Related papers: LogGuardQ: A Cognitive-Enhanced Reinforcement Lear…
Reinforcement Learning can be applied to various tasks, and environments. Many of these environments have a similar shared structure, which can be exploited to improve RL performance on other tasks. Transfer learning can be used to take…
Reinforcement learning (RL) has emerged as the predominant paradigm for training large language model (LLM)-based AI agents. However, existing backbone RL algorithms lack verified convergence guarantees in agentic scenarios, especially in…
Search-augmented reasoning agents interleave multi-step reasoning with external information retrieval, but uncontrolled retrieval often leads to redundant evidence, context saturation, and unstable learning. Existing approaches rely on…
We study reinforcement learning in infinite-horizon discounted Markov decision processes with continuous state spaces, where data are generated online from a single trajectory under a Markovian behavior policy. To avoid maintaining an…
While Bayesian-based exploration often demonstrates superior empirical performance compared to bonus-based methods in model-based reinforcement learning (RL), its theoretical understanding remains limited for model-free settings. Existing…
Reinforcement learning (RL) is widely used for post-training large language models (LLMs) in code editing, where group-relative methods, such as GRPO, are popular due to their critic-free and normalized advantage estimation. However, in…
Contemporary DevSecOps pipelines have to deal with the evolution of security in an ever-continuously integrated and deployed environment. Existing methods,such as rule-based intrusion detection and static vulnerability scanning, are…
Anomaly Detection (AD) focuses on detecting samples that differ from the standard pattern, making it a vital tool in process control. Logical anomalies may appear visually normal yet violate predefined constraints on object presence,…
Deep Q Network (DQN) is a very successful algorithm, yet the inherent problem of reinforcement learning, i.e. the exploit-explore balance, remains. In this work, we introduce entropy regularization into DQN and propose SQN. We find that the…
Recent works have demonstrated the effectiveness of reinforcement learning (RL)-based post-training for enhancing the reasoning capabilities of large language models (LLMs). In particular, Group Relative Policy Optimization (GRPO) has shown…
Security applications are increasingly relying on large language models (LLMs) for cyber threat detection; however, their opaque reasoning often limits trust, particularly in decisions that require domain-specific cybersecurity knowledge.…
Retriever-augmented generation (RAG) has become a widely adopted approach for enhancing the factual accuracy of large language models (LLMs). While current benchmarks evaluate the performance of RAG methods from various perspectives, they…
The success of Deepseek-R1 has drawn the LLM community's attention to reinforcement learning (RL) methods like GRPO. However, such rule-based 0/1 outcome reward methods lack the capability to regulate the intermediate reasoning processes…
Deep Reinforcement Learning (RL) has considerably advanced over the past decade. At the same time, state-of-the-art RL algorithms require a large computational budget in terms of training time to converge. Recent work has started to…
The exponential growth of data-intensive applications has placed unprecedented demands on modern storage systems, necessitating dynamic and efficient optimization strategies. Traditional heuristics employed for storage performance…
This paper presents CADL (Cognitive-Adaptive Deception Layer), an adaptive deception framework achieving 99.88% detection rate with 0.13% false positive rate on the CICIDS2017 dataset. The framework employs ensemble machine learning (Random…
We introduce Coarse Q-learning (CQL), a reinforcement-learning model for bandit problems with stochastically varying menus. Alternatives are exogenously partitioned into similarity classes, and feedback from sampled alternatives is pooled…
Deep reinforcement learning (DRL) has demonstrated impressive performance in various gaming simulators and real-world applications. In practice, however, a DRL agent may receive faulty observation by abrupt interferences such as black-out,…
Proximal Policy Optimisation (PPO) is an established and effective policy gradient algorithm used for Language Model Reinforcement Learning from Human Feedback (LM-RLHF). PPO performs well empirically but has a heuristic motivation and…
We present a comprehensive framework for enhancing Retrieval-Augmented Generation (RAG) systems through dynamic retrieval strategies and reinforcement fine-tuning. This approach significantly improves large language models on…