Cover Image

Debate as Reward: A Multi-Agent Reward System for Scientific Ideation via RL Post-Training

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Salimi, Moein, Mohtasham, Babak Hosseini, Aghakasiri, Amin, Naieni, Mahdi, Qeysarbeigi, Amir Hossein, Nazer, Mohammad Masih Shalchian, Azar, Zahra, Siavoshani, Mahdi Jafari, Rohban, Mohammad Hossein
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Generalization and Membership Inference Attack a Practical Perspective
by: Rahmani, Fateme, et al.
Published: (2026)

Wiring the 'Why': A Unified Taxonomy and Survey of Abductive Reasoning in LLMs
by: Salimi, Moein, et al.
Published: (2026)

Differentially Private Machine Learning-powered Combinatorial Auction Design
by: Jamshidi, Arash, et al.
Published: (2024)

Toward IIT-Inspired Consciousness in LLMs: A Reward-Based Learning Framework
by: Akbari, Hamid Reza, et al.
Published: (2026)

Extended Deep Submodular Functions
by: Hosseini, Seyed Mohammad, et al.
Published: (2024)

Networked Information Aggregation for Binary Classification
by: Bateni, MohammadHossein, et al.
Published: (2026)

A Class of Subadditive Information Measures and their Applications
by: Abin, Hamidreza, et al.
Published: (2026)

Killing it with Zero-Shot: Adversarially Robust Novelty Detection
by: Mirzaei, Hossein, et al.
Published: (2025)

A Hybrid TGN-SEAL Model for Dynamic Graph Link Prediction
by: Sajadi, Nafiseh Sadat, et al.
Published: (2026)

Revolutionizing Traffic Management with AI-Powered Machine Vision: A Step Toward Smart Cities
by: DolatAbadi, Seyed Hossein Hosseini, et al.
Published: (2025)

Universal Novelty Detection Through Adaptive Contrastive Learning
by: Mirzaei, Hossein, et al.
Published: (2024)

Erased but Exploitable: Black-box Embedding-Aware Prompting Against Unlearned Text-to-Image Diffusion Models
by: Koma, Arian Komaei, et al.
Published: (2026)

CARINOX: Inference-time Scaling with Category-Aware Reward-based Initial Noise Optimization and Exploration
by: Kasaei, Seyed Amir, et al.
Published: (2025)

Evaluating the effectiveness of concrete and metal shields in photoneutron reduction: A Monte Carlo study
by: Jahanimehr, Mohammad Hossein, et al.
Published: (2025)

Hallucination as an Upper Bound: A New Perspective on Text-to-Image Evaluation
by: Kasaei, Seyed Amir, et al.
Published: (2025)

Advancing Retrieval-Augmented Generation for Persian: Development of Language Models, Comprehensive Benchmarks, and Best Practices for Optimization
by: Hosseinbeigi, Sara Bourbour, et al.
Published: (2025)

Resilient Integrated Guidance and Control for Long‐Range High‐Speed Aerospace Vehicles Using LSTM‐Enhanced ACHSOMC in GNSS‐Denied Environments
by: Mohammad Mahdi Soori, et al.
Published: (2026)

Mitigating Spurious Negative Pairs for Robust Industrial Anomaly Detection
by: Mirzaei, Hossein, et al.
Published: (2025)

Influence of Biomass‐Modified Asphalt Binder on Rutting Resistance
by: Mahyar Arabani, et al.
Published: (2024)

Enhanced TNSA Ion Acceleration via Optical Confinement and Geometric Plasma Focusing in Annular Sector Targets
by: Rezaei-Pandari, Mohammad, et al.
Published: (2026)

How Does Virtual Reality Technology Affect Suicidal Ideation in Society?
by: Mohammad Hossein Ronaghi, et al.
Published: (2024)

CRISPR: Ensemble Model
by: Rostami, Mohammad, et al.
Published: (2024)

Real-Time Knee Angle Prediction Using EMG and Kinematic Data with an Attention-Based CNN-LSTM Network and Transfer Learning Across Multiple Datasets
by: Mollahossein, Mojtaba, et al.
Published: (2025)

Old wine in old glasses: Comparing computational and qualitative methods in identifying incivility on Persian Twitter during the #MahsaAmini movement
by: Kermani, Hossein, et al.
Published: (2026)

Erasure or Erosion? Evaluating Compositional Degradation in Unlearned Text-To-Image Diffusion Models
by: Koma, Arian Komaei, et al.
Published: (2026)

Scientific profiles in the field of children obesity
by: Mohammad-Hossein Biglu
Published: (2016)

OTClean: Data Cleaning for Conditional Independence Violations using Optimal Transport
by: Pirhadi, Alireza, et al.
Published: (2024)

Oral immunotherapy for Helicobacter pylori: Can it be trusted? A systematic review
by: Mohammad Hossein Peypar, et al.
Published: (2024)

The Silent Judge: Unacknowledged Shortcut Bias in LLM-as-a-Judge
by: Marioriyad, Arash, et al.
Published: (2025)

Deciphering the Role of Representation Disentanglement: Investigating Compositional Generalization in CLIP Models
by: Abbasi, Reza, et al.
Published: (2024)

Language Plays a Pivotal Role in the Object-Attribute Compositional Generalization of CLIP
by: Abbasi, Reza, et al.
Published: (2024)

All Centers Are at most a Few Tokens Apart: Knowledge Distillation with Domain Invariant Prompt Tuning
by: Ezzati, Amir Mohammad, et al.
Published: (2025)

SR-Reward: Taking The Path More Traveled
by: Azad, Seyed Mahdi B., et al.
Published: (2025)

Scanning Trojaned Models Using Out-of-Distribution Samples
by: Mirzaei, Hossein, et al.
Published: (2025)

MAGE-ID: A Multimodal Generative Framework for Intrusion Detection Systems
by: Loodaricheh, Mahdi Arab, et al.
Published: (2025)

Development of a Transit-Time Ultrasonic Flow Measurement System for Partially Filled Pipes: Incorporating Flow Profile Correction Factor and Real-Time Clogging Detection
by: Mesmarian, Mohammadhadi, et al.
Published: (2025)

Enhancing Scientific Literature Chatbots with Retrieval-Augmented Generation: A Performance Evaluation of Vector and Graph-Based Systems
by: Ghanadian, Hamideh, et al.
Published: (2026)

HyCoVAD: A Hybrid SSL-LLM Model for Complex Video Anomaly Detection
by: Hemmatyar, Mohammad Mahdi, et al.
Published: (2025)

PersianRAG: A Retrieval-Augmented Generation System for Persian Language
by: Hosseini, Hossein, et al.
Published: (2024)

SORA: Free Second-Order Attacks in Fast Adversarial Training
by: Teymourian, Mazdak, et al.
Published: (2026)