ALDEN: Reinforcement Learning for Active Navigation and Evidence Gathering in Long Documents

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yang, Tianyu, Ruas, Terry, Tian, Yijun, Wahle, Jan Philip, Kurzawe, Daniel, Gipp, Bela
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Artificial Intelligence Multimedia
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

What's under the hood: Investigating Automatic Metrics on Meeting Summarization
di: Kirstein, Frederic, et al.
Pubblicazione: (2024)

CADS: A Systematic Literature Review on the Challenges of Abstractive Dialogue Summarization
di: Kirstein, Frederic, et al.
Pubblicazione: (2024)

How Large Language Models are Transforming Machine-Paraphrased Plagiarism
di: Wahle, Jan Philip, et al.
Pubblicazione: (2022)

SPaRC: A Spatial Pathfinding Reasoning Challenge
di: Kaesberg, Lars Benedikt, et al.
Pubblicazione: (2025)

Big Tech-Funded AI Papers Have Higher Citation Impact, Greater Insularity, and Larger Recency Bias
di: Gnewuch, Max Martin, et al.
Pubblicazione: (2025)

You need to MIMIC to get FAME: Solving Meeting Transcript Scarcity with a Multi-Agent Conversations
di: Kirstein, Frederic, et al.
Pubblicazione: (2025)

Mind the Gap Between Spatial Reasoning and Acting! Step-by-Step Evaluation of Agents With Spatial-Gym
di: Kaesberg, Lars Benedikt, et al.
Pubblicazione: (2026)

Multi-Agent Reasoning Improves Compute Efficiency: Pareto-Optimal Test-Time Scaling
di: Wunderlich, Florian Valentin, et al.
Pubblicazione: (2026)

Voting or Consensus? Decision-Making in Multi-Agent Debate
di: Kaesberg, Lars Benedikt, et al.
Pubblicazione: (2025)

Testing the Generalization of Neural Language Models for COVID-19 Misinformation Detection
di: Wahle, Jan Philip, et al.
Pubblicazione: (2021)

Paraphrase Types for Generation and Detection
di: Wahle, Jan Philip, et al.
Pubblicazione: (2023)

Is my Meeting Summary Good? Estimating Quality with a Multi-LLM Evaluator
di: Kirstein, Frederic, et al.
Pubblicazione: (2024)

What's Wrong? Refining Meeting Summaries with LLM Feedback
di: Kirstein, Frederic, et al.
Pubblicazione: (2024)

Piecing Together Cross-Document Coreference Resolution Datasets: Systematic Dataset Analysis and Unification
di: Zhukova, Anastasia, et al.
Pubblicazione: (2026)

MALLM: Multi-Agent Large Language Models Framework
di: Becker, Jonas, et al.
Pubblicazione: (2025)

Paraphrase Types Elicit Prompt Engineering Capabilities
di: Wahle, Jan Philip, et al.
Pubblicazione: (2024)

Tell me what I need to know: Exploring LLM-based (Personalized) Abstractive Multi-Source Meeting Summarization
di: Kirstein, Frederic, et al.
Pubblicazione: (2024)

Re-FRAME the Meeting Summarization SCOPE: Fact-Based Summarization and Personalization via Questions
di: Kirstein, Frederic, et al.
Pubblicazione: (2025)

Who Watches the Watchmen? Humans Disagree With Translation Metrics on Unseen Domains
di: Schmidt, Finn, et al.
Pubblicazione: (2026)

Text Generation: A Systematic Literature Review of Tasks, Evaluation, and Challenges
di: Becker, Jonas, et al.
Pubblicazione: (2024)

Towards Human Understanding of Paraphrase Types in Large Language Models
di: Meier, Dominik, et al.
Pubblicazione: (2024)

LL-GABR: Energy Efficient Live Video Streaming Using Reinforcement Learning
di: Raman, Adithya, et al.
Pubblicazione: (2024)

Beyond a Single Direction: Chain-of-Thought Disrupts Simple Steering of Refusal
di: Yang, Kia-Jüng, et al.
Pubblicazione: (2026)

QMAVIS: Long Video-Audio Understanding using Fusion of Large Multimodal Models
di: Lin, Zixing, et al.
Pubblicazione: (2026)

SIN-Bench: Tracing Native Evidence Chains in Long-Context Multimodal Scientific Interleaved Literature
di: Ren, Yiming, et al.
Pubblicazione: (2026)

AniME: Adaptive Multi-Agent Planning for Long Animation Generation
di: Zhang, Lisai, et al.
Pubblicazione: (2025)

CiteAssist: A System for Automated Preprint Citation and BibTeX Generation
di: Kaesberg, Lars Benedikt, et al.
Pubblicazione: (2024)

D3: A Massive Dataset of Scholarly Metadata for Analyzing the State of Computer Science Research
di: Wahle, Jan Philip, et al.
Pubblicazione: (2022)

RW-Post: Auditable Evidence-Grounded Multimodal Fact-Checking in the Wild
di: Xu, Danni, et al.
Pubblicazione: (2026)

Enhancing Modality Representation and Alignment for Multimodal Cold-start Active Learning
di: Shen, Meng, et al.
Pubblicazione: (2024)

The Dream Within Huang Long Cave: AI-Driven Interactive Narrative for Family Storytelling and Emotional Reflection
di: Huang, Jiayang, et al.
Pubblicazione: (2025)

Exposing Cross-Modal Consistency for Fake News Detection in Short-Form Videos
di: Tian, Chong, et al.
Pubblicazione: (2026)

Iterative Residual Cross-Attention Mechanism: An Integrated Approach for Audio-Visual Navigation Tasks
di: Zhang, Hailong, et al.
Pubblicazione: (2025)

LLMER: Crafting Interactive Extended Reality Worlds with JSON Data Generated by Large Language Models
di: Chen, Jiangong, et al.
Pubblicazione: (2025)

FairStream: Fair Multimedia Streaming Benchmark for Reinforcement Learning Agents
di: Weil, Jannis, et al.
Pubblicazione: (2024)

TrojanStego: Your Language Model Can Secretly Be A Steganographic Privacy Leaking Agent
di: Meier, Dominik, et al.
Pubblicazione: (2025)

Learning Primitive Embodied World Models: Towards Scalable Robotic Learning
di: Sun, Qiao, et al.
Pubblicazione: (2025)

Multimodal Emotion Recognition by Fusing Video Semantic in MOOC Learning Scenarios
di: Zhang, Yuan, et al.
Pubblicazione: (2024)

Has Multimodal Learning Delivered Universal Intelligence in Healthcare? A Comprehensive Survey
di: Lin, Qika, et al.
Pubblicazione: (2024)

Stage Light is Sequence$^2$: Multi-Light Control via Imitation Learning
di: Zhao, Zijian, 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"
language	"it"
VUFIND_SESSION	"13d103e73c3f9db994d2fb0343e30fe7"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790836454.0282 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "13d103e73c3f9db994d2fb0343e30fe7" ]`]
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; language=it; VUFIND_SESSION=13d103e73c3f9db994d2fb0343e30fe7"
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	"216.73.216.147"
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	"26010"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2510_25668/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2510_25668/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790836454.024
REQUEST_TIME	1790836454

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler