publications

Peer-reviewed publications and preprints, each in reverse chronological order. * denotes equal contribution.

See also my Google Scholar profile.

Publications

2026

  1. Evaluating Code Slop in Long-Horizon Coding Agents
    Shubham Gandhi*, Shyam Agarwal*, Nachiket Kotalwar*, and 1 more author
    In Workshop on Agent Behavior (WAB) at the Conference on Language Modeling (COLM), Oct 2026
  2. Steer, Don’t Solve: Training Small Critic Models for Large Code Agents
    Shubham Gandhi*, Yiqing Xie*, Atharva Naik, and 2 more authors
    In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP), Nov 2026
  3. Hybrid-Gym: Training Coding Agents to Generalize Across Tasks
    Yiqing Xie, Emmy Liu, Gaokai Zhang, and 7 more authors
    In Proceedings of the 43rd International Conference on Machine Learning (ICML), Jul 2026

2025

  1. When Agents go Astray: Course-Correcting SWE Agents with PRMs
    Shubham Gandhi, Jason Tsay, Jatin Ganhotra, and 2 more authors
    In Scaling Environments for Agents (SEA) Workshop at NeurIPS, Dec 2025
  2. Secure and Useful Models are Reasonable: Aligning Code Models via Utility-Preserving Reasoning
    Atharva Naik, Alex Xie, Abhinav Rao, and 4 more authors
    Aug 2025
  3. An Empirical Study on Strong-Weak Model Collaboration for Repo-level Code Generation
    Shubham Gandhi, Atharva Naik, Yiqing Xie, and 1 more author
    In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP), Nov 2025
  4. ResearchCodeAgent: An LLM Multi-Agent System for Automated Codification of Research Methodologies
    Shubham Gandhi, Dhruv Shah, Manasi Patwardhan, and 2 more authors
    In AI4Research Workshop at AAAI, Mar 2025

2024

  1. BudgetMLAgent: A Cost-Effective LLM Multi-Agent System for Automating Machine Learning Tasks
    Shubham Gandhi, Manasi Patwardhan, Lovekesh Vig, and 1 more author
    In Proceedings of the 4th International Conference on AI-ML Systems (AIMLSystems), Oct 2024
  2. Translation of Low-Resource COBOL to Logically Correct and Readable Java leveraging High-Resource Java Refinement
    Shubham Gandhi, Manasi Patwardhan, Jyotsana Khatri, and 2 more authors
    In LLM4Code Workshop at the International Conference on Software Engineering (ICSE), Apr 2024

Preprints

2026

  1. Preprint
    Ulysses: A Security Harness for Synthesizing Verifiable Web Exploits
    Aditya Oke, André Vicente Duarte, Rui Melo, and 6 more authors
    arXiv preprint arXiv:2610.31831, Oct 2026
  2. Preprint
    Self-Evolving Static Analysis via LLM Pseudo-Labeling
    Rui Melo, André Vicente Duarte, Aditya Oke, and 5 more authors
    arXiv preprint arXiv:2610.30184, Oct 2026
  3. Preprint
    Exploring Visual Access and Proactive AI Tutoring for Handwritten Mathematics
    Nachiket Kotalwar, Conrad Borchers, Shubham Gandhi, and 3 more authors
    arXiv preprint arXiv:2610.26411, Oct 2026
  4. Preprint
    ABSENTIA: Detecting Broken Access Control Vulnerabilities in Web Applications
    André Vicente Duarte, Aditya Oke, Rui Melo, and 7 more authors
    arXiv preprint arXiv:2610.00977 (under review), Oct 2026
  5. Preprint
    DRACO: Fine-Grained Credit Assignment with Dynamic Rubrics for Long-Horizon Agent Training
    Shubham Gandhi*, Saurabh Goyal*, Kiran Kate, and 1 more author
    arXiv preprint arXiv:2609.04094 (under review), Sep 2026

2023

  1. Preprint
    StaticFixer: From Static Analysis to Static Repair
    Naman Jain, Shubham Gandhi, Atharv Sonwane, and 5 more authors
    arXiv preprint arXiv:2307.12465, Jul 2023