Related papers: Debugging the Debuggers: Failure-Anchored Structur…
Mixture-of-Experts models have become a dominant architecture for scaling Large Language Models by activating only a sparse subset of experts per token. However, latency-critical MoE inference faces a fundamental tension: while expert…
Code agents are advancing rapidly, but debugging them is becoming increasingly difficult. As frameworks orchestrate parallel tool calls and multi-stage workflows over complex tasks, making the agent's state transitions and error propagation…
Multimodal creative assistants decompose user goals and route tasks to subagents for layout, styling, retrieval, and generation. Retrieval quality is pivotal, yet failures can arise at several stages: understanding user intent, choosing…
Vulnerability detection tools are widely adopted in software projects, yet they often overwhelm maintainers with false positives and non-actionable reports. Automated exploitation systems can help validate these reports; however, existing…
We present a framework for bridging the gap between sensor attack detection and recovery in cyber-physical systems. The proposed framework models modern-day, complex perception pipelines as bipartite graphs, which combined with anomaly…
Machine learning models commonly exhibit unexpected failures post-deployment due to either data shifts or uncommon situations in the training environment. Domain experts typically go through the tedious process of inspecting the failure…
As agentic coding systems decompose work across multiple model instances, a critical safety question is whether those instances can coordinate to achieve a hidden malicious objective while remaining aligned with user intent. We introduce…
LLM-based agents are rapidly being adopted across diverse domains. Since they interact with users without supervision, they must be tested extensively. Current testing approaches focus on acceptance-level evaluation from the user's…
As LLM-based agents exhibit exceptional capabilities in addressing complex problems, there is a growing focus on developing coding agents to tackle increasingly sophisticated tasks. Despite their promising performance, these coding agents…
While significant progress has been made in automating various aspects of software development through coding agents, there is still significant room for improvement in their bug fixing capabilities. Debugging and investigation of runtime…
Many applications are implemented as multi-tier software systems, and are executed on distributed infrastructures, like cloud infrastructures, to benefit from the cost reduction that derives from dynamically allocating resources on-demand.…
System prompts for AI coding agents increasingly employ motivational framing -- from neutral task descriptions to fear-driven threats -- yet no controlled study has examined whether such framing affects agent behavior. We present two…
Agentic systems have been widely studied to automate software engineering jobs such as bug fixing. As these systems increasingly tackle complex tasks, understanding where and why they fail becomes essential for iterative refinement and…
LLM agents with tool-calling capabilities often fail when user instructions are ambiguous or incomplete, leading to incorrect invocations and task failures. Existing approaches operate in unstructured language spaces, generating clarifying…
Failure to accurately measure the outcomes of an experiment can lead to bias and incorrect conclusions. Online controlled experiments (aka AB tests) are increasingly being used to make decisions to improve websites as well as mobile and…
Structured claim decomposition is often proposed as a solution for verifying complex, multi-faceted claims, yet empirical results have been inconsistent. We argue that these inconsistencies stem from two overlooked bottlenecks: evidence…
Despite the growing capabilities of autonomous agents powered by large language models (LLMs), their adoption in high-stakes domains remains limited. A key barrier is security: the inherently nondeterministic behavior of LLM agents defies…
Software testing has progressed toward intelligent automation, yet current AI-based test generators still suffer from static, single-shot outputs that frequently produce invalid, redundant, or non-executable tests due to the lack of…
Frequent toolchain updates and growing ISA diversity have made system-level software package repair increasingly important. Diagnosing and repairing build failures remains challenging because failures involve heterogeneous evidence,…
Multi-agent systems (MAS) are increasingly capable of tackling complex real-world tasks, yet their reliance on inter-agent coordination, tool use, and long-horizon reasoning makes error recognition particularly challenging. Minor errors can…