Cover Image

The Majority is not always right: RL training for solution aggregation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhao, Wenting, Aggarwal, Pranjal, Saha, Swarnadeep, Celikyilmaz, Asli, Weston, Jason, Kulikov, Ilia
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

OptimalThinkingBench: Evaluating Over and Underthinking in LLMs
by: Aggarwal, Pranjal, et al.
Published: (2025)

Branch-Solve-Merge Improves Large Language Model Evaluation and Generation
by: Saha, Swarnadeep, et al.
Published: (2023)

Adaptive Decoding via Latent Preference Optimization
by: Dhuliawala, Shehzaad, et al.
Published: (2024)

J1: Incentivizing Thinking in LLM-as-a-Judge via Reinforcement Learning
by: Whitehouse, Chenxi, et al.
Published: (2025)

Reasoning over mathematical objects: on-policy reward modeling and test time aggregation
by: Aggarwal, Pranjal, et al.
Published: (2026)

Hybrid Reinforcement: When Reward Is Sparse, It's Better to Be Dense
by: Tao, Leitian, et al.
Published: (2025)

Distilling System 2 into System 1
by: Yu, Ping, et al.
Published: (2024)

Learning to Plan & Reason for Evaluation with Thinking-LLM-as-a-Judge
by: Saha, Swarnadeep, et al.
Published: (2025)

Bridging Offline and Online Reinforcement Learning for LLMs
by: Lanchantin, Jack, et al.
Published: (2025)

SPICE: Self-Play In Corpus Environments Improves Reasoning
by: Liu, Bo, et al.
Published: (2025)

Diverse Preference Optimization
by: Lanchantin, Jack, et al.
Published: (2025)

Following Length Constraints in Instructions
by: Yuan, Weizhe, et al.
Published: (2024)

Jointly Reinforcing Diversity and Quality in Language Model Generations
by: Li, Tianjian, et al.
Published: (2025)

Open-Domain Text Evaluation via Contrastive Distribution Methods
by: Lu, Sidi, et al.
Published: (2023)

Learning to Reason for Factuality
by: Chen, Xilun, et al.
Published: (2025)

The Era of Real-World Human Interaction: RL from User Conversations
by: Jin, Chuanyang, et al.
Published: (2025)

RLCD: Reinforcement Learning from Contrastive Distillation for Language Model Alignment
by: Yang, Kevin, et al.
Published: (2023)

L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning
by: Aggarwal, Pranjal, et al.
Published: (2025)

reWordBench: Benchmarking and Improving the Robustness of Reward Models with Transformed Inputs
by: Wu, Zhaofeng, et al.
Published: (2025)

Learning to Interrupt in Language-based Multi-agent Communication
by: Wang, Danqing, et al.
Published: (2026)

Self-Improving Pretraining: using post-trained models to pretrain better models
by: Tan, Ellen Xiaoqing, et al.
Published: (2026)

CoT-Self-Instruct: Building high-quality synthetic prompts for reasoning and non-reasoning tasks
by: Yu, Ping, et al.
Published: (2025)

LLM Pretraining with Continuous Concepts
by: Tack, Jihoon, et al.
Published: (2025)

NaturalThoughts: Selecting and Distilling Reasoning Traces for General Reasoning Tasks
by: Li, Yang, et al.
Published: (2025)

NaturalReasoning: Reasoning in the Wild with 2.8M Challenging Questions
by: Yuan, Weizhe, et al.
Published: (2025)

Post-training an LLM for RAG? Train on Self-Generated Demonstrations
by: Finlayson, Matthew, et al.
Published: (2025)

ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs
by: Chen, Justin Chih-Yao, et al.
Published: (2023)

Don't throw away your value model! Generating more preferable text with Value-Guided Monte-Carlo Tree Search decoding
by: Liu, Jiacheng, et al.
Published: (2023)

MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models
by: Chen, Justin Chih-Yao, et al.
Published: (2024)

StepWiser: Stepwise Generative Judges for Wiser Reasoning
by: Xiong, Wei, et al.
Published: (2025)

Self-Taught Evaluators
by: Wang, Tianlu, et al.
Published: (2024)

MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for Reasoning
by: Chen, Justin Chih-Yao, et al.
Published: (2024)

Agentic-R1: Distilled Dual-Strategy Reasoning
by: Du, Weihua, et al.
Published: (2025)

Explore Theory of Mind: Program-guided adversarial data generation for theory of mind reasoning
by: Sclar, Melanie, et al.
Published: (2024)

Strong hallucinations from negation and how to fix them
by: Asher, Nicholas, et al.
Published: (2024)

RESTRAIN: From Spurious Votes to Signals -- Self-Driven RL with Self-Penalization
by: Yu, Zhaoning, et al.
Published: (2025)

System-Level Natural Language Feedback
by: Yuan, Weizhe, et al.
Published: (2023)

SSA: Improving Performance With a Better Scoring Function
by: Naim, Omar, et al.
Published: (2025)

Multi-Token Attention
by: Golovneva, Olga, et al.
Published: (2025)

Resprompt: Residual Connection Prompting Advances Multi-Step Reasoning in Large Language Models
by: Jiang, Song, et al.
Published: (2023)