规划安全论文趋势 2023–2026

主要结论

• 规划安全论文从 2023 年的 33 篇增长到 2026 年的 37 篇，三年间扩大到约 1.1 倍。
• NeurIPS 是发规划安全论文最多的会议，2023–2026 年共 59 篇，占四个会议总量的 56%。
• 交叉方向里涨得最快的是社会层面 · safety：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 5 篇。
• 在「博弈与规划」的 5 个主题里，它的 2026 年论文数排第 5；同组增长最快的经典规划是 3.3 倍，规划安全是 1.1 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 2026PASSAGE: A Real-Terrain Benchmark for Trustworthy Constrained Path Planning
• ICML 2026Constrained Bayesian Experimental Design via Online Planning
• ICLR 2026Superficial Safety Alignment Hypothesis
• CVPR 2026ActiveAD Planning-Oriented Active Learning for End-to-End Autonomous Driving
• NeurIPS 2025Refusal Direction is Universal Across Safety-Aligned Languages
• ICML 2025Goal-Space Planning with Subgoal Models
• ICLR 2025Durable Quantization Conditioned Misalignment Attack on Large Language Models
• NeurIPS 2024Introspective Planning: Aligning Robots' Uncertainty with Inherent Task Ambiguity
• ICML 2024MC-GTA: Metric-Constrained Model-Based Clustering using Goodness-of-fit Tests with Autocorrelations
• ICLR 2024Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions
• CVPR 2024Anatomically Constrained Implicit Face Models
• NeurIPS 2023Experiment Planning with Function Approximation
• ICML 2023Constrained Monotonic Neural Networks
• ICLR 2023Integrating Symmetry into Differentiable Planning with Steerable Convolutions
• NeurIPS 2026Ordinal Geometry Complements Reconstruction: Diagnosing Planning with Compressed Value Functions
• ICML 2026On the Ability of Transformers to Verify Plans
• ICLR 2026Mitigating the Safety Alignment Tax with Null-Space Constrained Policy Optimization
• CVPR 2026HQC-NBV A Hybrid Quantum-Classical View Planning Approach
• NeurIPS 2025Alignment of Large Language Models with Constrained Learning
• ICML 2025Training Deep Learning Models with Norm-Constrained LMOs

全部规划安全论文

共 59 篇，第 1 / 2 页

1. NeurIPS 2026A Single Neuron Is Sufficient to Bypass Safety Alignment in Large Language Models
2. NeurIPS 2026Causal-Geo: Neuro-Symbolic Spatial Grounding for Situated Agent Planning
3. NeurIPS 2026Compositional Training-Free Diffusion Planning for Long-Horizon Multiple Reach-Avoid Tasks
4. NeurIPS 2026Constrained MDPs with Trajectory Constraints
5. NeurIPS 2026Constraint-Aware Influence Estimation in Deep Constrained Learning
6. NeurIPS 2026DARTS: Targeting Prognostic Covariates in Budget-Constrained Sequential Experiments
7. NeurIPS 2026Decomposing One Professional-Framing Pipeline: Which Components Shift LLM Safety Boundaries?
8. NeurIPS 2026DiRecT: Safe Diffusion-Based Planning via Receding-Horizon Denoising
9. NeurIPS 2026Exact Recovery of Lipschitz Orthogonal Coordinate Transformations via Constrained Normalizing Flows
10. NeurIPS 2026Last-Iterate Convergence of Single-Loop Stochastic Methods for Constrained Convex-Concave Minimax Problems
11. NeurIPS 2026Learning Chance-Constrained MDPs with Bellman Distributional Certificates
12. NeurIPS 2026LPS-Bench: Benchmarking Safety Awareness of Computer-Use Agents in Long-Horizon Planning under Benign and Adversarial Scenarios
13. NeurIPS 2026MindShape: Superquadric-Constrained High-Fidelity 3D Reconstruction from fMRI
14. NeurIPS 2026Ordinal Geometry Complements Reconstruction: Diagnosing Planning with Compressed Value Functions
15. NeurIPS 2026PASSAGE: A Real-Terrain Benchmark for Trustworthy Constrained Path Planning
16. NeurIPS 2026Personalized Safety in Federated Fine-Tuning of Large Language Models
17. NeurIPS 2026PoSafeNet: Structured Safety Learning via Compositional Projection
18. NeurIPS 2026Scalable Neural Safety Certification via Monotonicity
19. NeurIPS 2026Soteria: Formally Verified Planning with Runtime Enforcement for Safe LLM Agents
20. NeurIPS 2026Subprocess-Constrained Markov Decision Processes
21. NeurIPS 2026Trajectory Planning without Trajectory Data: A Manifold-Guided Approach
22. NeurIPS 2025Alignment of Large Language Models with Constrained Learning
23. NeurIPS 2025Constrained Diffusers for Safe Planning and Control
24. NeurIPS 2025Don’t Trade Off Safety: Diffusion Regularization for Constrained Offline RL
25. NeurIPS 2025LexiCon: a Benchmark for Planning under Temporal Constraints in Natural Language
26. NeurIPS 2025LLM Safety Alignment is Divergence Estimation in Disguise
27. NeurIPS 2025Provably Efficient RL under Episode-Wise Safety in Constrained MDPs with Linear Function Approximation
28. NeurIPS 2025Refusal Direction is Universal Across Safety-Aligned Languages
29. NeurIPS 2024Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies
30. NeurIPS 2024Confident Natural Policy Gradient for Local Planning in $q_\pi$-realizable Constrained MDPs
31. NeurIPS 2024Conformalized Multiple Testing after Data-dependent Selection
32. NeurIPS 2024Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained Optimization
33. NeurIPS 2024Introspective Planning: Aligning Robots' Uncertainty with Inherent Task Ambiguity
34. NeurIPS 2024Jailbreaking Large Language Models Against Moderation Guardrails via Cipher Characters
35. NeurIPS 2024Navigating the Safety Landscape: Measuring Risks in Finetuning Large Language Models
36. NeurIPS 2024Safety through feedback in Constrained RL
37. NeurIPS 2023$p$-Poisson surface reconstruction in curl-free flow from point clouds
38. NeurIPS 2023Accelerating Motion Planning via Optimal Transport
39. NeurIPS 2023Asynchronous Proportional Response Dynamics: Convergence in Markets with Adversarial Scheduling
40. NeurIPS 2023Demographic Parity Constrained Minimax Optimal Regression under Linear Model
41. NeurIPS 2023DICES Dataset: Diversity in Conversational AI Evaluation for Safety
42. NeurIPS 2023Experiment Planning with Function Approximation
43. NeurIPS 2023Fully Dynamic $k$-Clustering in $\tilde O(k)$ Update Time
44. NeurIPS 2023How do Minimum-Norm Shallow Denoisers Look in Function Space?
45. NeurIPS 2023Information-guided Planning: An Online Approach for Partially Observable Problems
46. NeurIPS 2023Mitigating Over-smoothing in Transformers via Regularized Nonlocal Functionals
47. NeurIPS 2023Near-Optimal $k$-Clustering in the Sliding Window Model
48. NeurIPS 2023Online Ad Procurement in Non-stationary Autobidding Worlds
49. NeurIPS 2023Online POMDP Planning with Anytime Deterministic Guarantees
50. NeurIPS 2023Optimistic Exploration in Reinforcement Learning Using Symbolic Model Estimates

常见问题

2023–2026 年四大会议一共有多少篇规划安全论文？

共 105 篇，按年份分别是 2023 年 33 篇、2024 年 16 篇、2025 年 19 篇、2026 年 37 篇。

NeurIPS 2026 有多少篇规划安全论文？

NeurIPS 2026 有 21 篇规划安全论文，上一届是 7 篇。

ICLR 2026 有多少篇规划安全论文？

ICLR 2026 有 4 篇规划安全论文，上一届是 5 篇。

ICML 2026 有多少篇规划安全论文？

ICML 2026 有 8 篇规划安全论文，上一届是 7 篇。

CVPR 2026 有多少篇规划安全论文？

CVPR 2026 有 4 篇规划安全论文。

哪个会议的规划安全论文最多？

NeurIPS，2023–2026 年共 59 篇。