7 papers
Scrouting: Cost-Aware Routing of Coding Agents by Scouting the Repository First
Ishaan Bhola, Adithyan Krishnan, Mukunda NS
Frontier language models can resolve repository-level software issues, but each attempt is expensive, and existing routers select a model from the issue text alone. We present Supe…
Code Isn't Memory: A Structural Codebase Index Inside a Coding Agent
Ishaan Bhola, Adithyan Krishnan, Sravanth Kurmala +1
Coding agents now interleave LLMs with retrieval over the working repository, and retrieval implementations vary widely across deployed harnesses. Inside a fixed coding-agent harne…
Trained Miniatures: Low cost, High Efficacy SLMs for Sales & Marketing
Ishaan Bhola, Mukunda NS, Sravanth Kurmala +2
Large language models (LLMs) excel in text generation; however, these creative elements require heavy computation and are accompanied by a steep cost. Especially for targeted appli…
Safeguarding AI Agents: Developing and Analyzing Safety Architectures
Ishaan Domkundwar, Mukunda N S, Ishaan Bhola +1
AI agents, specifically powered by large language models, have demonstrated exceptional capabilities in various applications where precision and efficacy are necessary. However, th…
SuperCoder2.0: Technical Report on Exploring the feasibility of LLMs as Autonomous Programmer
Anmol Gautam, Kishore Kumar, Adarsh Jha +2
We present SuperCoder2.0, an advanced autonomous system designed to enhance software development through artificial intelligence. The system combines an AI-native development appro…
GUIDE: Graphical User Interface Data for Execution
Rajat Chawla, Adarsh Jha, Muskaan Kumar +2
In this paper, we introduce GUIDE, a novel dataset tailored for the advancement of Multimodal Large Language Model (MLLM) applications, particularly focusing on Robotic Process Aut…