Cover Image

Mid-Training with Self-Generated Data Improves Reinforcement Learning in Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	RRV, Aswin, Dineen, Jacob, Handa, Divij, Parmar, Mihir, Zhou, Ben, Mishra, Swaroop, Baral, Chitta
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ThinkTuning: Instilling Cognitive Reflections without Distillation
by: RRV, Aswin, et al.
Published: (2025)

GuidedSampling: Steering LLMs Towards Diverse Candidate Solutions at Inference-Time
by: Handa, Divij, et al.
Published: (2025)

Don't Blame the Annotator: Bias Already Starts in the Annotation Instructions
by: Parmar, Mihir, et al.
Published: (2022)

When "Competency" in Reasoning Opens the Door to Vulnerability: Jailbreaking LLMs via Novel Complex Ciphers
by: Handa, Divij, et al.
Published: (2024)

Vocabulary Dropout for Curriculum Diversity in LLM Co-Evolution
by: Dineen, Jacob, et al.
Published: (2026)

PHANTOM RECALL: When Familiar Puzzles Fool Smart Models
by: Mukhopadhyay, Souradeep, et al.
Published: (2025)

ToW: Thoughts of Words Improve Reasoning in Large Language Models
by: Xu, Zhikun, et al.
Published: (2024)

Step-by-Step Reasoning to Solve Grid Puzzles: Where do LLMs Falter?
by: Tyagi, Nemika, et al.
Published: (2024)

Polymath: A Challenging Multi-modal Mathematical Reasoning Benchmark
by: Gupta, Himanshu, et al.
Published: (2024)

ActionReasoningBench: Reasoning about Actions with and without Ramification Constraints
by: Handa, Divij, et al.
Published: (2024)

TarGEN: Targeted Data Generation with Large Language Models
by: Gupta, Himanshu, et al.
Published: (2023)

PLAN-TUNING: Post-Training Language Models to Learn Step-by-Step Planning for Complex Problem Solving
by: Parmar, Mihir, et al.
Published: (2025)

Chaos with Keywords: Exposing Large Language Models Sycophantic Hallucination to Misleading Keywords and Evaluating Defense Strategies
by: RRV, Aswin, et al.
Published: (2024)

Hypothesis Generation for Materials Discovery and Design Using Goal-Driven and Constraint-Guided LLM Agents
by: Kumbhar, Shrinidhi, et al.
Published: (2025)

Triple Preference Optimization: Achieving Better Alignment using a Single Step Optimization
by: Saeidi, Amir, et al.
Published: (2024)

Multi-LogiEval: Towards Evaluating Multi-Step Logical Reasoning Ability of Large Language Models
by: Patel, Nisarg, et al.
Published: (2024)

QA-LIGN: Aligning LLMs through Constitutionally Decomposed QA
by: Dineen, Jacob, et al.
Published: (2025)

LogicBench: Towards Systematic Evaluation of Logical Reasoning Ability of Large Language Models
by: Parmar, Mihir, et al.
Published: (2024)

Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Models
by: Luo, Man, et al.
Published: (2023)

PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solving
by: Parmar, Mihir, et al.
Published: (2025)

OptAgent: Optimizing Query Rewriting for E-commerce via Multi-Agent Simulation
by: Handa, Divij, et al.
Published: (2025)

Investigating the Shortcomings of LLMs in Step-by-Step Legal Reasoning
by: Mishra, Venkatesh, et al.
Published: (2025)

SMART SLM: Structured Memory and Reasoning Transformer, A Small Language Model for Accurate Document Assistance
by: Dudeja, Divij, et al.
Published: (2025)

Large Language Models Cannot Self-Correct Reasoning Yet
by: Huang, Jie, et al.
Published: (2023)

Cutting Through the Noise: Boosting LLM Performance on Math Word Problems
by: Anantheswaran, Ujjwala, et al.
Published: (2024)

BOW: Reinforcement Learning for Bottlenecked Next Word Prediction
by: Shen, Ming, et al.
Published: (2025)

Skill Reuse as Compression in Agentic RL
by: Xu, Zhikun, et al.
Published: (2026)

MMTABREAL: Real-World Benchmark for Multimodal Table Understanding
by: Titiya, Prasham, et al.
Published: (2025)

ArenaBencher: Automatic Benchmark Evolution via Multi-Model Competitive Evaluation
by: Liu, Qin, et al.
Published: (2025)

Self-Discover: Large Language Models Self-Compose Reasoning Structures
by: Zhou, Pei, et al.
Published: (2024)

UnSeenTimeQA: Time-Sensitive Question-Answering Beyond LLMs' Memorization
by: Uddin, Md Nayem, et al.
Published: (2024)

Reinforcement Learning for Self-Improving Agent with Skill Library
by: Wang, Jiongxiao, et al.
Published: (2025)

Improving Automatic Summarization of Radiology Reports through Mid-Training of Large Language Models
by: Lyu, Mengxian, et al.
Published: (2026)

Interpretable Vital Sign Forecasting with Model Agnostic Attention Maps
by: Liu, Yuwei, et al.
Published: (2024)

Prompted Policy Search: Reinforcement Learning through Linguistic and Numerical Reasoning in LLMs
by: Zhou, Yifan, et al.
Published: (2025)

Self-Questioning Language Models
by: Chen, Lili, et al.
Published: (2025)

Learning to Better Search with Language Models via Guided Reinforced Self-Training
by: Moon, Seungyong, et al.
Published: (2024)

BuildBench: Benchmarking LLM Agents on Compiling Real-World Open-Source Software
by: Zhang, Zehua, et al.
Published: (2025)

SeRL: Self-Play Reinforcement Learning for Large Language Models with Limited Data
by: Fang, Wenkai, et al.
Published: (2025)

Low-Rank Adaptation of Time Series Foundational Models for Out-of-Domain Modality Forecasting
by: Gupta, Divij, et al.
Published: (2024)