WorkflowPerturb: Calibrated Stress Tests for Evaluating Multi-Agent Workflow Metrics

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kanda, Madhav, Las-Casas, Pedro, Kumbhare, Alok Gautam, Fonseca, Rodrigo, Agarwal, Sharad
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Designing Datacenter Power Delivery Hierarchies for the AI Era
by: Wilkins, Grant, et al.
Published: (2026)

Automated Multi-Agent Workflows for RTL Design
by: Bhattaram, Amulya, et al.
Published: (2025)

When Does Multi-Agent RL Improve LLM Workflows? Workflow, Scale, and Policy-Sharing Tradeoffs
by: Zeng, Yifan, et al.
Published: (2026)

Constrained Process Maps for Multi-Agent Generative AI Workflows
by: Joshi, Ananya, et al.
Published: (2026)

Adaptive Multi-Agent Reasoning via Automated Workflow Generation
by: Sami, Humza, et al.
Published: (2025)

AgentCo-op: Retrieval-Based Synthesis of Interoperable Multi-Agent Workflows
by: Shen, Shuaike, et al.
Published: (2026)

Rethinking the AI Scientist: Interactive Multi-Agent Workflows for Scientific Discovery
by: Weidener, Lukas, et al.
Published: (2026)

EvoMAS: Learning Execution-Time Workflows for Multi-Agent Systems
by: Xu, Chengdong, et al.
Published: (2026)

Difficulty-Aware Agentic Orchestration for Query-Specific Multi-Agent Workflows
by: Su, Jinwei, et al.
Published: (2025)

FlowAgent: Achieving Compliance and Flexibility for Workflow Agents
by: Shi, Yuchen, et al.
Published: (2025)

AgentSCOPE: Evaluating Contextual Privacy Across Agentic Workflows
by: Ngong, Ivoline C., et al.
Published: (2026)

AgentCompass: Towards Reliable Evaluation of Agentic Workflows in Production
by: Kartik, NVJK, et al.
Published: (2025)

Benchmarking LLM Agents for Wealth-Management Workflows
by: Milsom, Rory
Published: (2025)

Workflow-R1: Group Sub-sequence Policy Optimization for Multi-turn Workflow Construction
by: Kong, Mingze, et al.
Published: (2026)

HAWK: A Hierarchical Workflow Framework for Multi-Agent Collaboration
by: Cheng, Yuyang, et al.
Published: (2025)

$π$-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows
by: Zhang, Haoran, et al.
Published: (2026)

Workflows vs Agents for Code Translation
by: Gray, Henry, et al.
Published: (2025)

Opus: A Workflow Intention Framework for Complex Workflow Generation
by: Kingston, Phillip, et al.
Published: (2025)

BankerToolBench: Evaluating AI Agents in End-to-End Investment Banking Workflows
by: Lau, Elaine, et al.
Published: (2026)

Are Agents Ready to Teach? A Multi-Stage Benchmark for Real-World Teaching Workflows
by: Chen, Zixin, et al.
Published: (2026)

Governed Memory: A Production Architecture for Multi-Agent Workflows
by: Taheri, Hamed
Published: (2026)

Do We Always Need Query-Level Workflows? Rethinking Agentic Workflow Generation for Multi-Agent Systems
by: Wang, Zixu, et al.
Published: (2026)

From Intent to Execution: Composing Agentic Workflows with Agent Recommendation
by: Athrey, Kishan, et al.
Published: (2026)

EvoAgentX: An Automated Framework for Evolving Agentic Workflows
by: Wang, Yingxu, et al.
Published: (2025)

NetGent: Agent-Based Automation of Network Application Workflows
by: Daneshamooz, Jaber, et al.
Published: (2025)

L-MARS: Legal Multi-Agent Workflow with Orchestrated Reasoning and Agentic Search
by: Wang, Ziqi, et al.
Published: (2025)

Agentic Mixture-of-Workflows for Multi-Modal Chemical Search
by: Callahan, Tiffany J., et al.
Published: (2025)

Murakkab: Resource-Efficient Agentic Workflow Orchestration in Cloud Platforms
by: Chaudhry, Gohar Irfan, et al.
Published: (2025)

Building Persona-Based Agents On Demand: Tailoring Multi-Agent Workflows to User Needs
by: Arbore, Giuseppe, et al.
Published: (2026)

A Survey on Agent Workflow -- Status and Future
by: Yu, Chaojia, et al.
Published: (2025)

From Text to Simulation: A Multi-Agent LLM Workflow for Automated Chemical Process Design
by: Tian, Xufei, et al.
Published: (2026)

TDFlow: Agentic Workflows for Test Driven Development
by: Han, Kevin, et al.
Published: (2025)

Opus: A Quantitative Framework for Workflow Evaluation
by: Seroul, Alan, et al.
Published: (2025)

Engineering Robustness into Personal Agents with the AI Workflow Store
by: Geambasu, Roxana, et al.
Published: (2026)

Foam-Agent: Towards Automated Intelligent CFD Workflows
by: Yue, Ling, et al.
Published: (2025)

Exploring Robust Multi-Agent Workflows for Environmental Data Management
by: Guan, Boyuan, et al.
Published: (2026)

Beyond Rule-Based Workflows: An Information-Flow-Orchestrated Multi-Agents Paradigm via Agent-to-Agent Communication from CORAL
by: Ren, Xinxing, et al.
Published: (2026)

Multi-Step Dialogue Workflow Action Prediction
by: Ramakrishnan, Ramya, et al.
Published: (2023)

EduAgentQG: A Multi-Agent Workflow Framework for Personalized Question Generation
by: Jia, Rui, et al.
Published: (2025)

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	"en"
VUFIND_SESSION	"b304aefc1b9196f658fdd9ddd0e16b7c"
ui	"standard"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790951270.5791 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "b304aefc1b9196f658fdd9ddd0e16b7c" ]`]
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=en; VUFIND_SESSION=b304aefc1b9196f658fdd9ddd0e16b7c; ui=standard"
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	"5628"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2602_17990/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2602_17990/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790951270.5725
REQUEST_TIME	1790951270

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler

Environment & details:

GET Data empty

POST Data empty

Files empty

Key	Value
language	"en"
VUFIND_SESSION	"b304aefc1b9196f658fdd9ddd0e16b7c"
ui	"standard"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790951270.5791 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "b304aefc1b9196f658fdd9ddd0e16b7c" ]`]
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=en; VUFIND_SESSION=b304aefc1b9196f658fdd9ddd0e16b7c; ui=standard"
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	"5628"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2602_17990/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2602_17990/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790951270.5725
REQUEST_TIME	1790951270

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler

Similar Items

Similar Items

Environment & details:

Environment & details: