LLM Agents at the Roundtable: A Multi-Perspective and Dialectical Reasoning Framework for Essay Scoring

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Jang, Jinhee, Moon, Ayoung, Jung, Minkyoung, Kim, YoungBin, Lee, Seung Jin
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Plug-in and Fine-tuning: Bridging the Gap between Small Language Models and Large Language Models
par: Kim, Kyeonghyun, et autres
Publié: (2025)

Multi-News+: Cost-efficient Dataset Cleansing via LLM-based Data Annotation
par: Choi, Juhwan, et autres
Publié: (2024)

Adverb Is the Key: Simple Text Data Augmentation with Adverb Deletion
par: Choi, Juhwan, et autres
Publié: (2024)

GPTs Are Multilingual Annotators for Sequence Generation Tasks
par: Choi, Juhwan, et autres
Publié: (2024)

Beyond Single-User Dialogue: Assessing Multi-User Dialogue State Tracking Capabilities of Large Language Models
par: Song, Sangmin, et autres
Publié: (2025)

SUMMPILOT: Bridging Efficiency and Customization for Interactive Summarization System
par: Yun, JungMin, et autres
Publié: (2026)

Autoregressive Score Generation for Multi-trait Essay Scoring
par: Do, Heejin, et autres
Publié: (2024)

VolDoGer: LLM-assisted Datasets for Domain Generalization in Vision-Language Tasks
par: Choi, Juhwan, et autres
Publié: (2024)

Rationale Behind Essay Scores: Enhancing S-LLM's Multi-Trait Essay Scoring with Rationale Generated by LLMs
par: Chu, SeongYeub, et autres
Publié: (2024)

Medal Matters: Probing LLMs' Failure Cases Through Olympic Rankings
par: Choi, Juhwan, et autres
Publié: (2024)

Teach-to-Reason with Scoring: Self-Explainable Rationale-Driven Multi-Trait Essay Scoring
par: Do, Heejin, et autres
Publié: (2025)

UniGen: Universal Domain Generalization for Sentiment Classification via Zero-shot Dataset Generation
par: Choi, Juhwan, et autres
Publié: (2024)

CAFES: A Collaborative Multi-Agent Framework for Multi-Granular Multimodal Essay Scoring
par: Su, Jiamin, et autres
Publié: (2025)

Can David Beat Goliath? On Multi-Hop Reasoning with Resource-Constrained Agents
par: Han, Hojae, et autres
Publié: (2026)

Trait-Aware Policy Optimization for Autoregressive Multi-Trait Essay Scoring
par: Wang, Zhengyang, et autres
Publié: (2026)

From Ground Trust to Truth: Disparities in Offensive Language Judgments on Contemporary Korean Political Discourse
par: Yu, Seunguk, et autres
Publié: (2025)

Can Large Language Models Differentiate Harmful from Argumentative Essays? Steps Toward Ethical Essay Scoring
par: Kim, Hongjin, et autres
Publié: (2026)

Autoregressive Multi-trait Essay Scoring via Reinforcement Learning with Scoring-aware Multiple Rewards
par: Do, Heejin, et autres
Publié: (2024)

Composable Cross-prompt Essay Scoring by Merging Models
par: Lee, Sanwoo, et autres
Publié: (2025)

Exploring LLM Prompting Strategies for Joint Essay Scoring and Feedback Generation
par: Stahl, Maja, et autres
Publié: (2024)

CODMAS: A Dialectic Multi-Agent Collaborative Framework for Structured RTL Optimization
par: Chang, Che-Ming, et autres
Publié: (2026)

VG-CoT: Towards Trustworthy Visual Reasoning via Grounded Chain-of-Thought
par: Lim, Byeonggeuk, et autres
Publié: (2026)

PSYCHE: A Multi-faceted Patient Simulation Framework for Evaluation of Psychiatric Assessment Conversational Agents
par: Lee, Jingoo, et autres
Publié: (2025)

Improve LLM-based Automatic Essay Scoring with Linguistic Features
par: Hou, Zhaoyi Joey, et autres
Publié: (2025)

GEMA-Score: Granular Explainable Multi-Agent Scoring Framework for Radiology Report Evaluation
par: Zhang, Zhenxuan, et autres
Publié: (2025)

MAPLE: A Meta-learning Framework for Cross-Prompt Essay Scoring
par: Albatarni, Salam, et autres
Publié: (2026)

Rank-Then-Score: Enhancing Large Language Models for Automated Essay Scoring
par: Cai, Yida, et autres
Publié: (2025)

RDBE: Reasoning Distillation-Based Evaluation Enhances Automatic Essay Scoring
par: Mohammadkhani, Ali Ghiasvand
Publié: (2024)

A Training-Free Large Reasoning Model-based Knowledge Tracing Framework for Unified Prediction and Prescription
par: Lee, Unggi, et autres
Publié: (2026)

Pair2Score: Pairwise-to-Absolute Transfer for LLM-Based Essay Scoring
par: Hallaç, İbrahim Rıza, et autres
Publié: (2026)

Enhancing Automated Essay Scoring with Three Techniques: Two-Stage Fine-Tuning, Score Alignment, and Self-Training
par: Choi, Hongseok, et autres
Publié: (2026)

A Multi-Agent Framework for Mitigating Dialect Biases in Privacy Policy Question-Answering Systems
par: Klisura, Đorđe, et autres
Publié: (2025)

Unleashing Large Language Models' Proficiency in Zero-shot Essay Scoring
par: Lee, Sanwoo, et autres
Publié: (2024)

From Assumptions to Actions: Turning LLM Reasoning into Uncertainty-Aware Planning for Embodied Agents
par: Seo, SeungWon, et autres
Publié: (2026)

Can LLM Agents Identify Spoken Dialects like a Linguist?
par: Bystrich, Tobias, et autres
Publié: (2026)

Query, Decompose, Compress: Structured Query Expansion for Efficient Multi-Hop Retrieval
par: Yun, JungMin, et autres
Publié: (2026)

BlockDialect: Block-wise Fine-grained Mixed Format Quantization for Energy-Efficient LLM Inference
par: Jang, Wonsuk, et autres
Publié: (2025)

Dual-Scale World Models for LLM Agents Towards Hard-Exploration Problems
par: Kim, Minsoo, et autres
Publié: (2025)

Automatic Essay Scoring in a Brazilian Scenario
par: Matsuoka, Felipe Akio
Publié: (2023)

Position on LLM-Assisted Peer Review: Addressing Reviewer Gap through Mentoring and Feedback
par: Yun, JungMin, et autres
Publié: (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	"fr"
VUFIND_SESSION	"a57ee538bd6831b526703d4b3ba40c0c"
ui	"standard"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790897088.1866 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "a57ee538bd6831b526703d4b3ba40c0c" ]`]
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=a57ee538bd6831b526703d4b3ba40c0c; 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	"2479"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2509_14834/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2509_14834/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790897088.1823
REQUEST_TIME	1790897088

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler