Iterative Foundation Model Fine-Tuning on Multiple Rewards

• URL: http://arxiv.org/abs/2511.00220v1
• Date: Fri, 31 Oct 2025 19:37:16 GMT
• Title: Iterative Foundation Model Fine-Tuning on Multiple Rewards
• Authors: Pouya M. Ghari, Simone Sciabola, Ye Wang,
• Abstract summary: This paper proposes a novel reinforcement learning-based method for fine-tuning foundation models.<n>By employing an iterative fine-tuning strategy across these rewards, our approach generalizes state-of-the-art RL-based methods.
• Score: 12.126070369637551
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Fine-tuning foundation models has emerged as a powerful approach for generating objects with specific desired properties. Reinforcement learning (RL) provides an effective framework for this purpose, enabling models to generate outputs that maximize a given reward function. However, in many applications such as text generation and drug discovery, it can be suboptimal to optimize using a single reward signal, as multiple evaluation criteria are often necessary. This paper proposes a novel reinforcement learning-based method for fine-tuning foundation models using multiple reward signals. By employing an iterative fine-tuning strategy across these rewards, our approach generalizes state-of-the-art RL-based methods. We further provide a theoretical analysis that offers insights into the performance of multi-reward RL fine-tuning. Experimental results across diverse domains including text, biological sequence, and small molecule generation, demonstrate the effectiveness of the proposed algorithm compared to state-of-the-art baselines.

Related papers

• Beyond Monolithic Rewards: A Hybrid and Multi-Aspect Reward Optimization for MLLM Alignment [1.8552770604791606]
  We propose a hybrid reward modeling framework that integrates complementary reward paradigms.<n>We show consistent improvements across different multimodal benchmarks when applying hybrid and multi-aspect reward modeling.<n>Our best performing model in the 3B family achieves an overall average improvement of 9.5% across general and math reasoning tasks.
  arXiv  Detail & Related papers  (2025-10-06T18:53:23Z)
• Delving into RL for Image Generation with CoT: A Study on DPO vs. GRPO [68.44918104224818]
  Autoregressive image generation presents unique challenges distinct from Chain-of-Thought (CoT) reasoning.<n>This study provides the first comprehensive investigation of the GRPO and DPO algorithms in autoregressive image generation.<n>Our findings reveal that GRPO and DPO exhibit distinct advantages, and crucially, that reward models possessing stronger intrinsic generalization capabilities potentially enhance the generalization potential of the applied RL algorithms.
  arXiv  Detail & Related papers  (2025-05-22T17:59:49Z)
• RL-finetuning LLMs from on- and off-policy data with a single algorithm [53.70731390624718]
  We introduce a novel reinforcement learning algorithm (AGRO) for fine-tuning large-language models.<n>AGRO leverages the concept of generation consistency, which states that the optimal policy satisfies the notion of consistency across any possible generation of the model.<n>We derive algorithms that find optimal solutions via the sample-based policy gradient and provide theoretical guarantees on their convergence.
  arXiv  Detail & Related papers  (2025-03-25T12:52:38Z)
• Understanding Reinforcement Learning-Based Fine-Tuning of Diffusion Models: A Tutorial and Review [63.31328039424469]
  This tutorial provides a comprehensive survey of methods for fine-tuning diffusion models to optimize downstream reward functions. We explain the application of various RL algorithms, including PPO, differentiable optimization, reward-weighted MLE, value-weighted sampling, and path consistency learning.
  arXiv  Detail & Related papers  (2024-07-18T17:35:32Z)
• Step-level Value Preference Optimization for Mathematical Reasoning [6.318873143509028]
  We introduce a novel algorithm called Step-level Value Preference Optimization (SVPO) Our method achieves state-of-the-art performance on both in-domain and out-of-domain mathematical reasoning benchmarks.
  arXiv  Detail & Related papers  (2024-06-16T09:06:17Z)
• Provable Reward-Agnostic Preference-Based Reinforcement Learning [61.39541986848391]
  Preference-based Reinforcement Learning (PbRL) is a paradigm in which an RL agent learns to optimize a task using pair-wise preference-based feedback over trajectories. We propose a theoretical reward-agnostic PbRL framework where exploratory trajectories that enable accurate learning of hidden reward functions are acquired.
  arXiv  Detail & Related papers  (2023-05-29T15:00:09Z)
• When to Update Your Model: Constrained Model-based Reinforcement Learning [50.74369835934703]
  We propose a novel and general theoretical scheme for a non-decreasing performance guarantee of model-based RL (MBRL) Our follow-up derived bounds reveal the relationship between model shifts and performance improvement. A further example demonstrates that learning models from a dynamically-varying number of explorations benefit the eventual returns.
  arXiv  Detail & Related papers  (2022-10-15T17:57:43Z)
• A General Framework for Sample-Efficient Function Approximation in Reinforcement Learning [132.45959478064736]
  We propose a general framework that unifies model-based and model-free reinforcement learning. We propose a novel estimation function with decomposable structural properties for optimization-based exploration. Under our framework, a new sample-efficient algorithm namely OPtimization-based ExploRation with Approximation (OPERA) is proposed.
  arXiv  Detail & Related papers  (2022-09-30T17:59:16Z)
• An intelligent algorithmic trading based on a risk-return reinforcement learning algorithm [0.0]
  This scientific paper propose a novel portfolio optimization model using an improved deep reinforcement learning algorithm. The proposed algorithm is based on actor-critic architecture, in which the main task of critical network is to learn the distribution of portfolio cumulative return. A multi-process method is used, called Ape-x, to accelerate the speed of deep reinforcement learning training.
  arXiv  Detail & Related papers  (2022-08-23T03:20:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.