AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

LLMs Unleashed: Generating Protocol Code from RFC Specifications

Junfeng Long, Jinshu Su, Biao Han

AAAI 2026 · Large language models › Language, safety and interpretability · approach: Controlled text generation · 0 citations (OpenAlex)

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
provide full RFC in one input instead of chapter-wise or fixed-length chunking (ablation)RFC component extraction · ICMP, TCP, QUIC functional component extractionF1Improved
chapter-wise multi-turn chunking of RFC (ablation)RFC component extraction · TCP, QUIC extractionprecisionHurt
add summarized RFC context to prompt (ablation)Qwen2.5 TCP generation · TCP code generationprotocol behavior: 0.6095 -> 0.8571Improved
add raw RFC excerpts to prompt (ablation)Qwen-coder TCP generation · TCP code generationprotocol behavior: 0.9524 -> 0.5619Hurt
add summarized RFC context to prompt (ablation)Qwen-coder TCP generation · TCP code generationComposite Success Rate: 0.93 -> 0.70Hurt
add context to prompt for GPT-4o (ablation)GPT-4o TCP generation · TCP code generationprotocol behavior: 0.6571 -> 0.7143Improved
inject diagram-derived handshake sequence into prompt (ablation)TCP generation with summaries · TCP teardown flag coverageflag coverage: 0.66 -> 0.86 (Qwen2.5)Improved
use Qwen-Coder instead of general Qwen2.5ICMP generation · ICMP code generationComposite Success Rate (%): 95.0 -> 60.0Hurt
use APG LLM pipeline instead of rule-based SageICMP generation · ICMP generation timeminutes: 19 min -> 6 minImproved
use APG instead of Sage for IGMPIGMP generation · IGMP generation timeminutes: 2 min -> 3 min (Qwen2.5), 2 min -> 1 min (Qwen-coder)Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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