Automated test generation to evaluate tool-augmented LLMs as conversational AI agents

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Arcadinho, Samuel, Aparicio, David, Almeida, Mariana
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computation and Language Artificial Intelligence Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Agentic-imodels: Evolving agentic interpretability tools via autoresearch
di: Singh, Chandan, et al.
Pubblicazione: (2026)

Language hooks: a modular framework for augmenting LLM reasoning that decouples tool usage from the model and its prompt
di: de Mijolla, Damien, et al.
Pubblicazione: (2024)

Efficient multi-prompt evaluation of LLMs
di: Polo, Felipe Maia, et al.
Pubblicazione: (2024)

How malicious AI swarms can threaten democracy: The fusion of agentic AI and LLMs marks a new frontier in information warfare
di: Schroeder, Daniel Thilo, et al.
Pubblicazione: (2025)

tinyBenchmarks: evaluating LLMs with fewer examples
di: Polo, Felipe Maia, et al.
Pubblicazione: (2024)

The Illusion of Progress: Re-evaluating Hallucination Detection in LLMs
di: Janiak, Denis, et al.
Pubblicazione: (2025)

Towards Scalable Automated Alignment of LLMs: A Survey
di: Cao, Boxi, et al.
Pubblicazione: (2024)

Improving embedding with contrastive fine-tuning on small datasets with expert-augmented scores
di: Lu, Jun, et al.
Pubblicazione: (2024)

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
di: Lu, Chris, et al.
Pubblicazione: (2024)

Towards physician-centered oversight of conversational diagnostic AI
di: Vedadi, Elahe, et al.
Pubblicazione: (2025)

Layerwise Recall and the Geometry of Interwoven Knowledge in LLMs
di: Lei, Ge, et al.
Pubblicazione: (2025)

Towards Execution-Grounded Automated AI Research
di: Si, Chenglei, et al.
Pubblicazione: (2026)

Retrieval-augmented GUI Agents with Generative Guidelines
di: Xu, Ran, et al.
Pubblicazione: (2025)

BEExAI: Benchmark to Evaluate Explainable AI
di: Sithakoul, Samuel, et al.
Pubblicazione: (2024)

Predicting Training Re-evaluation Curves Enables Effective Data Curriculums for LLMs
di: Bergsma, Shane, et al.
Pubblicazione: (2025)

AI Knowledge Assist: An Automated Approach for the Creation of Knowledge Bases for Conversational AI Agents
di: Laskar, Md Tahmid Rahman, et al.
Pubblicazione: (2025)

What's the plan? Metrics for implicit planning in LLMs and their application to rhyme generation and question answering
di: Maar, Jim, et al.
Pubblicazione: (2026)

Automated Text Scoring in the Age of Generative AI for the GPU-poor
di: Ormerod, Christopher Michael, et al.
Pubblicazione: (2024)

AIGS: Generating Science from AI-Powered Automated Falsification
di: Liu, Zijun, et al.
Pubblicazione: (2024)

Remote Labor Index: Measuring AI Automation of Remote Work
di: Mazeika, Mantas, et al.
Pubblicazione: (2025)

TxGemma: Efficient and Agentic LLMs for Therapeutics
di: Wang, Eric, et al.
Pubblicazione: (2025)

The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search
di: Yamada, Yutaro, et al.
Pubblicazione: (2025)

EAGLE: A Domain Generalization Framework for AI-generated Text Detection
di: Bhattacharjee, Amrita, et al.
Pubblicazione: (2024)

Prefill-Guided Thinking for zero-shot detection of AI-generated images
di: Kachwala, Zoher, et al.
Pubblicazione: (2025)

Representation of perceived prosodic similarity of conversational feedback
di: Qian, Livia, et al.
Pubblicazione: (2025)

TLDR at SemEval-2024 Task 2: T5-generated clinical-Language summaries for DeBERTa Report Analysis
di: Das, Spandan, et al.
Pubblicazione: (2024)

RuAG: Learned-rule-augmented Generation for Large Language Models
di: Zhang, Yudi, et al.
Pubblicazione: (2024)

RadioRAG: Online Retrieval-augmented Generation for Radiology Question Answering
di: Arasteh, Soroosh Tayebi, et al.
Pubblicazione: (2024)

Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs
di: Laine, Rudolf, et al.
Pubblicazione: (2024)

The AI Data Scientist
di: Akimov, Farkhad, et al.
Pubblicazione: (2025)

Aviary: training language agents on challenging scientific tasks
di: Narayanan, Siddharth, et al.
Pubblicazione: (2024)

UnibucLLM: Harnessing LLMs for Automated Prediction of Item Difficulty and Response Time for Multiple-Choice Questions
di: Rogoz, Ana-Cristina, et al.
Pubblicazione: (2024)

COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation
di: Zhou, Tianyi, et al.
Pubblicazione: (2026)

Alignment Pretraining: AI Discourse Causes Self-Fulfilling (Mis)alignment
di: Tice, Cameron, et al.
Pubblicazione: (2026)

Speaking the Same Language: Leveraging LLMs in Standardizing Clinical Data for AI
di: Sett, Arindam, et al.
Pubblicazione: (2024)

Censored LLMs as a Natural Testbed for Secret Knowledge Elicitation
di: Casademunt, Helena, et al.
Pubblicazione: (2026)

DeTeCtive: Detecting AI-generated Text via Multi-Level Contrastive Learning
di: Guo, Xun, et al.
Pubblicazione: (2024)

PersonaGym: Evaluating Persona Agents and LLMs
di: Samuel, Vinay, et al.
Pubblicazione: (2024)

T-FREE: Subword Tokenizer-Free Generative LLMs via Sparse Representations for Memory-Efficient Embeddings
di: Deiseroth, Björn, et al.
Pubblicazione: (2024)

A prospective clinical feasibility study of a conversational diagnostic AI in an ambulatory primary care clinic
di: Brodeur, Peter, 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
ui	"standard"
VUFIND_SESSION	"d5ec67625d0f721368567eb415586b5e"
language	"it"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790899784.8521 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "d5ec67625d0f721368567eb415586b5e" ]`]
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	"ui=standard; VUFIND_SESSION=d5ec67625d0f721368567eb415586b5e; language=it"
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	"5976"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2409_15934/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2409_15934/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790899784.8476
REQUEST_TIME	1790899784

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler