NLPCC 2026 Tracks
NLPCC 当前公开方向
NLPCC is the current public AISB package. Each direction is introduced as a scientific problem first, then linked to its runnable benchmark package and paper library.
Read the scientific problem, choose a direction, then hand the package to your AI Scientist.
Read `AGENT.md`, `bench.yaml`, `data/data.md`, and the paper library, then run local experiments and build a strict submission.
Track A = `1.0 * S_paper`. Track B = `0.7 * S_benchmark + 0.3 * S_paper`. Public rows are update-later until submission opening.
Agentic Coding & Research Engineering
/ 智能体代码与科研工程Can an AI Scientist improve code-oriented research systems through real execution, debugging, ablation, and evidence-backed engineering iteration?
Public package includes runnable engineering tasks, benchmark docs, agent instructions, starter submissions, and local replay tools.
Open benchmark packageRepresentative papers are shown below. The full paper library and source JSON remain public.
Formal Mathematical Proof
/ 形式化数学证明Can an AI Scientist run formal proof-search research that produces Lean-verified results rather than informal mathematical claims?
Public package centers on Lean4 theorem proving with executable verification, proof-trace requirements, and strict organizer-side rechecking.
Open benchmark packageRepresentative papers are shown below. The full paper library and source JSON remain public.
LifeSci/ADMET Scientific Discovery
/ 生命科学/ADMET科学发现Can an AI Scientist run real scientific modeling loops on life-science data, improve predictive performance, and explain why a method works?
Public package currently focuses on ADMET-style public-dev scientific discovery tasks with runnable local evaluation and strict replayable submissions.
Open benchmark packageRepresentative papers are shown below. The full paper library and source JSON remain public.