Related papers: Nexus: Execution-Grounded Multi-Agent Test Oracle …
Speech synthesis is crucial for human-computer interaction, enabling natural and intuitive communication. However, existing datasets involve high construction costs due to manual annotation and suffer from limited character diversity,…
Scaling test-time computation improves large language model performance without additional training. Recent work demonstrates that techniques such as repeated sampling, self-verification, and self-reflection can significantly enhance task…
Studies show that neural networks, not unlike traditional programs, are subject to bugs, e.g., adversarial samples that cause classification errors and discriminatory instances that demonstrate the lack of fairness. Given that neural…
Metamorphic testing is a well known approach to tackle the oracle problem in software testing. This technique requires the use of source test cases that serve as seeds for the generation of follow-up test cases. Systematic design of test…
Existing Multi-Agent Systems (MAS) typically rely on homogeneous model configurations, failing to exploit the diverse expertise inherent in different post-trained architectures. We propose Team-of-Thoughts, a heterogeneous MAS framework…
For decades, human-computer interaction has fundamentally been manual. Even today, almost all productive work done on the computer necessitates human input at every step. Autonomous virtual agents represent an exciting step in automating…
Evaluating and improving the security capabilities of code agents requires high-quality, executable vulnerability tasks. However, existing works rely on costly, unscalable manual reproduction and suffer from outdated data distributions. To…
Testing autonomous vehicles (AVs) requires complex oracles to determine if the AVs behavior conforms with specifications and humans' expectations. Available open source oracles are tightly embedded in the AV simulation software and are…
Multi-agent large language model frameworks are promising for complex multi step reasoning, yet existing systems remain weak for scientific and knowledge intensive domains due to static prompts and agent roles, rigid workflows, and…
In automated web testing, generating test scripts from natural language task descriptions is crucial for enhancing the test generation process. This activity involves creating the correct sequences of actions to form test scripts for future…
LLM agents have begun to find real security vulnerabilities that human auditors and automated fuzzers missed for decades, in source-available targets where the analyst can build and instrument the code. In practice the work is split among…
Language agents have shown strong promise for task automation. Realizing this promise for increasingly complex, long-horizon tasks has driven the rise of a sub-agent-as-tools paradigm for multi-turn task solving. However, existing designs…
While existing text-to-speech (TTS) models exhibit high expressiveness, fine-grained control over composite instructions remains challenging due to the structural mismatch between discrete textual intents and continuous acoustic…
Empirical claims about autonomous Kubernetes operations agents are largely unfalsifiable. Published work reports observational results without controlled comparisons against an agent-disabled baseline, selection bias is endemic,…
As production code evolves, the test suite must co-evolve to remain effective. Existing benchmarks for test evolution operate at method-level granularity with pre-paired inputs, bypassing the task of locating affected tests from the full…
Recent progress in large language model (LLM) agents has largely focused on embedding self-improvement mechanisms inside the agent or searching over many concurrent variants. While these approaches can raise aggregate scores, they often…
Existing REST API testing tools are typically evaluated using code coverage and crash-based fault metrics. However, recent LLM-based approaches increasingly generate tests from NL requirements to validate functional behaviour, making…
Recent agent frameworks and inference-time algorithms often struggle with complex planning problems due to limitations in verifying generated plans or reasoning and varying complexity of instances within a single task. Many existing methods…
The exponential growth of academic publications has led to a surge in papers of varying quality, increasing the cost of paper screening. Current approaches either use novelty assessment within general AI Reviewers or repurpose DeepResearch,…
Functionality-correct repository setup aims to configure execution environments (e.g., dependencies, build scripts) to successfully execute a repository's documented features. It presents significant challenges due to diverse,…