相关论文: DART: Semantic Recoverability for Structured Tool …

Despite achieving remarkable success in complex tasks, Deep Reinforcement Learning (DRL) is still suffering from critical issues in practical applications, such as low data efficiency, lack of interpretability, and limited cross-environment…

The safety alignment of Large Language Models (LLMs) is vulnerable to both manual and automated jailbreak attacks, which adversarially trigger LLMs to output harmful content. However, current methods for jailbreaking LLMs, which nest entire…

In this paper we present VART, a tool for automatically revealing regression faults missed by regression test suites. Interestingly, VART is not limited to faults causing crashing or exceptions, but can reveal faults that cause the…

Language use differs between domains and even within a domain, language use changes over time. For pre-trained language models like BERT, domain adaptation through continued pre-training has been shown to improve performance on in-domain…

Real-world applications of reinforcement learning for recommendation and experimentation faces a practical challenge: the relative reward of different bandit arms can evolve over the lifetime of the learning agent. To deal with these…

Solving mathematical problems requires advanced reasoning abilities and presents notable challenges for large language models. Previous works usually synthesize data from proprietary models to augment existing datasets, followed by…

To achieve general-purpose utility, we argue that robots must evolve from passive executors into active Information Retrieval users. In strictly zero-shot settings where no prior demonstrations exist, robots face a critical information gap,…

Knowledge of the input format of binary executables is important for finding bugs and vulnerabilities, such as generating data for fuzzing or manual reverse engineering. This paper presents an algorithm to recover the structure and semantic…

Agents are LLM-driven components that can mutate environments in powerful, arbitrary ways. Extracting guarantees for the execution of agents in production environments can be challenging due to asynchrony and failures. In this paper, we…

AI-based systems, currently driven largely by LLMs and tool-using agentic harnesses, are increasingly discussed as a possible threat to software engineering. Foundation models get stronger, agents can plan and act across multiple steps, and…

Tool-using LLM agents produce trajectories whose calls form a directed dependency graph: earlier tool outputs supply arguments to later calls. Whether this execution structure is represented inside the model is unknown; prior structural…

Resolving complex code defects from natural language descriptions remains a fundamental software engineering challenge. Recently, large language models (LLMs) have driven the creation of agent-based automated repair systems. While improving…

Large-scale pre-trained language models have contributed significantly to natural language processing by demonstrating remarkable abilities as few-shot learners. However, their effectiveness depends mainly on scaling the model parameters…

Authorizing Large Language Model (LLM)-driven agents to dynamically invoke tools and access protected resources introduces significant security risks, and the risks grow dramatically as agents engage in multi-turn conversations and scale…

The automatic generation of radiology reports has emerged as a promising solution to reduce a time-consuming task and accurately capture critical disease-relevant findings in X-ray images. Previous approaches for radiology report generation…

Zero-error recovery under deterministic partial views is graph recovery for the induced confusability relation. A finite family of coordinate-subset observations determines a graph on latent states; $T$-ary exact recovery is graph…

Tool use extends large language models beyond parametric knowledge, but reliable execution requires balancing appropriate reasoning depth with strict structural validity. We approach this problem from a case-based perspective to present…

Modeling semantic and structural information from tabular data remains a core challenge for effective table understanding. Existing Table-as-Text approaches flatten tables for large language models (LLMs), but lose crucial structural cues,…

Existing tool-augmented large language models (LLMs) encounter significant challenges when processing complex queries. Current frameworks such as ReAct are prone to local optimization traps due to their reliance on incremental…

Recent work has proposed automated red-teaming methods for testing the vulnerabilities of a given target large language model (LLM). These methods use red-teaming LLMs to uncover inputs that induce harmful behavior in a target LLM. In this…