SpecBench: Evaluating Specification-Level Reasoning for Software Engineering LLM Agents

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Hamblin, Grant, Song, Kevin, Zhu, Zhanda, Jayarajan, Anand, Liu, Sihang, Vijaykumar, Nandita, Pekhimenko, Gennady
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Multiagent Systems
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Aegis: Taxonomy and Optimizations for Overcoming Agent-Environment Failures in LLM Agents
di: Song, Kevin, et al.
Pubblicazione: (2025)

Tally: Non-Intrusive Performance Isolation for Concurrent Deep Learning Workloads
di: Zhao, Wei, et al.
Pubblicazione: (2024)

SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents
di: Zhao, Bingchen, et al.
Pubblicazione: (2026)

SWE-WebDevBench: Evaluating Coding Agent Application Platforms as Virtual Software Agencies
di: Saxena, Siddhant, et al.
Pubblicazione: (2026)

Silo-Bench: A Scalable Environment for Evaluating Distributed Coordination in Multi-Agent LLM Systems
di: Zhang, Yuzhe, et al.
Pubblicazione: (2026)

DPQuant: Efficient and Differentially-Private Model Training via Dynamic Quantization Scheduling
di: Gao, Yubo, et al.
Pubblicazione: (2025)

MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents
di: Zhu, Kunlun, et al.
Pubblicazione: (2025)

What Limits Agentic Systems Efficiency?
di: Bian, Song, et al.
Pubblicazione: (2025)

Facilitating Trustworthy Human-Agent Collaboration in LLM-based Multi-Agent System oriented Software Engineering
di: Ronanki, Krishna
Pubblicazione: (2025)

SAGE: Multi-Agent Self-Evolution for LLM Reasoning
di: Peng, Yulin, et al.
Pubblicazione: (2026)

Evaluating Collective Behaviour of Hundreds of LLM Agents
di: Willis, Richard, et al.
Pubblicazione: (2026)

Spec Kit Agents: Context-Grounded Agentic Workflows
di: Taghavi, Pardis, et al.
Pubblicazione: (2026)

MACRO-LLM: LLM-Empowered Multi-Agent Collaborative Reasoning under Spatiotemporal Partial Observability
di: Chen, Handi, et al.
Pubblicazione: (2026)

Aegis:An Advanced LLM-Based Multi-Agent for Intelligent Functional Safety Engineering
di: Shi, Lu, et al.
Pubblicazione: (2024)

AgentWebBench: Benchmarking Multi-Agent Coordination in Agentic Web
di: Zhong, Shanshan, et al.
Pubblicazione: (2026)

Can LLM Agents Really Debate? A Controlled Study of Multi-Agent Debate in Logical Reasoning
di: Wu, Haolun, et al.
Pubblicazione: (2025)

Synergizing Logical Reasoning, Knowledge Management and Collaboration in Multi-Agent LLM System
di: Kostka, Adam, et al.
Pubblicazione: (2025)

Evaluating Multi-Agent LLM Architectures for Rare Disease Diagnosis
di: Almasoud, Ahmed
Pubblicazione: (2026)

Fairness in Multi-Agent Systems for Software Engineering: An SDLC-Oriented Rapid Review
di: Yang-Smith, Corey, et al.
Pubblicazione: (2026)

Adaptive Coopetition: Leveraging Coarse Verifier Signals for Resilient Multi-Agent LLM Reasoning
di: Huang, Rui Jerry, et al.
Pubblicazione: (2025)

Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering
di: Zhou, Chenyu, et al.
Pubblicazione: (2026)

CalBench: Evaluating Coordination-Privacy Trade-offs in Multi-Agent LLMs
di: Zou, Chelsea, et al.
Pubblicazione: (2026)

Fairness Driven Multi-Agent Path Finding Problem
di: Anand, Aditi, et al.
Pubblicazione: (2026)

LoRAFusion: Efficient LoRA Fine-Tuning for LLMs
di: Zhu, Zhanda, et al.
Pubblicazione: (2025)

SkillOps: Managing LLM Agent Skill Libraries as Self-Maintaining Software Ecosystems
di: Pu, Hongji, et al.
Pubblicazione: (2026)

GateLens: A Reasoning-Enhanced LLM Agent for Automotive Software Release Analytics
di: Khoee, Arsham Gholamzadeh, et al.
Pubblicazione: (2025)

From General Relation Patterns to Task-Specific Decision-Making in Continual Multi-Agent Coordination
di: Yao, Chang, et al.
Pubblicazione: (2025)

Long Live the Librarian! A Persistent Search Sub-Agent for Energy-Efficient Multi-Agent Software Engineering Systems
di: Cho, Seunghyuk, et al.
Pubblicazione: (2026)

Swarm Intelligence Enhanced Reasoning: A Density-Driven Framework for LLM-Based Multi-Agent Optimization
di: Zhu, Ying, et al.
Pubblicazione: (2025)

Analyzing Code Injection Attacks on LLM-based Multi-Agent Systems in Software Development
di: Bowers, Brian, et al.
Pubblicazione: (2025)

Self-Organizing Agent Network for LLM-based Workflow Automation
di: Xiong, Yiming, et al.
Pubblicazione: (2025)

MedAgentBench: A Realistic Virtual EHR Environment to Benchmark Medical LLM Agents
di: Jiang, Yixing, et al.
Pubblicazione: (2025)

Your Agents Are Aging Too: Agent Lifespan Engineering for Deployed Systems
di: Zhu, Jianing, et al.
Pubblicazione: (2026)

Logic of Awareness in Agent's Reasoning
di: Kubono, Yudai, et al.
Pubblicazione: (2023)

ReSo: A Reward-driven Self-organizing LLM-based Multi-Agent System for Reasoning Tasks
di: Zhou, Heng, et al.
Pubblicazione: (2025)

Multi-Agent LLM Committees for Autonomous Software Beta Testing
di: Karanam, Sumanth Bharadwaj Hachalli, et al.
Pubblicazione: (2025)

LLM-Enabled Multi-Agent Systems: Empirical Evaluation and Insights into Emerging Design Patterns & Paradigms
di: Renney, Harri, et al.
Pubblicazione: (2026)

TrajOnco: a multi-agent framework for temporal reasoning over longitudinal EHR for multi-cancer early detection
di: Zeng, Sihang, et al.
Pubblicazione: (2026)

DemMA: Dementia Multi-Turn Dialogue Agent with Expert-Guided Reasoning and Action Simulation
di: Song, Yutong, et al.
Pubblicazione: (2026)

AgentConductor: Topology Evolution for Multi-Agent Competition-Level Code Generation
di: Wang, Siyu, 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	"d7c0849960c2ba0e10052915b5b7e4a4"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790990764.3329 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "d7c0849960c2ba0e10052915b5b7e4a4" ]`]
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=d7c0849960c2ba0e10052915b5b7e4a4"
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	"15194"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2605_30314/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2605_30314/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790990764.3259
REQUEST_TIME	1790990764

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler