Related papers: Towards Execution-Grounded Automated AI Research

The rapid evolution of software libraries creates a significant challenge for Large Language Models (LLMs), whose static parametric knowledge often becomes stale post-training. While retrieval-augmented generation (RAG) is commonly used to…

Large language models show strong potential for automated code generation, but lack guarantees for correctness, quality, safety, and domain-specific constraints. For instance in robotics, where code generation is increasingly being used for…

Reinforcement Learning (RL) plays an important role in the robotic manipulation domain since it allows self-learning from trial-and-error interactions with the environment. Still, sample efficiency and reward specification seriously limit…

Large language models (LLMs) are increasingly deployed for tasks requiring complex reasoning, prompting significant interest in improving their reasoning abilities through post-training. Especially RL based methods using verifiable reward,…

Code LLMs still struggle with code execution reasoning, especially in smaller models. Existing methods rely on supervised fine-tuning (SFT) with teacher-generated explanations, primarily in two forms: (1) input-output (I/O) prediction…

Large language models (LLMs) have been widely integrated into information retrieval to advance traditional techniques. However, effectively enabling LLMs to seek accurate knowledge in complex tasks remains a challenge due to the complexity…

Large Language Models (LLMs) pre-trained on code have recently emerged as the dominant approach to program synthesis. However, these models are trained using next-token prediction, which ignores the syntax and semantics of code. We propose…

Advanced reasoning in LLMs on challenging domains like mathematical reasoning can be tackled using verifiable rewards based reinforced fine-tuning (ReFT). In standard ReFT frameworks, a behavior model generates multiple completions with…

Reasoning-augmented search agents, such as Search-R1, are trained to reason, search, and generate the final answer iteratively. Nevertheless, due to their limited capabilities in reasoning and search, their performance on multi-hop QA…

Large language model (LLM) agents are moving beyond prompting alone. ChatGPT marked the rise of general-purpose LLM assistants, DeepSeek showed that on-policy reinforcement learning with verifiable rewards can improve reasoning and tool…

Reflection is widely recognized as a cornerstone of student development, fostering critical thinking, self-regulation, and deep conceptual understanding. Traditionally, reflective skills have been cultivated through structured feedback,…

Reinforcement learning from verifiable rewards (RLVR) stimulates the thinking processes of large language models (LLMs), substantially enhancing their reasoning abilities on verifiable tasks. It is often assumed that similar gains should…

Large Language Models (LLMs) are typically fine-tuned for reasoning tasks through a two-stage pipeline of Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL), a process fraught with catastrophic forgetting and suboptimal…

Large language models (LLMs) have demonstrated impressive performance and have come to dominate the field of natural language processing (NLP) across various tasks. However, due to their strong instruction-following capabilities and…

Reward design plays a pivotal role in the training of game AIs, requiring substantial domain-specific knowledge and human effort. In recent years, several studies have explored reward generation for training game agents and controlling…

Inductive reasoning enables humans to infer abstract rules from limited examples and apply them to novel situations. In this work, we compare an LLM-based hypothesis search framework with direct program generation approaches on few-shot…

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…

Generative artificial intelligence (AI), in particular large language models (LLMs), is poised to drive transformative economic change. LLMs are pre-trained on vast text data to learn general language patterns, but a subsequent…

Reinforcement Learning with Verifiable Rewards (RLVR) has improved the reasoning abilities of Large Language Models (LLMs) by using rule-based binary feedback. However, current RLVR methods typically assign the same reward to every token.…

Large language models (LLMs) have demonstrated remarkable capabilities across a range of text-generation tasks. However, LLMs still struggle with problems requiring multi-step decision-making and environmental feedback, such as online…