大模型基准论文趋势 2023–2026

主要结论

• 大模型基准论文从 2023 年的 2 篇增长到 2026 年的 307 篇，三年间扩大到约 154 倍。
• NeurIPS 是发大模型基准论文最多的会议，2023–2026 年共 256 篇，占四个会议总量的 47%。
• 交叉方向里涨得最快的是AI 智能体：同时属于两个主题的论文从 2023 年的 1 篇增至 2026 年的 116 篇。
• 在「评测与基准」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的模型即裁判是 27 倍，大模型基准是 154 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• NeurIPS 2026A Free Lunch in LLM Compression: Revisiting Retraining after Pruning
• ICML 2026Controlled LLM Training on Spectral Sphere
• ICLR 2026Hey, That's My Model! Introducing Chain & Hash, An LLM Fingerprinting Technique
• CVPR 20263DrawAgent Teaching LLM to Draw in 3D with Early Contrastive
• NeurIPS 2025ACCO: Accumulate While You Communicate for Communication-Overlapped Sharded LLM Training
• ICML 2025Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM’s Reasoning Capability
• ICLR 2025Catastrophic Failure of LLM Unlearning via Quantization
• CVPR 2025Period-LLM: Extending the Periodic Capability of Multimodal Large Language Model
• NeurIPS 2024Large Language Models' Expert-level Global History Knowledge Benchmark (HiST-LLM)
• ICML 2024Characterizing ResNet's Universal Approximation Capability
• ICLR 2024Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactuals
• CVPR 2024Koala: Key Frame-Conditioned Long Video-LLM
• NeurIPS 2023Quantizable Transformers: Removing Outliers by Helping Attention Heads Do Nothing
• NeurIPS 2026Accelerating LLM Pre-Training through Flat-Direction Dynamics Enhancement
• ICML 2026LLM Priors for ERM over Programs
• ICLR 2026How Learning Rate Decay Wastes Your Best Data in Curriculum-Based LLM Pretraining
• CVPR 20263D-VCD Hallucination Mitigation in 3D-LLM Embodied Agents through Visual Contrastive
• NeurIPS 2025BrainEC-LLM: Brain Effective Connectivity Estimation by Multiscale Mixing LLM
• ICML 2025Position: Medical Large Language Model Benchmarks Should Prioritize Construct Validity
• ICLR 2025Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates

全部大模型基准论文

共 544 篇，第 5 / 11 页

201. NeurIPS 2026Confidence Estimation via Decoupled Smoothing for Dynamic LLM Routing and Aggregation
202. NeurIPS 2026Consolidating Rewarded Perturbations for LLM Post-Training
203. NeurIPS 2026ContractBench: Can LLM Agents Preserve Observation Contracts?
204. NeurIPS 2026Contrastive Representation Shaping for LLM Unlearning
205. NeurIPS 2026Correlation-Aware Contextual Bandits with Surrogate Rewards for LLM Routing
206. NeurIPS 2026CurveRL: Principled Distribution-Aware Context Reweighting for LLM Reasoning
207. NeurIPS 2026DAPS: Dependency-Aware Premise Selection for LLM Theorem Proving
208. NeurIPS 2026Decentralized Aggregation of LLM Predictions via Wagering Mechanisms
209. NeurIPS 2026Demystifying Numerical Errors in LLM Inference: Achieving Reproducible Inference for Mission-Critical Tasks with HEAL
210. NeurIPS 2026DICE: Decoupling Capability from Intervention Necessity in LLM Tutoring
211. NeurIPS 2026Differential Item Functioning as an Item-Level Diagnostic for LLM Benchmarks
212. NeurIPS 2026DistDebug-Bench: Can LLM Agents Diagnose Bugs in Distributed Systems?
213. NeurIPS 2026Don't Always Pick the Highest-Performing Model: An Information Theoretic View of LLM Ensemble Selection
214. NeurIPS 2026Efficient Evaluation of LLM Performance with Statistical Guarantees
215. NeurIPS 2026Efficient Gradient-Aware Asynchronous Reinforcement Learning for LLM Post-Training
216. NeurIPS 2026ENGINE: Endogenous Variational MultiScale Optimization for Zeroth-Order LLM Fine-Tuning
217. NeurIPS 2026Evaluating Physical Reasoning in LLM Agents Requires Construction Benchmarks
218. NeurIPS 2026Every Bit, Everywhere, All At Once: A Binomial Multibit LLM Watermark
219. NeurIPS 2026Fast-dLLM++: Fr\'{e}chet Profile Decoding for Faster Diffusion LLM Inference
220. NeurIPS 2026FEP-Agent: Grounding LLM Agent Self-Evolution in Active Inference with Semantic Memory
221. NeurIPS 2026Fisher-R1: Training LLM Agents for Reliable Hypothesis Testing
222. NeurIPS 2026Forced Deferral: Manipulating Routing Decisions in Multimodal LLM Cascades
223. NeurIPS 2026Forced Orders: What LLM Leaderboards Hide About Model Comparisons
224. NeurIPS 2026From Chats to Markets: AgenticPay for LLM-Powered Negotiation in Multi-Agent Commerce
225. NeurIPS 2026From History to State: Constant-Context Skill Learning for LLM Agents
226. NeurIPS 2026From Infrastructure to Interface, the AI Value Chain Drives LLM Homogenization
227. NeurIPS 2026From Local Skills to Long-Horizon Tasks: Progressive Skill Exploration for LLM Web Agents
228. NeurIPS 2026From Reasoning Chains to Verifiable Subproblems: Curriculum Reinforcement Learning Enables Credit Assignment for LLM Reasoning
229. NeurIPS 2026From Talking Words to Sharing Thoughts: Scalable Multi-LLM Aggregation via Structured Message Passing
230. NeurIPS 2026From Walls to Synergy: A Joint LLM-Evolution Framework for MILP Solvers
231. NeurIPS 2026GraphInstruct: A Progressive Benchmark for Diagnosing Capability Gaps in LLM Graph Generation
232. NeurIPS 2026GroupMemBench: Benchmarking LLM Agent Memory in Multi-Party Conversations
233. NeurIPS 2026HARP: Training-Free Dual-Profile Agentic Communication for LLM-Based Recommendation
234. NeurIPS 2026Hidden Positives: Why Code Retrieval Benchmarks Underestimate Model Quality
235. NeurIPS 2026HireWatch: Evaluating LLM Compliance with U.S. Employment Law Under Contextual Pressure
236. NeurIPS 2026Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering
237. NeurIPS 2026Improving LLM Final Representations with Inter-Layer Geometry
238. NeurIPS 2026Instrumental Choices: Measuring the Propensity of LLM Agents to Pursue Instrumental Behaviors
239. NeurIPS 2026Jacobian Scopes: A Unified Geometric Framework for Token-Level LLM Attributions
240. NeurIPS 2026Joint Sequence--Vocabulary Selection for Efficient LLM Distillation
241. NeurIPS 2026JuICE: A Benchmark for Evaluating LLM-Judge in Identifying Cultural Errors
242. NeurIPS 2026Knowing When to Ask: Segment-Level Credit Assignment for LLM Tool Use
243. NeurIPS 2026Learning Cost-Efficient Autoscaling for Latency-Constrained Disaggregated LLM Serving
244. NeurIPS 2026Learning What to Forget: Improving LLM Unlearning via Learned Token-Level Importance
245. NeurIPS 2026LLM Agents Already Know When to Call Tools - Even Without Reasoning
246. NeurIPS 2026LLM-AutoSciLab: Closed-Loop Scientific Law Discovery via Active Experimentation with LLMs
247. NeurIPS 2026LLM-Enhanced Random Forests in Orthogonal Hyperbolic Subspaces for Tabular Learning
248. NeurIPS 2026MAGE: All-[MASK] Block Already Knows Where to Look in Block Diffusion LLM
249. NeurIPS 2026Measuring Collapse and Correction in Homogeneous-Panel LLM Debate
250. NeurIPS 2026MemeEconomy : Do LLM Agents Trade Ethics for Survival?

常见问题

2023–2026 年四大会议一共有多少篇大模型基准论文？

共 544 篇，按年份分别是 2023 年 2 篇、2024 年 61 篇、2025 年 174 篇、2026 年 307 篇。

NeurIPS 2026 有多少篇大模型基准论文？

NeurIPS 2026 有 138 篇大模型基准论文，上一届是 92 篇。

ICLR 2026 有多少篇大模型基准论文？

ICLR 2026 有 103 篇大模型基准论文，上一届是 50 篇。

ICML 2026 有多少篇大模型基准论文？

ICML 2026 有 60 篇大模型基准论文，上一届是 24 篇。

CVPR 2026 有多少篇大模型基准论文？

CVPR 2026 有 6 篇大模型基准论文，上一届是 8 篇。

哪个会议的大模型基准论文最多？

NeurIPS，2023–2026 年共 256 篇。