03 / Research output

Publications

Peer-reviewed papers, workshop contributions and preprints. 12 total — expand Abstract or BibTeX on any entry.

All Agents Evaluation LLMs Reasoning Safety Training

2026

[001]

Mid-Training with Self-Generated Data Improves Reinforcement Learning in Language Models

Aswin RRV, Jacob Dineen, Divij Handa, Mihir Parmar, Ben Zhou, Swaroop Mishra, Chitta Baral

Preprint arXiv

TL;DR Mid-training on self-generated data boosts downstream RL and reasoning.

arXiv ↗ LLMsTraining

Shows that mid-training language models on their own self-generated data improves downstream reinforcement learning, yielding stronger reasoning than RL alone.

[002]

GuidedSampling: Steering LLMs Towards Diverse Candidate Solutions at Inference-Time

Divij Handa, Mihir Parmar, Aswin RRV, Md Nayem Uddin, Hamid Palangi, Chitta Baral

✓ ICLR 2026 Conference

TL;DR Makes inference-time sampling produce genuinely diverse solutions — +21.6% pass@50.

OpenReview ↗ LLMsReasoning

Decouples exploration from generation at inference time so repeated sampling produces genuinely diverse candidate solutions, improving pass@50 by ~21.6% over standard repeated sampling.

2025

[001]

When “Competency” in Reasoning Opens the Door to Vulnerability: Jailbreaking LLMs via Novel Complex Ciphers

Divij Handa, Zehua Zhang, Amir Saeidi, Shrinidhi Kumbhar, Md Nayem Uddin, Aswin RRV, Chitta Baral

✓ NeurIPS 2025 Workshop (Reliable ML from Unreliable Data) Workshop

TL;DR Stronger reasoning makes LLMs easier to jailbreak — via custom ciphers (ACE/LACE).

OpenReview ↗ LLMsSafety

Shows that as LLMs get better at reasoning they become more susceptible to novel jailbreaks. Introduces ACE and LACE — attacks that encode malicious queries with custom and layered ciphers — and CipherBench to measure cipher-decoding ability.

[002]

OptAgent: Optimizing Query Rewriting for E-Commerce via Multi-Agent Simulation

Divij Handa, David Blincoe, Orson Adams, Yinlin Fu

Preprint arXiv

TL;DR Uses multi-agent shopper simulation as a reward to optimize e-commerce query rewriting.

arXiv ↗ AgentsLLMs

Combines multi-agent simulation with an evolutionary algorithm for query rewriting: multiple LLM agents act as simulated shoppers, and their averaged scores form a dynamic reward that iteratively refines the query — improving fitness by ~22%.