Related papers: Compiler-R1: Towards Agentic Compiler Auto-tuning …

Large Language Models (LLMs) have shown impressive capabilities in multi-step reasoning and problem-solving.Recent works introduce multi-agent reflection frameworks where multiple LLM agents critique and refine each other's outputs using…

Data selection for finetuning Large Language Models (LLMs) can be framed as a budget-constrained optimization problem: maximizing a model's downstream performance under a strict training data budget. Solving this problem is generally…

GCC and LLVM underpin much of modern software infrastructure, relying on distinct Intermediate Representations (IRs) to drive optimizations and code generation. However, the semantic and structural differences between these IRs create…

An optimizing compiler consists of a front end parsing a textual programming language into an intermediate representation (IR), a middle end performing optimizations on the IR, and a back end lowering the IR to a target representation (TR)…

Large reasoning models (LRMs) are proficient at generating explicit, step-by-step reasoning sequences before producing final answers. However, such detailed reasoning can introduce substantial computational overhead and latency,…

Reinforcement Learning (RL) has emerged as a crucial method for training or fine-tuning large language models (LLMs), enabling adaptive, task-specific optimizations through interactive feedback. Multi-Agent Reinforcement Learning (MARL), in…

A burgeoning area within reinforcement learning (RL) is the design of sequential decision-making agents centered around large language models (LLMs). While autonomous decision-making agents powered by modern LLMs could facilitate numerous…

Modern scientific discovery increasingly relies on high-performance computing for complex modeling and simulation. A key challenge in improving parallel program performance is efficiently mapping tasks to processors and data to memory, a…

Robust deployment of large multimodal models (LMMs) in real-world scenarios requires access to external knowledge sources, given the complexity and dynamic nature of real-world information. Existing approaches such as retrieval-augmented…

Reinforcement learning (RL) has demonstrated its capability in solving various tasks but is notorious for its low sample efficiency. In this paper, we propose RLingua, a framework that can leverage the internal knowledge of large language…

Reinforcement learning (RL) has become an effective approach for fine-tuning large language models (LLMs), particularly to enhance their reasoning capabilities. However, RL fine-tuning remains highly resource-intensive, and existing work…

Visual reinforcement learning (RL) suffers from poor sample efficiency due to high-dimensional observations in complex tasks. While existing works have shown that vision-language models (VLMs) can assist RL, they often focus on knowledge…

Reinforcement learning (RL) agent development traditionally requires substantial expertise and iterative effort, often leading to high failure rates and limited accessibility. This paper introduces Agent$^2$, an LLM-driven…

Sampling-based trajectory planners are widely used for agile autonomous driving due to their ability to generate fast, smooth, and kinodynamically feasible trajectories. However, their behavior is often governed by a cost function with…

Large Language Models (LLMs) have achieved remarkable success through imitation learning on vast text corpora, but this paradigm creates a training-generation gap and limits robust reasoning. Reinforcement learning (RL) offers a more…

Large language model alignment via reinforcement learning depends critically on reward function quality. However, static, domain-specific reward models are often costly to train and exhibit poor generalization in out-of-distribution…

User simulators serve as the critical interactive environment for agent post-training, and an ideal user simulator generalizes across domains and proactively engages in negotiation by challenging or bargaining. However, current methods…

Large Language Models (LLMs) have been widely used as general-purpose AI agents showing comparable performance on many downstream tasks. However, existing work shows that it is challenging for LLMs to integrate structured data (e.g. KG,…

The automated repair of C++ compilation errors presents a significant challenge, the resolution of which is critical for developer productivity. Progress in this domain is constrained by two primary factors: the scarcity of large-scale,…

Large language models (LLMs) are becoming the foundation for autonomous agents that can use tools to solve complex tasks. Reinforcement learning (RL) has emerged as a common approach for injecting such agentic capabilities, but typically…