大模型基准论文趋势 2023–2026

能力评测

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 544 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

大模型基准论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202320002
2024241321361
20259250248174
2026138103606307

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

全部大模型基准论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 307 篇，第 5 / 7 页

  1. NeurIPS 2026Confidence Estimation via Decoupled Smoothing for Dynamic LLM Routing and Aggregation
  2. NeurIPS 2026Consolidating Rewarded Perturbations for LLM Post-Training
  3. NeurIPS 2026ContractBench: Can LLM Agents Preserve Observation Contracts?
  4. NeurIPS 2026Contrastive Representation Shaping for LLM Unlearning
  5. NeurIPS 2026Correlation-Aware Contextual Bandits with Surrogate Rewards for LLM Routing
  6. NeurIPS 2026CurveRL: Principled Distribution-Aware Context Reweighting for LLM Reasoning
  7. NeurIPS 2026DAPS: Dependency-Aware Premise Selection for LLM Theorem Proving
  8. NeurIPS 2026Decentralized Aggregation of LLM Predictions via Wagering Mechanisms
  9. NeurIPS 2026Demystifying Numerical Errors in LLM Inference: Achieving Reproducible Inference for Mission-Critical Tasks with HEAL
  10. NeurIPS 2026DICE: Decoupling Capability from Intervention Necessity in LLM Tutoring
  11. NeurIPS 2026Differential Item Functioning as an Item-Level Diagnostic for LLM Benchmarks
  12. NeurIPS 2026DistDebug-Bench: Can LLM Agents Diagnose Bugs in Distributed Systems?
  13. NeurIPS 2026Don't Always Pick the Highest-Performing Model: An Information Theoretic View of LLM Ensemble Selection
  14. NeurIPS 2026Efficient Evaluation of LLM Performance with Statistical Guarantees
  15. NeurIPS 2026Efficient Gradient-Aware Asynchronous Reinforcement Learning for LLM Post-Training
  16. NeurIPS 2026ENGINE: Endogenous Variational MultiScale Optimization for Zeroth-Order LLM Fine-Tuning
  17. NeurIPS 2026Evaluating Physical Reasoning in LLM Agents Requires Construction Benchmarks
  18. NeurIPS 2026Every Bit, Everywhere, All At Once: A Binomial Multibit LLM Watermark
  19. NeurIPS 2026Fast-dLLM++: Fr\'{e}chet Profile Decoding for Faster Diffusion LLM Inference
  20. NeurIPS 2026FEP-Agent: Grounding LLM Agent Self-Evolution in Active Inference with Semantic Memory
  21. NeurIPS 2026Fisher-R1: Training LLM Agents for Reliable Hypothesis Testing
  22. NeurIPS 2026Forced Deferral: Manipulating Routing Decisions in Multimodal LLM Cascades
  23. NeurIPS 2026Forced Orders: What LLM Leaderboards Hide About Model Comparisons
  24. NeurIPS 2026From Chats to Markets: AgenticPay for LLM-Powered Negotiation in Multi-Agent Commerce
  25. NeurIPS 2026From History to State: Constant-Context Skill Learning for LLM Agents
  26. NeurIPS 2026From Infrastructure to Interface, the AI Value Chain Drives LLM Homogenization
  27. NeurIPS 2026From Local Skills to Long-Horizon Tasks: Progressive Skill Exploration for LLM Web Agents
  28. NeurIPS 2026From Reasoning Chains to Verifiable Subproblems: Curriculum Reinforcement Learning Enables Credit Assignment for LLM Reasoning
  29. NeurIPS 2026From Talking Words to Sharing Thoughts: Scalable Multi-LLM Aggregation via Structured Message Passing
  30. NeurIPS 2026From Walls to Synergy: A Joint LLM-Evolution Framework for MILP Solvers
  31. NeurIPS 2026GraphInstruct: A Progressive Benchmark for Diagnosing Capability Gaps in LLM Graph Generation
  32. NeurIPS 2026GroupMemBench: Benchmarking LLM Agent Memory in Multi-Party Conversations
  33. NeurIPS 2026HARP: Training-Free Dual-Profile Agentic Communication for LLM-Based Recommendation
  34. NeurIPS 2026Hidden Positives: Why Code Retrieval Benchmarks Underestimate Model Quality
  35. NeurIPS 2026HireWatch: Evaluating LLM Compliance with U.S. Employment Law Under Contextual Pressure
  36. NeurIPS 2026Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering
  37. NeurIPS 2026Improving LLM Final Representations with Inter-Layer Geometry
  38. NeurIPS 2026Instrumental Choices: Measuring the Propensity of LLM Agents to Pursue Instrumental Behaviors
  39. NeurIPS 2026Jacobian Scopes: A Unified Geometric Framework for Token-Level LLM Attributions
  40. NeurIPS 2026Joint Sequence--Vocabulary Selection for Efficient LLM Distillation
  41. NeurIPS 2026JuICE: A Benchmark for Evaluating LLM-Judge in Identifying Cultural Errors
  42. NeurIPS 2026Knowing When to Ask: Segment-Level Credit Assignment for LLM Tool Use
  43. NeurIPS 2026Learning Cost-Efficient Autoscaling for Latency-Constrained Disaggregated LLM Serving
  44. NeurIPS 2026Learning What to Forget: Improving LLM Unlearning via Learned Token-Level Importance
  45. NeurIPS 2026LLM Agents Already Know When to Call Tools - Even Without Reasoning
  46. NeurIPS 2026LLM-AutoSciLab: Closed-Loop Scientific Law Discovery via Active Experimentation with LLMs
  47. NeurIPS 2026LLM-Enhanced Random Forests in Orthogonal Hyperbolic Subspaces for Tabular Learning
  48. NeurIPS 2026MAGE: All-[MASK] Block Already Knows Where to Look in Block Diffusion LLM
  49. NeurIPS 2026Measuring Collapse and Correction in Homogeneous-Panel LLM Debate
  50. NeurIPS 2026MemeEconomy : Do LLM Agents Trade Ethics for Survival?

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查大模型基准在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "llm-benchmarks"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

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。

「评测与基准」下的其他主题