LIDL: LLM Integration Defect Localization via Knowledge Graph-Enhanced Multi-Agent Analysis

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Tan, Gou, He, Zilong, Li, Min, Chen, Pengfei, Shi, Jieke, Sun, Zhensu, Zhang, Ting, Chen, Danwen, Shar, Lwin Khin, Zhang, Chuanfu, Lo, David
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Software Engineering
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

PenForge: On-the-Fly Expert Agent Construction for Automated Penetration Testing
di: Huang, Huihui, et al.
Pubblicazione: (2026)

Runtime Anomaly Detection for Drones: An Integrated Rule-Mining and Unsupervised-Learning Approach
di: Tan, Ivan, et al.
Pubblicazione: (2025)

Back to the Basics: Rethinking Issue-Commit Linking with LLM-Assisted Retrieval
di: Huang, Huihui, et al.
Pubblicazione: (2025)

Fixseeker: An Empirical Driven Graph-based Approach for Detecting Silent Vulnerability Fixes in Open Source Software
di: Cheng, Yiran, et al.
Pubblicazione: (2025)

Think Like Human Developers: Harnessing Community Knowledge for Structured Code Reasoning
di: Yang, Chengran, et al.
Pubblicazione: (2025)

InferLog: Accelerating LLM Inference for Online Log Parsing via ICL-oriented Prefix Caching
di: Wang, Yilun, et al.
Pubblicazione: (2025)

VERCATION: Precise Vulnerable Open-source Software Version Identification based on Static Analysis and LLM
di: Cheng, Yiran, et al.
Pubblicazione: (2024)

Semantics-Aligned, Curriculum-Driven, and Reasoning-Enhanced Vulnerability Repair Framework
di: Yang, Chengran, et al.
Pubblicazione: (2025)

CovAgent: Overcoming the 30% Curse of Mobile Application Coverage with Agentic AI and Dynamic Instrumentation
di: Minn, Wei, et al.
Pubblicazione: (2026)

Bamboo: LLM-Driven Discovery of API-Permission Mappings in the Android Framework
di: Hu, Han, et al.
Pubblicazione: (2025)

VLM-Fuzz: Vision Language Model Assisted Recursive Depth-first Search Exploration for Effective UI Testing of Android Apps
di: Demissie, Biniam Fisseha, et al.
Pubblicazione: (2025)

Let the Trial Begin: A Mock-Court Approach to Vulnerability Detection using LLM-Based Agents
di: Widyasari, Ratnadira, et al.
Pubblicazione: (2025)

Towards Reliable LLM-Driven Fuzz Testing: Vision and Road Ahead
di: Cheng, Yiran, et al.
Pubblicazione: (2025)

Beyond Function-Level Analysis: Context-Aware Reasoning for Inter-Procedural Vulnerability Detection
di: Li, Yikun, et al.
Pubblicazione: (2026)

Benchmarking Large Language Models for Multi-Language Software Vulnerability Detection
di: Zhang, Ting, et al.
Pubblicazione: (2025)

An Execution-Verified Multi-Language Benchmark for Code Semantic Reasoning
di: Li, Yikun, et al.
Pubblicazione: (2026)

PatchSeeker: Mapping NVD Records to their Vulnerability-fixing Commits with LLM Generated Commits and Embeddings
di: Nguyen, Huu Hung, et al.
Pubblicazione: (2025)

Rethinking the Value of Agent-Generated Tests for LLM-Based Software Engineering Agents
di: Chen, Zhi, et al.
Pubblicazione: (2026)

Revisiting Vulnerability Patch Identification on Data in the Wild
di: Irsan, Ivana Clairine, et al.
Pubblicazione: (2026)

The Hidden Cost of Readability: How Code Formatting Silently Consumes Your LLM Budget
di: Pan, Dangfeng, et al.
Pubblicazione: (2025)

VulCoCo: A Simple Yet Effective Method for Detecting Vulnerable Code Clones
di: Bui, Tan, et al.
Pubblicazione: (2025)

Mapping NVD Records to Their Vulnerability-fixing Commits: How Hard is It?
di: Nguyen, Huu Hung, et al.
Pubblicazione: (2025)

CleanVul: Automatic Function-Level Vulnerability Detection in Code Commits Using LLM Heuristics
di: Li, Yikun, et al.
Pubblicazione: (2024)

Efficient and Green Large Language Models for Software Engineering: Literature Review, Vision, and the Road Ahead
di: Shi, Jieke, et al.
Pubblicazione: (2024)

Virtualization-based Penetration Testing Study for Detecting Accessibility Abuse Vulnerabilities in Banking Apps in East and Southeast Asia
di: Minn, Wei, et al.
Pubblicazione: (2026)

AgentSZZ: Teaching the LLM Agent to Play Detective with Bug-Inducing Commits
di: Lyu, Yunbo, et al.
Pubblicazione: (2026)

SLICEMATE: Accurate and Scalable Static Program Slicing via LLM-Powered Agents
di: Chang, Jianming, et al.
Pubblicazione: (2025)

Bridging Developer Instructions and Code Completion Through Instruction-Aware Fill-in-the-Middle Paradigm
di: Sun, Zhensu, et al.
Pubblicazione: (2025)

R2Vul: Learning to Reason about Software Vulnerabilities with Reinforcement Learning and Structured Reasoning Distillation
di: Weyssow, Martin, et al.
Pubblicazione: (2025)

Executing as You Generate: Hiding Execution Latency in LLM Code Generation
di: Sun, Zhensu, et al.
Pubblicazione: (2026)

From Incomplete Architecture to Quantified Risk: Multimodal LLM-Driven Security Assessment for Cyber-Physical Systems
di: Huang, Shaofei, et al.
Pubblicazione: (2026)

Beyond the Tip of the Iceberg: Understanding SATD in Dockerfiles through the Lens of Co-evolution
di: Minn, Wei, et al.
Pubblicazione: (2026)

Ecosystem of Large Language Models for Code
di: Yang, Zhou, et al.
Pubblicazione: (2024)

Out of Distribution, Out of Luck: How Well Can LLMs Trained on Vulnerability Datasets Detect Top 25 CWE Weaknesses?
di: Li, Yikun, et al.
Pubblicazione: (2025)

Robustness, Security, Privacy, Explainability, Efficiency, and Usability of Large Language Models for Code
di: Yang, Zhou, et al.
Pubblicazione: (2024)

ACECode: A Reinforcement Learning Framework for Aligning Code Efficiency and Correctness in Code Language Models
di: Yang, Chengran, et al.
Pubblicazione: (2024)

MetaRCA: A Generalizable Root Cause Analysis Framework for Cloud-Native Systems Powered by Meta Causal Knowledge
di: Liang, Shuai, et al.
Pubblicazione: (2026)

Finding Missing Input Validation in TEEs via LLM-Assisted Symbolic Execution
di: Ma, Chengyan, et al.
Pubblicazione: (2026)

Token Sugar: Making Source Code Sweeter for LLMs through Token-Efficient Shorthand
di: Sun, Zhensu, et al.
Pubblicazione: (2025)

Deterministic vs. LLM-Controlled Orchestration for COBOL-to-Python Modernization
di: Lwin, Naing Oo, et al.
Pubblicazione: (2026)

if (filemtime($filename) + $maxlifetime < time()) { unlink($filename); $count++; } } return $count; } /** * A function that is called internally when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ protected function saveSession($sessId, $data): bool { $sessFile = $this->path . '/sess_' . $sessId; if ($handle = fopen($sessFile, 'w')) { $return = false; // Lock the file for exclusive access to avoid issues with multiple // processes writing session simultaneously: if (flock($handle, LOCK_EX)) { $return = fwrite($handle, $data); // Make sure that there's no trailing data by truncating the file to // the correct length: ftruncate($handle, strlen($data)); fflush($handle); flock($handle, LOCK_UN); } fclose($handle); if ($return !== false) { return true; } } // If we got this far, something went wrong with the file output... // It is tempting to throw an exception here, but this code is called // outside of the context of exception handling, so all we can do is // echo a message.

// Anecdotal testing Today and Yesterday seems to indicate destroy() // is called by the garbage collector and everything is good. // Something to keep in mind though. return 0; } /** * Write function that is called when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ public function write($sessId, $data): bool { if ($this->writesDisabled) { return true; } return $this->saveSession($sessId, $data); } /** * A function that is called internally when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ abstract protected function saveSession($sessId, $data): bool; }

* * @return void */ public function writeClose() { // The assumption is that we're using PHP's ext/session. // session_write_close() will actually overwrite $_SESSION with an // empty array on completion -- which leads to a mismatch between what // is in the storage object and $_SESSION. To get around this, we // temporarily reset $_SESSION to an array, and then re-link it to // the storage object. // // Additionally, while you _can_ write to $_SESSION following a // session_write_close() operation, no changes made to it will be // flushed to the session handler. As such, we now mark the storage // object isImmutable. $storage = $this->getStorage(); if (! $storage->isImmutable()) { $_SESSION = $storage->toArray(true); session_write_close(); $storage->fromArray($_SESSION); $storage->markImmutable(); } } /** * Attempt to set the session name * * If the session has already been started, or if the name provided fails * validation, an exception will be raised. * * @param string $name * @return SessionManager * @throws Exception\InvalidArgumentException */ public function setName($name) { if ($this->sessionExists()) { throw new Exception\InvalidArgumentException( 'Cannot set session name after a session has already started'

Environment & details:

GET Data empty

POST Data empty

Files empty

Key	Value
language	"it"
ui	"standard"
VUFIND_SESSION	"d0d1b0ae05acb9ce57def29675bf4c5c"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790958139.0733 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "d0d1b0ae05acb9ce57def29675bf4c5c" ]`]
SessionState	Laminas\Stdlib\ArrayObject {#938}
FlashMessenger	Laminas\Stdlib\ArrayObject {#1433}
SessionHelper	Laminas\Stdlib\ArrayObject {#1759}

Server/Request Data

Key	Value
REDIRECT_VUFIND_LOCAL_DIR	"/usr/local/vufind/local"
REDIRECT_HTTPS	"on"
REDIRECT_SSL_TLS_SNI	"info.umar.mx"
REDIRECT_STATUS	"200"
VUFIND_LOCAL_DIR	"/usr/local/vufind/local"
HTTPS	"on"
SSL_TLS_SNI	"info.umar.mx"
HTTP_ACCEPT	"/"
HTTP_USER_AGENT	"Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; ClaudeBot/1.0; +claudebot@anthropic.com)"
HTTP_COOKIE	"language=it; ui=standard; VUFIND_SESSION=d0d1b0ae05acb9ce57def29675bf4c5c"
HTTP_ACCEPT_ENCODING	"gzip, br, zstd, deflate"
HTTP_HOST	"info.umar.mx"
PATH	"/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/snap/bin"
SERVER_SIGNATURE	"<address>Apache/2.4.66 (Ubuntu) Server at info.umar.mx Port 443</address>\n"
SERVER_SOFTWARE	"Apache/2.4.66 (Ubuntu)"
SERVER_NAME	"info.umar.mx"
SERVER_ADDR	"200.23.222.19"
SERVER_PORT	"443"
REMOTE_ADDR	"216.73.217.142"
DOCUMENT_ROOT	"/usr/local/vufind/public"
REQUEST_SCHEME	"https"
CONTEXT_PREFIX	""
CONTEXT_DOCUMENT_ROOT	"/usr/local/vufind/public"
SERVER_ADMIN	"admin@localhost"
SCRIPT_FILENAME	"/usr/local/vufind/public/index.php"
REMOTE_PORT	"54703"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2601_05539/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2601_05539/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790958139.0689
REQUEST_TIME	1790958139

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler