Safety in Planning papers, 2023–2026

Key findings

• Safety in Planning went from 33 papers in 2023 to 37 in 2026, roughly 1.1x in three years.
• NeurIPS publishes the most Safety in Planning work: 59 papers from 2023 to 2026, 56% of the four-venue total.
• The fastest-growing overlap is with Social aspects · safety: papers tagged with both rose from 0 in 2023 to 5 in 2026.
• Among the 5 topics under Games and Planning, it ranks #5 by 2026 paper count; the fastest grower in the group, Classical Planning, is up 3.3x versus 1.1x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Safety in Planning papers

105 papers, page 1 of 3

1. CVPR 2026ActiveAD Planning-Oriented Active Learning for End-to-End Autonomous Driving
2. CVPR 2026AGENTSAFE Benchmarking the Safety of Embodied Agents on Hazardous Instructions
3. CVPR 2026High-Fidelity Diffusion Face Swapping with ID-Constrained Facial Conditioning
4. CVPR 2026HQC-NBV A Hybrid Quantum-Classical View Planning Approach
5. ICLR 2026Mitigating the Safety Alignment Tax with Null-Space Constrained Policy Optimization
6. ICLR 2026SAFETY-GUIDED FLOW (SGF): A UNIFIED FRAMEWORK FOR NEGATIVE GUIDANCE IN SAFE GENERATION
7. ICLR 2026Superficial Safety Alignment Hypothesis
8. ICLR 2026When a Robot is More Capable than a Human: Learning from Constrained Demonstrators
9. ICML 2026Constrained Bayesian Experimental Design via Online Planning
10. ICML 2026Constrained Meta Reinforcement Learning with Provable Test-Time Safety
11. ICML 2026EMBGuard: Constructing Hazard-Aware Guardrails for Safe Planning in Embodied Agents
12. ICML 2026InfraRL: A Benchmark for Constrained Resource Allocation in Large-Scale Infrastructure Asset Management
13. ICML 2026mHC: Manifold-Constrained Hyper-Connections
14. ICML 2026On the Ability of Transformers to Verify Plans
15. ICML 2026Stochastic Minimum-Cost Reach-Avoid Reinforcement Learning
16. ICML 2026Training-Free Guided Diffusion for Planning: A Unified Framework via Doob’s h-Transform with Safety Guarantees
17. NeurIPS 2026A Single Neuron Is Sufficient to Bypass Safety Alignment in Large Language Models
18. NeurIPS 2026Causal-Geo: Neuro-Symbolic Spatial Grounding for Situated Agent Planning
19. NeurIPS 2026Compositional Training-Free Diffusion Planning for Long-Horizon Multiple Reach-Avoid Tasks
20. NeurIPS 2026Constrained MDPs with Trajectory Constraints
21. NeurIPS 2026Constraint-Aware Influence Estimation in Deep Constrained Learning
22. NeurIPS 2026DARTS: Targeting Prognostic Covariates in Budget-Constrained Sequential Experiments
23. NeurIPS 2026Decomposing One Professional-Framing Pipeline: Which Components Shift LLM Safety Boundaries?
24. NeurIPS 2026DiRecT: Safe Diffusion-Based Planning via Receding-Horizon Denoising
25. NeurIPS 2026Exact Recovery of Lipschitz Orthogonal Coordinate Transformations via Constrained Normalizing Flows
26. NeurIPS 2026Last-Iterate Convergence of Single-Loop Stochastic Methods for Constrained Convex-Concave Minimax Problems
27. NeurIPS 2026Learning Chance-Constrained MDPs with Bellman Distributional Certificates
28. NeurIPS 2026LPS-Bench: Benchmarking Safety Awareness of Computer-Use Agents in Long-Horizon Planning under Benign and Adversarial Scenarios
29. NeurIPS 2026MindShape: Superquadric-Constrained High-Fidelity 3D Reconstruction from fMRI
30. NeurIPS 2026Ordinal Geometry Complements Reconstruction: Diagnosing Planning with Compressed Value Functions
31. NeurIPS 2026PASSAGE: A Real-Terrain Benchmark for Trustworthy Constrained Path Planning
32. NeurIPS 2026Personalized Safety in Federated Fine-Tuning of Large Language Models
33. NeurIPS 2026PoSafeNet: Structured Safety Learning via Compositional Projection
34. NeurIPS 2026Scalable Neural Safety Certification via Monotonicity
35. NeurIPS 2026Soteria: Formally Verified Planning with Runtime Enforcement for Safe LLM Agents
36. NeurIPS 2026Subprocess-Constrained Markov Decision Processes
37. NeurIPS 2026Trajectory Planning without Trajectory Data: A Manifold-Guided Approach
38. ICLR 2025ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning
39. ICLR 2025Conservative Contextual Bandits: Beyond Linear Representations
40. ICLR 2025Durable Quantization Conditioned Misalignment Attack on Large Language Models
41. ICLR 2025SafeDiffuser: Safe Planning with Diffusion Probabilistic Models
42. ICLR 2025Safety-Prioritizing Curricula for Constrained Reinforcement Learning
43. ICML 2025Action-Constrained Imitation Learning
44. ICML 2025Embedding Safety into RL: A New Take on Trust Region Methods
45. ICML 2025Goal-Space Planning with Subgoal Models
46. ICML 2025LIVS: A Pluralistic Alignment Dataset for Inclusive Public Spaces
47. ICML 2025Position: Editing Large Language Models Poses Serious Safety Risks
48. ICML 2025Rejecting Hallucinated State Targets during Planning
49. ICML 2025Training Deep Learning Models with Norm-Constrained LMOs
50. NeurIPS 2025Alignment of Large Language Models with Constrained Learning

FAQ

How many Safety in Planning papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

105 in total: 33 in 2023, 16 in 2024, 19 in 2025, 37 in 2026.

How many Safety in Planning papers are at NeurIPS 2026?

NeurIPS 2026 has 21 Safety in Planning papers, versus 7 the year before.

How many Safety in Planning papers are at ICLR 2026?

ICLR 2026 has 4 Safety in Planning papers, versus 5 the year before.

How many Safety in Planning papers are at ICML 2026?

ICML 2026 has 8 Safety in Planning papers, versus 7 the year before.

How many Safety in Planning papers are at CVPR 2026?

CVPR 2026 has 4 Safety in Planning papers.

Which conference publishes the most Safety in Planning papers?

NeurIPS, with 59 papers from 2023 to 2026.