LLM tool-use agent for DevRev
Inter IIT Tech Meet, IIT Bombay team
Fine-tuned agent that turns conversational queries into a graph of tool calls, adapting to the tools available. Built a synthetic dataset with ReAct prompting over ~100 strongly typed domain tools, and a graph-based correctness metric that ignores the order of independent calls. Fine-tuned 7B–13B open-source models with QLoRA on masked tool and argument prediction, benchmarked against GPT and Claude, and added a lightweight high-recall embedding retriever to narrow the tool search space.