Related papers: BootstrapAgent: Distilling Repository Setup into R…
We introduce a novel large language model (LLM)-driven agent framework, which iteratively refines queries and filters contextual evidence by leveraging dynamically evolving knowledge. A defining feature of the system is its decoupling of…
While widely used as a general method for uncertainty quantification, the bootstrap method encounters difficulties that raise concerns about its validity in practical applications. This paper introduces a new resampling-based method, termed…
The task of repository-level code completion is to continue writing the unfinished code based on a broader context of the repository. While for automated code completion tools, it is difficult to utilize the useful information scattered in…
With the rapid advancement of Large Language Models (LLMs), significant progress has been made in multi-agent applications. However, the complexities in coordinating agents' cooperation and LLMs' erratic performance pose notable challenges…
Following natural language instructions by executing actions in digital environments (e.g. web-browsers and REST APIs) is a challenging task for language model (LM) agents. Unfortunately, LM agents often fail to generalize to new…
Autonomous agent frameworks still struggle to reconcile long-term experiential learning with real-time, context-sensitive decision-making. In practice, this gap appears as static cognition, rigid workflow dependence, and inefficient context…
User comments on online programming platforms such as Stack Overflow play a vital role in maintaining the correctness and relevance of shared code examples. However, the majority of comments express gratitude or clarification, while only a…
Foundation model (FM)-based AI agents are rapidly gaining adoption across diverse domains, but their inherent non-determinism and non-reproducibility pose testing and quality assurance challenges. While recent benchmarks provide task-level…
AI coding agents are increasingly integrated into real-world software development workflows, yet their robustness under diverse and adversarial scenarios remains poorly understood. We present ABTest, a behavior-driven fuzzing framework that…
Agents that assist people need to have well-initialized policies that can adapt quickly to align with their partners' reward functions. Initializing policies to maximize performance with unknown partners can be achieved by bootstrapping…
LLM-based agents are increasingly deployed to autonomously solve complex tasks, raising urgent needs for IP protection and regulatory provenance. While content watermarking effectively attributes LLM-generated outputs, it fails to directly…
Repository-level code review requires reasoning over project structure, repository context, and file-level implementation details. Existing automated review workflows often collapse these tasks into a single pass, which can reduce…
This paper develops a stochastic programming framework for multi-agent systems where task decomposition, assignment, and scheduling problems are simultaneously optimized. The framework can be applied to heterogeneous mobile robot teams with…
Coding agents are increasingly used as general-purpose problem solvers, but their flexibility does not by itself confer the domain expertise needed for specialized tasks. Recent work addresses this through \textit{agent skills}: reusable…
In this paper we describe two bootstrap methods for massive data sets. Naive applications of common resampling methodology are often impractical for massive data sets due to computational burden and due to complex patterns of inhomogeneity.…
In experimental causal inference, we distinguish between two sources of uncertainty: design uncertainty, due to the treatment assignment mechanism, and sampling uncertainty, when the sample is drawn from a super-population. This distinction…
Many works have recently proposed the use of Large Language Model (LLM) based agents for performing `repository level' tasks, loosely defined as a set of tasks whose scopes are greater than a single file. This has led to speculation that…
AI coding assistants like GitHub Copilot are rapidly transforming software development, but their safety remains deeply uncertain-especially in high-stakes domains like cybersecurity. Current red-teaming tools often rely on fixed benchmarks…
As autonomous coding agents become deeply embedded in software development workflows, their high operational velocity introduces a critical oversight challenge: the accumulating divergence between agentic actions and architectural intent.…
TRUST Agents is a collaborative multi-agent framework for explainable fact verification and fake news detection. Rather than treating verification as a simple true-or-false classification task, the system identifies verifiable claims,…