Related papers: READY: Reward Discovery for Meta-Black-Box Optimiz…

There has been significant progress in deep reinforcement learning (RL) in recent years. Nevertheless, finding suitable hyperparameter configurations and reward functions remains challenging even for experts, and performance heavily relies…

Improving the multi-step reasoning ability of Large Language Models (LLMs) is a critical yet challenging task. The dominant paradigm, outcome-supervised reinforcement learning (RLVR), rewards only correct final answers, often propagating…

Large Reasoning Models (LRMs) have achieved remarkable performance on complex reasoning tasks by adopting the ``think-then-answer'' paradigm, which enhances both accuracy and interpretability. However, current LRMs exhibit two critical…

Differential evolution (DE) algorithm is recognized as one of the most effective evolutionary algorithms, demonstrating remarkable efficacy in black-box optimization due to its derivative-free nature. Numerous enhancements to the…

An open challenge in recent machine learning is about how to improve the reasoning capability of large language models (LLMs) in a black-box setting, i.e., without access to detailed information such as output token probabilities. Existing…

Prompt optimization has become a practical way to improve the performance of Large Language Models (LLMs) without retraining. However, most existing frameworks treat evaluation as a black box, relying solely on outcome scores without…

Large Language Models (LLMs) trained with reinforcement learning and verifiable rewards have achieved strong results on complex reasoning tasks. Recent work extends this paradigm to a multi-agent setting, where a meta-thinking agent…

Reinforcement Learning (RL) offers a powerful framework for optimizing dynamic treatment regimes (DTRs). However, clinical RL is fundamentally bottlenecked by reward engineering: the challenge of defining signals that safely and effectively…

Recent advances demonstrate that reinforcement learning with verifiable rewards (RLVR) significantly enhances the reasoning capabilities of large language models (LLMs). However, standard RLVR faces challenges with reward sparsity, where…

The evolution of Large Language Model (LLM) reasoning is bottlenecked by the scarcity of high-quality process data. While self-alignment via endogenous rewards offers a solution, mining valid supervision faces three challenges: (1) Label…

Designing effective reward functions is a cornerstone of reinforcement learning (RL), yet it remains a challenging process due to the inefficiencies and inconsistencies inherent in conventional reward engineering methodologies. Recent…

Speech large language models (LLMs) have driven significant progress in end-to-end speech understanding and recognition, yet they continue to struggle with accurately recognizing rare words and domain-specific terminology. This paper…

While large language models (LLMs) have shown great potential across various domains, their applications in robotics remain largely limited to static prompt-based behaviors and still face challenges in complex tasks under zero-shot or…

Reinforcement Learning with Verifiable Rewards~(RLVR) has emerged as a powerful learn-to-reason paradigm for large reasoning models to tackle complex tasks. However, the current RLVR paradigm is still not efficient enough, as it works in a…

We present CRM (Multi-Agent Collaborative Reward Model), a framework that replaces a single black-box reward model with a coordinated team of specialist evaluators to improve robustness and interpretability in RLHF. Conventional reward…

Large Language Models (LLMs) often exhibit implicit biases and discriminatory tendencies that reflect underlying social stereotypes. While recent alignment techniques such as RLHF and DPO have mitigated some of these issues, they remain…

Reward engineering, the manual specification of reward functions to induce desired agent behavior, remains a fundamental challenge in multi-agent reinforcement learning. This difficulty is amplified by credit assignment ambiguity,…

Achieving the effective design and improvement of reward functions in reinforcement learning (RL) tasks with complex custom environments and multiple requirements presents considerable challenges. In this paper, we propose ERFSL, an…

Large Language Models (LLMs) have shown promising capabilities for solving Operations Research (OR) problems. While reinforcement learning serves as a powerful paradigm for LLM training on OR problems, existing works generally face two key…

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…