HAMMER: Hamiltonian Curiosity Augmented Large Language Model Reinforcement

Ming Yang, Xiaofan Li, Zhiyuan Ma, Dengliang Shi, Jintao Du +2 more
9/25/2025
cs.LGcs.AIcs.CL

No confident code implementation found for this paper. 2 possible matches can be shown below.

Abstract

Recent curriculum reinforcement learning for large language models (LLMs) typically rely on difficulty-based annotations for data filtering and ordering. However, such methods suffer from local optimization, where continual training on simple samples in the early steps can cause the policy to lose its exploration. We propose a novel schema, namely Hamiltonian curiosity augmented large language model reinforcement (HAMMER), that transfers diversity metrics, commonly used in dataset evaluation, into the dynamic reinforcement learning procedure, where training samples are ordered via a minimum-semantic Hamiltonian path making the initial training retrain more exploration. From a theoretical perspective of generalization bounds, diversity-driven ordering facilitates stable convergence. Empirical evaluations indicate that HAMMER stimulates model "curiosity" and consistently achieves a 3% to 4% average accuracy gain across diverse inference benchmark.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 2 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models

86% match2025

Efficient Reinforcement Learning for Large Language Models with Intrinsic Exploration

85% match2025

Post-training Large Language Models for Diverse High-Quality Responses

85% match2025

Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training

85% match2025

Reward Guidance for Reinforcement Learning Tasks Based on Large Language Models: The LMGT Framework

84% match2024

Is a Good Foundation Necessary for Efficient Reinforcement Learning? The Computational Role of the Base Model in Exploration

84% match2025

Cite this paper

@article{yang2025hammer,
  title  = {HAMMER: Hamiltonian Curiosity Augmented Large Language Model Reinforcement},
  author = {Ming Yang and Xiaofan Li and Zhiyuan Ma and Dengliang Shi and Jintao Du and Yu Cheng and Weiguo Zheng},
  year   = {2025},
  eprint = {2509.25240},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2509.25240v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2509.25240.svg)](https://codeofpaper.com/paper/2509.25240)

Discussion