Cover Image

Self-Improvement as Coherence Optimization: A Theoretical Account

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Qiu, Tianyi, Ismail, Ahmed Hani, He, Zhonghao, Feng, Shi
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Martingale Score: An Unsupervised Metric for Bayesian Rationality in LLM Reasoning
by: He, Zhonghao, et al.
Published: (2025)

A Theoretical Understanding of Chain-of-Thought: Coherent Reasoning and Error-Aware Demonstration
by: Cui, Yingqian, et al.
Published: (2024)

The Lock-in Hypothesis: Stagnation by Algorithm
by: Qiu, Tianyi Alex, et al.
Published: (2025)

Calibrated Surprise: An Information-Theoretic Account of Creative Quality
by: Zou, Bo, et al.
Published: (2026)

Mitigating Tail Narrowing in LLM Self-Improvement via Socratic-Guided Sampling
by: Ding, Yiwen, et al.
Published: (2024)

SAHOO: Safeguarded Alignment for High-Order Optimization Objectives in Recursive Self-Improvement
by: Sahoo, Subramanyam, et al.
Published: (2026)

TTSR: Test-Time Self-Reflection for Continual Reasoning Improvement
by: He, Haoyang, et al.
Published: (2026)

Self-Trained Verification for Training- and Test-Time Self-Improvement
by: Wu, Chen Henry, et al.
Published: (2026)

Self-Improvement in Language Models: The Sharpening Mechanism
by: Huang, Audrey, et al.
Published: (2024)

Latent Principle Discovery for Language Model Self-Improvement
by: Ramji, Keshav, et al.
Published: (2025)

Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains
by: Subramaniam, Vighnesh, et al.
Published: (2025)

Theoretical Benefit and Limitation of Diffusion Language Model
by: Feng, Guhao, et al.
Published: (2025)

You Didn't Have to Say It like That: Subliminal Learning from Faithful Paraphrases
by: Gisler, Isaia, et al.
Published: (2026)

Build, Judge, Optimize: A Blueprint for Continuous Improvement of Multi-Agent Consumer Assistants
by: Herrera, Alejandro Breen, et al.
Published: (2026)

Benefits and Pitfalls of Reinforcement Learning for Language Model Planning: A Theoretical Perspective
by: Wang, Siwei, et al.
Published: (2025)

ROPO: Robust Preference Optimization for Large Language Models
by: Liang, Xize, et al.
Published: (2024)

Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences
by: Rosset, Corby, et al.
Published: (2024)

LogicTree: Structured Proof Exploration for Coherent and Rigorous Logical Reasoning with Large Language Models
by: He, Kang, et al.
Published: (2025)

Representative Social Choice: From Learning Theory to AI Alignment
by: Qiu, Tianyi
Published: (2024)

Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement
by: Yang, An, et al.
Published: (2024)

Exploration-Driven Policy Optimization in RLHF: Theoretical Insights on Efficient Data Utilization
by: Du, Yihan, et al.
Published: (2024)

Stepwise Guided Policy Optimization: Coloring your Incorrect Reasoning in GRPO
by: Chen, Peter, et al.
Published: (2025)

Self-Consistency Preference Optimization
by: Prasad, Archiki, et al.
Published: (2024)

Self-Supervised Prompt Optimization
by: Xiang, Jinyu, et al.
Published: (2025)

Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement
by: Wang, Xiyao, et al.
Published: (2024)

Self-Rewarding PPO: Aligning Large Language Models with Demonstrations Only
by: Zhang, Qingru, et al.
Published: (2025)

BookSQL: A Large Scale Text-to-SQL Dataset for Accounting Domain
by: Kumar, Rahul, et al.
Published: (2024)

FairPy: A Toolkit for Evaluation of Prediction Biases and their Mitigation in Large Language Models
by: Viswanath, Hrishikesh, et al.
Published: (2023)

Beyond the Last Answer: Your Reasoning Trace Uncovers More than You Think
by: Hammoud, Hasan Abed Al Kader, et al.
Published: (2025)

Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation
by: Zelikman, Eric, et al.
Published: (2023)

From Words to Actions: Unveiling the Theoretical Underpinnings of LLM-Driven Autonomous Systems
by: He, Jianliang, et al.
Published: (2024)

A Survey on LoRA of Large Language Models
by: Mao, Yuren, et al.
Published: (2024)

TSO: Self-Training with Scaled Preference Optimization
by: Chen, Kaihui, et al.
Published: (2024)

Policy Improvement using Language Feedback Models
by: Zhong, Victor, et al.
Published: (2024)

QualEval: Qualitative Evaluation for Model Improvement
by: Murahari, Vishvak, et al.
Published: (2023)

Self-Play Preference Optimization for Language Model Alignment
by: Wu, Yue, et al.
Published: (2024)

Peering Inside the Black Box: Uncovering LLM Errors in Optimization Modelling through Component-Level Evaluation
by: Refai, Dania, et al.
Published: (2025)

Learning to Align, Aligning to Learn: A Unified Approach for Self-Optimized Alignment
by: Wang, Haowen, et al.
Published: (2025)

On the Role of Preference Variance in Preference Optimization
by: Guo, Jiacheng, et al.
Published: (2025)

A Theoretical Perspective for Speculative Decoding Algorithm
by: Yin, Ming, et al.
Published: (2024)