AI Paper Atlas

Research map / Large language models / Agents, code and math

FHE-Coder: Secure Agentic Code Generation for Fully Homomorphic Encryption

Mayank Kumar, Jiaqi Xue, Mengxin Zheng, Qian Lou

ICLR 2026 · Large language models › Agents, code and math · approach: Software engineering agents

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
run full FHE-Coder pipeline instead of baseline agentGPT-5 TFHE agent · TFHE MatMul/Softmax/Attention/Transformerpass@1 (func_sec): 0.00 -> 1.00 (MatMul)Improved
add Prompt Formalizer to baseline (ablation)GPT-5 baseline · TFHE Vector Additionpass@1 (func_sec): 0.0 -> 0.6Improved
add API RAG retriever on top of Formalizer (ablation)BAS + FP · TFHE Vector Additionpass@1 (func_sec): 0.6 -> 0.8Improved
add Security Verifier feedback loop on top of FP and RAG (ablation)BAS + FP + RAG · TFHE Vector Additionpass@1 (func_sec): 0.8 -> 1.0Improved
add structured decomposition (compose verified primitives) (ablation)FHE-Coder · TFHE Matrix-Vector, CNNpass@1 (func_sec): near-zero -> 0.70 (Mat-Vec), 0.60 (CNN)Improved
use expert-enriched docstring RAG instead of vanilla RAG (ablation)FHE-Coder RAG retriever · TFHE ReLU, MatMulpass@1 (sec): ReLU sec 0.20 with vanilla RAG; MatMul sec 0.00Improved
swap TFHE parameter solver and docs for CKKS versionsFHE-Coder · CKKS Softmax/Attention/Transformerpass@1 (func_sec): 0.00 -> 0.60 (Softmax), 1.00 (Attention)Improved
FHE-Coder on CKKS MatMul vs baseline functional correctnessGPT-5 CKKS · CKKS MatMulpass@1 (func): 1.00 -> 0.80Hurt
FHE-Coder on Transformer workloadsGPT-5 · TFHE Transformerpass@1 (func_sec): 0.00 -> 0.80 per Table 4; about 0.4 per textMixed
use stronger base LLM (GPT-5, Gemini-2.5-Pro vs DeepSeek-V3.1, Qwen3-Coder)FHE-Coder · TFHE tasks across four LLMspass@1 (func_sec)Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy