Author

Arnav Mehta

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

Understanding and Enhancing Backdoor Persistency in LLM Agent Post-Training

Developers can build LLM agents by adapting third-party models through benign post-training. We study a supply-chain threat in which an attacker supplies a model with a backdoor: hidden behavior that produces malicious outputs when a particular input pattern appears. Focusing on software-engineering agents, we ask whet...

Qiusi Zhan, Nian Lyu, Stephanie Ding et al. · 0 citations

#human-computer interacti... Preprint Sep 2026

LeanSide: A Formally Verified Co-Reasoning System for Natural-language Proofs

Large language models are increasingly used as collaborators on deductive-reasoning tasks, but their outputs can hallucinate or pull users away from intended reasoning. Formal proof assistants provide machine-checked verification, but have a steep learning curve and require more granular reasoning than human written pr...

Chen-Jun Guo, Manooshree Patel, Arnav Mehta et al. · 0 citations