8 papers
Tangent: An Empirical Study of Testing Practices for LLM-Based Agent Applications
Rangeet Pan, Tyler Stennett, Divya Sankar +5
Agents built on large language models (LLMs) are increasingly used to build applications that perform complex, multi-step tasks involving reasoning, tool use, and interaction with…
CRANE: Constrained Reasoning Injection for Code Agents via Nullspace Editing
Mingzhi Zhu, Michele Merler, Raju Pavuluri +1
Code agents must both reason over long-horizon repository state and obey strict tool-use protocols. In paired Instruct/Thinking checkpoints, these capabilities are complementary bu…
SAINT: Service-level Integration Test Generation with Program Analysis and LLM-based Agents
Rangeet Pan, Raju Pavuluri, Ruikai Huang +4
Enterprise applications are typically tested at multiple levels, with service-level testing playing an important role in validating application functionality. Existing service-leve…
Hamster: A Large-Scale Study and Characterization of Developer-Written Tests
Rangeet Pan, Tyler Stennett, Raju Pavuluri +3
Automated test generation (ATG), which aims to reduce the cost of manual test suite development, has been investigated for decades and has produced countless techniques based on a…
ScarfBench: A Benchmark for Cross-Framework Application Migration in Enterprise Java
Advait Pavuluri, Bridget McGinn, Ashita Saxena +6
Java remains central to enterprise software, and many applications outlive their original architecture. Migrating them across frameworks is a behavior-preserving refactoring spanni…
Multi-task Code LLMs: Data Mix or Model Merge?
Mingzhi Zhu, Boris Sobolev, Rahul Krishna +3
Recent research advocates deploying smaller, specialized code LLMs in agentic frameworks alongside frontier models, sparking interest in efficient strategies for multi-task learnin…