs excel at one-shot code synthesis, their ability to proactively clarify intent remains underexplored, as a critical trait for robust software engineering. Existing benchmarks largely overlook this interactive bottleneck, assuming perfectly specified prompts that do not reflect the iterative nature of requirement elicitation. To bridge this gap, we introduce ClarifyCodeBench, a novel interactive benchmark for evaluating LLMs' capability in resolving requirement ambiguity. Constructed from real-world programming tasks, ClarifyCodeBench features high-quality manual annotations, including N unique ambiguity types, associated clarification questions, and corresponding ground-truth answers. Furthermore, we formalize two rigorous metrics to assess the interaction quality: Turn-discounted Key Question Rate, which penalizes inefficient questioning, and Optimal Round Adherence, which measures the precision of the elicitation process. We conduct a systematic evaluation of six state-of-the-art LLMs using ClarifyCodeBench. Our empirical results yield three critical insights: 1) Capability Decoupling: Strong code generation performance does not inherently translate to effective requirement clarification; 2) The Reasoning Paradox: While increased computational thinking enhances code correctness, it yields marginal gains in identifying ambiguities; 3) The Multi-ambiguity Ceiling: LLMs' clarification performance degrades sharply as the density of ambiguities increases, revealing a significant bottleneck in handling complex, real-world specifications. Our work underscores the necessity for future AI4SE research to transition from static synthesis to interactive elicitation.

cs.SE↗

arXiv2026

An Interactive Agent for Requirement-Driven Candidate Sourcing

Finding people from a natural-language description (``ML engineers transitioning to research roles in biotech'') is increasingly delegated to LLM agents and framed as information retrieval. We argue that it is fundamentally a requirements engineering task: such a request is an under-determined requirement with implicit constraints, many valid answers, and no acceptance criterion, so useful answers require eliciting, validating, and verifying the requirement before search can matter. We present \sys{}, to our knowledge the first interactive, requirements-driven candidate-sourcing agent (it elicits, validates, retrieves, and verifies a vague people-request into a justified slate through bounded elicitation, workflow templates, a two-stage commit protocol, and bidirectional termination guards) and \bench{}, a benchmark that runs the requirements lifecycle (criteria-anchored validation, multi-model evidence-grounded oracle construction, and cost-aware verification). Across $21$ systems and all $691$ requirements, \sys{} dominates breadth ($100%$ coverage at $2.5\times$ the yield) and is \emph{near-orthogonal} to the field, with $90%$ of the people it returns are surfaced by \emph{none} of $20$ strong LLM-plus-web baselines combined. Beyond breadth, an evidence-grounded judging of every system shows \sys{} \emph{recalls} the most relevant real people: $0.241$ of the union pool, $1.9\times$ the next system, with a bootstrap $95%$ interval disjoint from every baseline. \sys{} is thus the strongest \emph{sourcing} engine (the deepest real, reachable candidate pool), while precision-ranking LLMs serve as~complementary verifiers.

cs.SE↗

arXiv2026

PRAXIS: Graph-Grounded Tacit Knowledge for Domain Code Generation

LLM agents have achieved strong performance on general software engineering tasks, yet struggle with domain-specific code generation. We identify the root cause as the agent's lack of tacit knowledge, including domain-specific business rules, interface contracts, and operational conventions that developers internalize through practice but never document. This knowledge is deeply buried beneath the domain code, dispersed across code entities and their dependency relations, and invisible to the agent that lacks it. These properties make tacit knowledge inherently difficult to retrieve or learn. In this work, we propose PRAXIS, a framework that enables agents to systematically extract, represent, and reuse tacit knowledge for domain code generation. PRAXIS acquires tacit knowledge by simulating human development workflows within the target codebase, distills it into structured units organized on the code dependency graph, and proactively surfaces it to the agent at the point of code interaction. Extensive experiments demonstrate that PRAXIS outperforms state-of-the-art agents equipped with powerful agentic search capabilities, as well as experience-based and skill-based methods. The approach integrates seamlessly into various agent frameworks and LLMs with consistent performance improvements, and supports continual evolution with performance steadily scaling as practice accumulates.

cs.SE↗

arXiv2026

When Modalities Remember: Continual Learning for Multimodal Knowledge Graphs

Real-world multimodal knowledge graphs (MMKGs) are dynamic, with new entities, relations, and multimodal knowledge emerging over time. Existing continual knowledge graph reasoning (CKGR) methods focus on structural triples and cannot fully exploit multimodal signals from new entities. Existing multimodal knowledge graph reasoning (MMKGR) methods, however, usually assume static graphs and suffer catastrophic forgetting as graphs evolve. To address this gap, we present a systematic study of continual multimodal knowledge graph reasoning (CMMKGR). We construct several continual multimodal knowledge graph benchmarks from existing MMKG datasets and propose MRCKG, a new CMMKGR model. Specifically, MRCKG employs a multimodal-structural collaborative curriculum to schedule progressive learning based on the structural connectivity of new triples to the historical graph and their multimodal compatibility. It also introduces a cross-modal knowledge preservation mechanism to mitigate forgetting through entity representation stability, relational semantic consistency, and modality anchoring. In addition, a multimodal contrastive replay scheme with a two-stage optimization strategy reinforces learned knowledge via multimodal importance sampling and representation alignment. Experiments on multiple datasets show that MRCKG preserves previously learned multimodal knowledge while substantially improving the learning of new knowledge.

cs.CL↗

arXiv2026

Knowledge before Reasoning: EC-Reason-Bench, a Training-Free Diagnostic Benchmark for LLM Enzyme Classification

Enzyme function prediction is a hierarchical, knowledge-intensive form of protein function classification. Existing benchmarks expose an anomaly: general LLMs often get the coarse first level right, yet once asked for a complete EC number their accuracy at levels two through four drops to almost zero, while specialized models and tools stay usable. We propose EC-Reason-Bench, a training-free, diagnostic evaluation protocol built to answer two questions: why general LLMs score close to nothing on EC number prediction, and how much of that loss can be recovered without updating a single weight. We break enzyme classification ability into four orthogonal levers that can each be measured on their own: output structure, external knowledge, reasoning structure, and reasoning robustness. We test each lever with an inference-time method against a shared zero-shot baseline reproducing previously reported near-zero performance. Experiments with several strong reasoning LLMs yield four main findings. First, external knowledge is decisive and must precede reasoning: uniformly low closed-book performance rises sharply with open-book access, narrowing model gaps. Second, in closed-book settings, whether cascading and chain-of-thought help or hurt depends on a model's tendency to abstain. Third, once evidence is available the aggregate score of the best LLM setting is indistinguishable from simply voting the EC numbers of the nearest retrieved neighbors; that tie is an artifact of averaging, and it hides a large gain on adversarial evidence set against an equally large loss on multi-functional enzymes. Reasoning over evidence therefore acts as an arbiter of conflicting neighbors rather than as a source of knowledge, and no single-number leaderboard can see it. Fourth, accuracy obeys a law of homology availability.

cs.CL↗

arXiv2026

CORE: A Unified Cascaded Ordinal Relevance Estimation Framework for E-commerce Search

Ranking relevance is a fundamental task in e-commerce search, directly affecting ranking quality and consumer experience. Although inherently an ordinal classification problem, it is commonly formulated as conventional multi-class classification, which overlooks the natural order among relevance levels and assigns equal penalties to adjacent and distant misclassifications. This mismatch leads to suboptimal learning objectives for practical relevance evaluation. To address this issue, we propose a unified cascaded binary classification framework applicable to both large language model inference and online BERT-based inference, which reformulates relevance estimation as a sequential decision process and decomposes multi-class prediction into a series of ordered binary judgments from higher to lower relevance tiers. For large language models, we design a step-wise reasoning procedure with pruning strategies and tier-specific reward functions. For the online BERT model, we replace the conventional classification head with multiple level-wise binary classifiers and distill the capabilities of large language models into the online model. Extensive offline industrial benchmark evaluations and online A/B experiments demonstrate that the proposed framework substantially improves relevance performance, reducing the online bad-case rate by 15.94\%. Further analyses suggest that tier-wise modeling is effective for relevance estimation.

cs.IR↗

arXiv2026

Generating Project-Specific Test Cases with Requirement Validation Intention

Test cases are valuable assets for maintaining software quality. State-of-the-art automated test generation techniques typically focus on maximizing program branch coverage or translating focal methods into test code. However, in contrast to branch coverage or code-to-test translation, practical tests are written out of the need to validate whether a requirement has been fulfilled. Specifically, each test usually reflects a developer's validation intention for a program function, regarding (1) what is the test scenario of a program function? and (2) what is expected behavior under such a scenario? Without taking such intention into account, generated tests are less likely to be adopted in practice. In this work, we propose IntentionTest, which generates project-specific tests given the description of validation intention. IntentionTest adopts a retrieval-and-edit manner. First, given a focal code and a description of validation intention consisting of a test objective with test precondition and expected results, IntentionTest retrieves a reusable test in the project as the test reference. Then, IntentionTest edits the test reference with an LLM regarding the validation intention toward the target test. We extensively evaluate IntentionTest against four baselines on 3,680 test cases. Compared to state-of-the-art baselines, IntentionTest can (1) generate tests far more semantically relevant to ground-truth tests by (i) killing 28.1% to 37.6% more common mutants and (ii) sharing 16.9% to 23.9% more common coverage; and (2) generate 23.7% to 49.0% more successful passing tests.

cs.SE↗

arXiv2026

RealBench: A Repo-Level Code Generation Benchmark Aligned with Real-World Software Development Practices

Writing code requires significant time and effort in software development. To automate this process, researchers have made substantial progress using Large Language Models (LLMs) for code generation. Many benchmarks like HumanEval and EvoCodeBench have been created to evaluate LLMs by requiring them to generate code from natural language requirements. However, in enterprise applications and team development, developers typically write code based on structured designs or specifications rather than raw natural language descriptions. This gap between existing benchmarks and real industry development practices means that current benchmark scores may not accurately reflect how much code generation can help automate software development tasks. To address this gap, we propose RealBench, a repository-level code generation benchmark aligned with real-world industry software development practices. Each example includes both natural language requirements and UML diagrams as system design, matching how developers typically receive specifications. Based on the constructed benchmarks, we conduct a systematic evaluation of advanced LLMs' code generation capabilities when provided with structured system designs. The experimental results reveal key insights in current LLMs' capabilities for repo-level code generation aligned with real-world software development practices. First, we notice that regarding repo-level code generation, LLMs show much worse performance and there are significant performance gaps among LLMs. Second, LLMs are good at finding and creating modules defined in UML diagrams, but the quality of generated modules is often poor due to grammar and logic errors. Third, generating the entire repository at once is the best generation strategy on smaller repositories, while generating a complex repository with the module-by-module strategy works better compared to other strategies.

cs.SE↗