Related papers: GASP: Guided Asymmetric Self-Play For Coding LLMs

Robotics education fosters computational thinking, creativity, and problem-solving, but remains challenging due to technical complexity. Game-based learning (GBL) and gamification offer engagement benefits, yet their comparative impact…

There is a growing trend of teaching large language models (LLMs) to solve mathematical problems through coding. Existing studies primarily focus on prompting powerful, closed-source models to generate seed training data followed by…

Automated assessment of open-ended student responses is a critical capability for scaling personalized feedback in education. While large language models (LLMs) have shown promise in grading tasks via in-context learning (ICL), their…

In higher education, gamification offers the prospect of providing a pivotal shift from traditional asynchronous forms of engagement, to developing methods to foster greater levels of synchronous interactivity and partnership between and…

Generative adversarial network (GAN) is among the most popular deep learning models for learning complex data distributions. However, training a GAN is known to be a challenging task. This is often attributed to the lack of correlation…

Recent advances in large language model (LLM) reasoning, led by reinforcement learning with verifiable rewards (RLVR), have inspired self-play post-training, where models improve by generating and solving their own problems. While self-play…

While Large Language Models (LLMs) have achieved remarkable success in formal learning tasks such as mathematics and code generation, they still struggle with the "practical wisdom" and generalizable intelligence, such as strategic…

Effective exploration continues to be a significant challenge that prevents the deployment of reinforcement learning for many physical systems. This is particularly true for systems with continuous and high-dimensional state and action…

This paper presents an AI-driven approach to enhance math learning in a modern Learning Management System (LMS) by recommending similar math questions. Deep embeddings for math questions are generated using Meta's…

Retraining a model using its own predictions together with the original, potentially noisy labels is a well-known strategy for improving the model performance. While prior works have demonstrated the benefits of specific heuristic…

This paper focuses on robotic reinforcement learning with sparse rewards for natural language goal representations. An open problem is the sample-inefficiency that stems from the compositionality of natural language, and from the grounding…

Adaptive gradient methods (AGMs) have become popular in optimizing the nonconvex problems in deep learning area. We revisit AGMs and identify that the adaptive learning rate (A-LR) used by AGMs varies significantly across the dimensions of…

Learning in a multi-agent system is challenging because agents are simultaneously learning and the environment is not stationary, undermining convergence guarantees. To address this challenge, this paper presents a new gradient-based…

Designing agents, capable of learning autonomously a wide range of skills is critical in order to increase the scope of reinforcement learning. It will both increase the diversity of learned skills and reduce the burden of manually…

Interaction between learner and feedback-giver has come into focus recently for post-training of Large Language Models (LLMs), through the use of reward models that judge the appropriateness of a model's response. In this paper, we…

It has been established in recent work that Large Language Models (LLMs) can be prompted to "self-play" conversational games that probe certain capabilities (general instruction following, strategic goal orientation, language understanding…

While recent low-light image enhancement (LLIE) methods have made significant advancements, they still face challenges in terms of low visual quality and weak generalization ability when applied to complex scenarios. To address these…

Mathematical problem generation (MPG) is a significant research direction in the field of intelligent education. In recent years, the rapid development of large language models (LLMs) has enabled new technological approaches to…

While Large Language Models (LLMs) excel in reasoning, whether they can sustain persistent latent states remains under-explored. The capacity to maintain and manipulate unexpressed, internal representations-analogous to human working…

Reinforcement learning has emerged as a powerful paradigm for unlocking reasoning capabilities in language models. However, relying on sparse rewards makes this process highly sample-inefficient, as models must navigate vast search spaces…