Related papers: Feedback-Driven Execution for LLM-Based Binary Ana…

Large language models (LLMs) demonstrate strong generative capabilities but remain vulnerable to hallucination and unreliable reasoning under adversarial prompting. Existing safety approaches -- such as reinforcement learning from human…

Large Language Models (LLMs) have significantly advanced tool-augmented agents, enabling autonomous reasoning via API interactions. However, executing multi-step tasks within massive tool libraries remains challenging due to two critical…

Large Language Models demonstrate strong reasoning and generation abilities, yet their behavior in multi-turn tasks often lacks reliability and verifiability. We present a task completion framework that enables LLM-based agents to act under…

Retrieval-augmented generation (RAG) frameworks enable large language models (LLMs) to retrieve relevant information from a knowledge base and incorporate it into the context for generating responses. This mitigates hallucinations and…

Automated Program Repair tools are developed for generating feedback and suggesting a repair method for erroneous code. State of the art (SOTA) code repair methods rely on data-driven approaches and often fail to deliver solution for…

The rise of Large Reasoning Models (LRMs) signifies a paradigm shift toward advanced computational reasoning. Yet, this progress disrupts traditional agent frameworks, traditionally anchored by execution-oriented Large Language Models…

Large Language Models (LLMs) have shown remarkable capabilities in code generation tasks, yet they face significant limitations in handling complex, long-context programming challenges and demonstrating complex compositional reasoning…

Vision language models (VLMs) have achieved impressive progress in diverse applications, becoming a prevalent research direction. In this paper, we build FIRE, a feedback-refinement dataset, consisting of 1.1M multi-turn conversations that…

Large Language Models (LLMs) have demonstrated significant performance improvements across various cognitive tasks. An emerging application is using LLMs to enhance retrieval-augmented generation (RAG) capabilities. These systems require…

The automatic evaluation of instruction following typically involves using large language models (LLMs) to assess response quality. However, there is a lack of comprehensive evaluation of these LLM-based evaluators across two dimensions:…

Multi-fidelity (MF) regression often operates in regimes of extreme data imbalance, where the commonly-used Gaussian-process (GP) surrogates struggle with cubic scaling costs and overfit to sparse high-fidelity observations, limiting…

Real-world sequential decision making is characterized by sparse rewards and large decision spaces, posing significant difficulty for experiential learning systems like $\textit{tabula rasa}$ reinforcement learning (RL) agents. Large…

Recent breakthroughs in generative simulation have harnessed Large Language Models (LLMs) to generate diverse robotic task curricula, yet these open-loop paradigms frequently produce linguistically coherent but physically infeasible goals,…

Large language models (LLMs) have been increasingly used to interact with external environments (e.g., games, compilers, APIs) as goal-driven agents. However, it remains challenging for these language agents to quickly and efficiently learn…

Large Language Models (LLMs) are increasingly used to power autonomous agents for complex, multi-step tasks. However, human-agent interaction remains pointwise and reactive: users approve or correct individual actions to mitigate immediate…

Recent advances in Large Language Models (LLMs) have driven interest in automating cybersecurity penetration testing workflows, offering the promise of faster and more consistent vulnerability assessment for enterprise systems. Existing LLM…

Retrieval-Augmented Generation (RAG) expands the knowledge boundary of large language models (LLMs) by integrating external knowledge bases, whose construction is often time-consuming and laborious. If an adversary extracts the knowledge…

Large language model (LLM) multi-agent coding systems typically fix agent capabilities at design time. We study an alternative setting, earned autonomy, in which a coding agent starts with zero pre-defined functions and incrementally builds…

Large language model (LLM) agents typically adopt a step-by-step reasoning framework, in which they interleave the processes of thinking and acting to accomplish the given task. However, this paradigm faces a deep-rooted one-pass issue…

Large language models (LLMs) often generate content that contains factual errors when responding to fact-seeking prompts on open-ended topics. To benchmark a model's long-form factuality in open domains, we first use GPT-4 to generate…