5 papers
Context-as-AI-Service: Surfacing Cross-File Dependency Chains for LLM-Generated Developer Documentation
Ameya Gawde, Vyzantinos Repantis, Harshvardhan Singh +1
LLM agents increasingly write and maintain developer documentation, but usefulness and accuracy often rely on dependency chains that are not obvious to follow. Even with more files…
Decoy-Calibrated Failure Audits for Language Models
Vyzantinos Repantis, Ameya Gawde, Harshvardhan Singh
Useful audits reveal not only how often a model fails, but also where its failures concentrate. An auditor may test many candidate explanations: long inputs, indirect questions, di…
How Many Tools Should an LLM Agent See? A Chance-Corrected Answer
Vyzantinos Repantis, Ameya Gawde, Harshvardhan Singh +1
Before an LLM agent can use a tool, a retrieval system must decide which candidate tools to show to the agent. How long should that shortlist be? Show too many tools and the model…
Separating Semantic Competition from Context Length in RAG Reading
Vyzantinos Repantis, Ameya Gawde, Harshvardhan Singh +4
Retrieval-augmented generation (RAG) systems can respond incorrectly even when the correct passage was retrieved. The model must still read the retrieved passages and identify whic…
The 99% Success Paradox: When Near-Perfect Retrieval Equals Random Selection
Vyzantinos Repantis, Harshvardhan Singh, Tony Joseph +5
For most of the history of information retrieval (IR), search results were designed for human consumers who could scan, filter, and discard irrelevant information on their own. Thi…