A three-paradigm taxonomy (feature-based, auxiliary-based, and policy-based) based on the functional role of LLMs within the RL pipeline is proposed, which provides superior scalability and stability, though often at the expense of representational depth.
Abstract
The integration of Large Language Models (LLMs) with Reinforcement Learning (RL) for financial decision-making has grown rapidly in recent years, yet the literature remains fragmented and lacks systematic comparison across methods. In this survey we analyze 34 core studies (2023–2026), selected through a multi-stage process involving 84 initial candidates and 46 full-text reviews, and propose a three-paradigm taxonomy (feature-based, auxiliary-based, and policy-based) based on the functional role of LLMs within the RL pipeline. Analysis of these integration paradigms reveals an emergent architectural trade-off: while tighter policy-based coupling theoretically offers deeper contextual reasoning, it frequently introduces significant computational overhead and training instability. Conversely, simpler feature-based integration provides superior scalability and stability, though often at the expense of representational depth. Given the current benchmark fragmentation, the reported performance gains across these studies remain difficult to validate universally across different asset classes. Critical gaps identified include the insufficient handling of data leakage and look-ahead bias, standardized benchmarks, and limited alignment with regulatory frameworks such as MiFID II and the EU AI Act.
This work proposes ARMOR (Anchor Rollout and Mixed Optimization for RL), a framework that shifts the paradigm from passive penalty to active sample stabilization, enabling sustained performance improvements over extended training horizons.
Kexin Huang, Junkang Wu, Jinda Lu et al.· arXiv.org· 0 citations
Model merging plays a crucial role in consolidating multiple specialized models into a single, unified model, especially in the era of large language models (LLMs). Recent research has primarily focused on developing strategies to enhance merging performance with the trained models, while the impact of training paradigms, such as supervised fine-tuning (SFT) and reinforcement learning (RL), on the effectiveness of model merging remains underexplored. In this study, we systematically explore the merging behavior of RL-trained LLMs compared to those trained with traditional SFT. Through comprehensive evaluations across five representative tasks, we find that RL significantly reduces task conflicts and results in less performance degradation after merging, making RL-trained models particularly well-suited for this process. To unearth the reasons behind the superior suitability of RL for model merging, we conduct extensive empirical experiments and theoretical analyses. Our findings highlight three key factors: (1) On-policy training data in RL control the gradient updates in a smaller magnitude, reducing the risk of overwriting existing knowledge for other tasks in the model. (2) The RL optimization objective, which favors ``\textit{enough is as good as a feast}", progressively reduces the magnitude and the number of conflict parameter updates as the model converges. (3) Joint optimization of positive and negative examples in RL steers the model towards an unbiased task-specific parameter subspace, ensuring robust performance while further preventing parameter conflicts.
This paper highlights the transition from static prediction to sequential decision-making, emphasizing RL’s strengths in long-term reward optimization and interaction modeling, and LLMs’ advantages in semantic understanding and reasoning.
Xi-Qian Lu· Computers and artificial int...· 0 citations
Reinforcement learning with verifiable rewards (RLVR) is rapidly advancing the reasoning capabilities of language models, yet the optimization layer that converts reward feedback into weight-space updates remains poorly understood. Building on our prior analysis (Zhu et al., 2025), we study this missing layer through the singular structure of model weights and identify spectral inheritance: RLVR can reuse the base model's weight spectra while acquiring new behavior through changes in the associated input and output singular frames. We operationalize spectral inheritance as Isospectral Optimization (ISO), an RLVR-native, fixed-spectrum optimization framework with complementary offline and online instantiations. Offline, ISO-Merger combines the frame changes of shared-base specialists into a single fixed-spectrum model, requiring no post-merge data, rollouts, gradient updates, or on-policy distillation (OPD). It recovers complementary specialist capabilities and achieves the strongest aggregate performance among the compared data-free merging methods. Online, ISO-Optimizer applies a chosen base optimizer, including AdamW and Muon, to the frame variables while keeping the base spectra fixed. Across reasoning and coding tasks ranging from 1.5B to 8B parameters, ISO-Optimizer improves accuracy in the reported runs and reaches matched scores with substantially fewer training steps. On Qwen3-8B-Base, AdamW reaches an aggregate accuracy of 0.495 after 270 training steps. ISO-AdamW reaches the same accuracy after only 100 training steps and improves further to 0.509 after 210 training steps. Together, ISO offers a concrete answer to RLVR's missing optimization layer: rather than inheriting pre-training optimization wholesale, design post-training around the structure of reward-driven adaptation: inherit the spectrum, optimize the frames.
This work empirically study the potential of outer prefixes, revealing the mechanism of the impact of distributional discrepancy to the exploration dynamics in RLVR training and efficiently mitigates entropy collapse without requiring additional SFT, intricate reward designs, or complex prompting.
Xin Shen, Huishuai Zhang, Peng Li et al.· 0 citations
A Large Language Model-enhanced Autonomous Reinforcement Learning Penetration Testing framework that leverages the domain knowledge embedded in a Large Language Model to perform tactical planning, thereby pruning the original action space into a compact set of candidate actions.
