4 papers
Where the LLM Ends and Reliable Decisions Begin
Priyadarshan Patil, Abhishek Basu, Vikas Reddy +1
Systems that turn natural-language descriptions of optimization problems into solver-ready code generally use a language model at every stage, including the final translation from…
Reliable Post-Retrieval Assembly for Agent Memory: Separating Evidence Extraction from Policy Execution
Vikas Reddy, Sumanth Reddy Challaram
LLM-based memory systems can retrieve relevant evidence yet still fail when answer generation entangles semantic filtering, conflict resolution, prior suppression, and output gener…
Reason Less, Verify More: Deterministic Gates Recover a Silent Policy-Violation Failure Mode in Tool-Using LLM Agents
Vikas Reddy, Sumanth Reddy Challaram, Abhishek Basu
Tool-using LLM agents can violate the very policies they are deployed to enforce while appearing to complete the task successfully. In policy-permissive environments, a tool may ex…
Building a Word Segmenter for Sanskrit Overnight
Vikas Reddy, Amrith Krishna, Vishnu Dutt Sharma +3
There is an abundance of digitised texts available in Sanskrit. However, the word segmentation task in such texts are challenging due to the issue of 'Sandhi'. In Sandhi, words in…