Improving Small-Scale Large Language Models Function Calling for Reasoning Tasks

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Manduzio, Graziano A., Galatolo, Federico A., Cimino, Mario G. C. A., Scilingo, Enzo Pasquale, Cominelli, Lorenzo
Format:	Preprint
Publié:	2024
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Interpretable Machine Learning for Oral Lesion Diagnosis through Prototypical Instances Identification
par: Cascione, Alessio, et autres
Publié: (2025)

Small Models, Big Tasks: An Exploratory Empirical Study on Small Language Models for Function Calling
par: Kavathekar, Ishan, et autres
Publié: (2025)

Reproducible Physiological Features in Affective Computing: A Preliminary Analysis on Arousal Modeling
par: Gargano, Andrea, et autres
Publié: (2025)

Improving Large Language Models Function Calling and Interpretability via Guided-Structured Templates
par: Dang, Hy, et autres
Publié: (2025)

Optimizing Small Language Models for In-Vehicle Function-Calling
par: Khiabani, Yahya Sowti, et autres
Publié: (2025)

Instruction-Following Evaluation in Function Calling for Large Language Models
par: Skripko, Nikolai
Publié: (2025)

CarbonCall: Sustainability-Aware Function Calling for Large Language Models on Edge Devices
par: Paramanayakam, Varatheepan, et autres
Publié: (2025)

Large Language Models as Zero-shot Dialogue State Tracker through Function Calling
par: Li, Zekun, et autres
Publié: (2024)

The Dark Side of Function Calling: Pathways to Jailbreaking Large Language Models
par: Wu, Zihui, et autres
Publié: (2024)

Small Language Models for Efficient Agentic Tool Calling: Outperforming Large Models with Targeted Fine-tuning
par: Jhandi, Polaris, et autres
Publié: (2025)

LightReasoner: Can Small Language Models Teach Large Language Models Reasoning?
par: Wang, Jingyuan, et autres
Publié: (2025)

A Mentalistic Interface for Probing Folk-Psychological Attribution to Non-Humanoid Robots
par: Pisaneschi, Giulio, et autres
Publié: (2026)

Granite-Function Calling Model: Introducing Function Calling Abilities via Multi-task Learning of Granular Tasks
par: Abdelaziz, Ibrahim, et autres
Publié: (2024)

Data-driven Exploration of Mobility Interaction Patterns
par: Galatolo, Gabriele, et autres
Publié: (2025)

Reasoning Capabilities of Large Language Models on Dynamic Tasks
par: Wong, Annie, et autres
Publié: (2025)

A Survey of Scaling in Large Language Model Reasoning
par: Chen, Zihan, et autres
Publié: (2025)

Tandem: Riding Together with Large and Small Language Models for Efficient Reasoning
par: Fu, Zichuan, et autres
Publié: (2026)

mind_call: A Dataset for Mental Health Function Calling with Large Language Models
par: Shafi, Fozle Rabbi, et autres
Publié: (2026)

Interleaved Tool-Call Reasoning for Protein Function Understanding
par: Fan, Chuanliu, et autres
Publié: (2026)

Think-Augmented Function Calling: Improving LLM Parameter Accuracy Through Embedded Reasoning
par: Wei, Lei, et autres
Publié: (2026)

On the Self-Verification Limitations of Large Language Models on Reasoning and Planning Tasks
par: Stechly, Kaya, et autres
Publié: (2024)

Eliciting Causal Abilities in Large Language Models for Reasoning Tasks
par: Wang, Yajing, et autres
Publié: (2024)

Route-and-Reason: Scaling Large Language Model Reasoning with Reinforced Model Router
par: Shao, Chenyang, et autres
Publié: (2025)

Can only LLMs do Reasoning?: Potential of Small Language Models in Task Planning
par: Choi, Gawon, et autres
Publié: (2024)

Pruning Long Chain-of-Thought of Large Reasoning Models via Small-Scale Preference Optimization
par: Hong, Bin, et autres
Publié: (2025)

Improving Phishing Email Detection Performance of Small Large Language Models
par: Lin, Zijie, et autres
Publié: (2025)

Using Contrastive Learning to Improve Two-Way Reasoning in Large Language Models: The Obfuscation Task as a Case Study
par: Nikiema, Serge Lionel, et autres
Publié: (2025)

Improving Mathematical Reasoning Capabilities of Small Language Models via Feedback-Driven Distillation
par: Zhu, Xunyu, et autres
Publié: (2024)

Can Large Reasoning Models Improve Accuracy on Mathematical Tasks Using Flawed Thinking?
par: Amjith, Saraswathy, et autres
Publié: (2025)

Meta-Reasoning Improves Tool Use in Large Language Models
par: Alazraki, Lisa, et autres
Publié: (2024)

Bridging the Reasoning Gap in Vietnamese with Small Language Models via Test-Time Scaling
par: Trung, Bui The, et autres
Publié: (2026)

Benchmarking Small Language Models and Small Reasoning Language Models on System Log Severity Classification
par: Masri, Yahya, et autres
Publié: (2026)

Confidence-Calibrated Small-Large Language Model Collaboration for Cost-Efficient Reasoning
par: Zhang, Chuang, et autres
Publié: (2026)

Spatial Reasoning in Multimodal Large Language Models: A Survey of Tasks, Benchmarks and Methods
par: Liu, Weichen, et autres
Publié: (2025)

DyVal: Dynamic Evaluation of Large Language Models for Reasoning Tasks
par: Zhu, Kaijie, et autres
Publié: (2023)

Can Large Language Models Create New Knowledge for Spatial Reasoning Tasks?
par: Greatrix, Thomas, et autres
Publié: (2024)

Understanding Artificial Theory of Mind: Perturbed Tasks and Reasoning in Large Language Models
par: Nickel, Christian, et autres
Publié: (2026)

Using Counterfactual Tasks to Evaluate the Generality of Analogical Reasoning in Large Language Models
par: Lewis, Martha, et autres
Publié: (2024)

Code Reasoning for Software Engineering Tasks: A Survey and A Call to Action
par: Pujar, Saurabh, et autres
Publié: (2025)

SPAN: Benchmarking and Improving Cross-Calendar Temporal Reasoning of Large Language Models
par: Miao, Zhongjian, et autres
Publié: (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	"fr"
VUFIND_SESSION	"c046ea49ecb9f06d05e24a94f8b49925"
ui	"standard"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790987123.8327 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "c046ea49ecb9f06d05e24a94f8b49925" ]`]
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=fr; VUFIND_SESSION=c046ea49ecb9f06d05e24a94f8b49925; 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	"51122"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2410_18890/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2410_18890/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790987123.8283
REQUEST_TIME	1790987123

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler