Related papers: Leader Reward for POMO-Based Neural Combinatorial …

Fine-tuning Large Language Models (LLMs) with first-order methods like back-propagation is computationally intensive. Zeroth-Order (ZO) optimisation uses function evaluations instead of gradients, reducing memory usage, but suffers from…

Combinatorial optimization (CO) problems, central to operation research and theoretical computer science, present significant computational challenges due to their NP-hard nature. While large language models (LLMs) have emerged as promising…

Model-based algorithms, which learn a dynamics model from logged experience and perform some sort of pessimistic planning under the learned model, have emerged as a promising paradigm for offline reinforcement learning (offline RL).…

Language models must now generalize out of the box to novel environments and work inside inference-scaling search procedures, such as AlphaEvolve, that select rollouts with a variety of task-specific reward functions. Unfortunately, the…

Multi-agent reinforcement learning (MARL) faces two critical bottlenecks distinct from single-agent RL: credit assignment in cooperative tasks and partial observability of environmental states. We propose LERO, a framework integrating Large…

Aligning large language models with pointwise absolute rewards has so far required online, on-policy algorithms such as PPO and GRPO. In contrast, simpler methods that can leverage offline or off-policy data, such as DPO and REBEL, are…

The optimal objective is a fundamental aspect of reinforcement learning (RL), as it determines how policies are evaluated and optimized. While total return maximization is the ideal objective in RL, discounted return maximization is the…

Combinatorial optimization problems (COPs) on the graph with real-life applications are canonical challenges in Computer Science. The difficulty of finding quality labels for problem instances holds back leveraging supervised learning…

While Retrieval-Augmented Generation (RAG) has exhibited promise in utilizing external knowledge, its generation process heavily depends on the quality and accuracy of the retrieved context. Large language models (LLMs) struggle to evaluate…

Group-Relative Policy Optimization (GRPO) has emerged as an efficient paradigm for aligning Large Language Models (LLMs), yet its efficacy is primarily confined to domains with verifiable ground truths. Extending GRPO to open-domain…

Large Language Models (LLMs) can generate code from natural language, but their performance is highly sensitive to prompt formulation. We propose a reinforcement-learning-based framework that models prompt refinement as a sequential…

Finding a high-quality feasible solution to a combinatorial optimization (CO) problem in a limited time is challenging due to its discrete nature. Recently, there has been an increasing number of machine learning (ML) methods for addressing…

Finding the optimal solution is often the primary goal in combinatorial optimization (CO). However, real-world applications frequently require diverse solutions rather than a single optimum, particularly in two key scenarios. The first…

Reinforcement learning (RL) has shown to be a valuable tool in training neural networks for autonomous motion planning. The application of RL to a specific problem is dependent on a reward signal to quantify how good or bad a certain action…

Deep reinforcement learning (DRL) has been used to learn effective heuristics for solving complex combinatorial optimisation problem via policy networks and have demonstrated promising performance. Existing works have focused on solving…

Large language models (LLMs) have recently advanced in reasoning when optimized with reinforcement learning (RL) under verifiable rewards. Existing methods primarily rely on outcome-based supervision to strengthen internal LLM reasoning,…

Traditional preference tuning methods for LLMs/Visual Generative Models often rely solely on reward model labeling, which can be opaque, offer limited insights into the rationale behind preferences, and are prone to issues such as reward…

Recent advancements in Multimodal Large Language Models (MLLMs) have incentivized models to ``think with images'' by actively invoking visual tools during multi-turn reasoning. The common Reinforcement Learning (RL) practice of relying on…

This work studies reinforcement learning (RL) in the context of multi-period supply chains subject to constraints, e.g., on production and inventory. We introduce Distributional Constrained Policy Optimization (DCPO), a novel approach for…

Large Reasoning Models (LRMs) achieve explicit chain-of-thought expansion by imitating deep thinking behaviors of humans, demonstrating excellent performance in complex task scenarios. However, the deep-thinking mode often leads to…