# NEXUS: Continual Learning of Symbolic Constraints for Safe and Robust Embodied Planning

arXiv: https://arxiv.org/abs/2605.09387 · HTML: https://mlsanity.com/paper/2605.09387/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 40 references that are in the map.
- First posted on arXiv 10 May 2026.

## Builds on (most cited first, 28 of 28)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models](https://mlsanity.com/paper/2310.04451/) (2023)
- [ProgPrompt: Generating Situated Robot Task Plans using Large Language Models](https://mlsanity.com/paper/2209.11302/) (2022)
- [SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planning](https://mlsanity.com/paper/2307.06135/) (2023)
- [A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily](https://mlsanity.com/paper/2311.08268/) (2023)
- [Large Language Models as Commonsense Knowledge for Large-Scale Task Planning](https://mlsanity.com/paper/2305.14078/) (2023)
- [AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents](https://mlsanity.com/paper/2503.18666/) (2025)
- [Hierarchical Open-Vocabulary 3D Scene Graphs for Language-Grounded Robot Navigation](https://mlsanity.com/paper/2403.17846/) (2024)
- [SafeAgentBench: A Benchmark for Safe Task Planning of Embodied LLM Agents](https://mlsanity.com/paper/2412.13178/) (2024)
- [SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigation](https://mlsanity.com/paper/2410.08189/) (2024)
- [Plug in the Safety Chip: Enforcing Constraints for LLM-driven Robot Agents](https://mlsanity.com/paper/2309.09919/) (2023)
- [Code-as-Monitor: Constraint-aware Visual Programming for Reactive and Proactive Robotic Failure Detection](https://mlsanity.com/paper/2412.04455/) (2024)
- [Dynamic Planning with a LLM](https://mlsanity.com/paper/2308.06391/) (2023)
- [LoTa-Bench: Benchmarking Language-oriented Task Planners for Embodied Agents](https://mlsanity.com/paper/2402.08178/) (2024)
- [Towards Robust and Secure Embodied AI: A Survey on Vulnerabilities and Attacks](https://mlsanity.com/paper/2502.13175/) (2025)
- [LaMMA-P: Generalizable Multi-Agent Long-Horizon Task Allocation and Planning with LM-Driven PDDL Planner](https://mlsanity.com/paper/2409.20560/) (2024)
- [A Framework for Benchmarking and Aligning Task-Planning Safety in LLM-Based Embodied Agents](https://mlsanity.com/paper/2504.14650/) (2025)
- [SELP: Generating Safe and Efficient Task Plans for Robot Agents with Large Language Models](https://mlsanity.com/paper/2409.19471/) (2024)
- [Modeling Dynamic Environments with Scene Graph Memory](https://mlsanity.com/paper/2305.17537/) (2023)
- [Semantically Safe Robot Manipulation: From Semantic Scene Understanding to Motion Safeguards](https://mlsanity.com/paper/2410.15185/) (2024)
- [MLDT: Multi-Level Decomposition for Complex Long-Horizon Robotic Task Planning with Open-Source Large Language Model](https://mlsanity.com/paper/2403.18760/) (2024)
- [SafeEmbodAI: a Safety Framework for Mobile Robots in Embodied AI Systems](https://mlsanity.com/paper/2409.01630/) (2024)
- [Safe Planner: Empowering Safety Awareness in Large Pre-Trained Models for Robot Task Planning](https://mlsanity.com/paper/2411.06920/) (2024)
- [Graphormer-Guided Task Planning: Beyond Static Rules with LLM Safety Perception](https://mlsanity.com/paper/2503.06866/) (2025)
- [Safe Multiagent Coordination via Entropic Exploration](https://mlsanity.com/paper/2412.20361/) (2024)
- [Self-Corrective Task Planning by Inverse Prompting with Large Language Models](https://mlsanity.com/paper/2503.07317/) (2025)

## Abstract (arXiv)

While Large Language Models (LLMs) have catalyzed progress in embodied intelligence, a fundamental gap between their inherent probabilistic uncertainty and the strict determinism and verifiable safety required in the physical world. To mitigate this gap, this paper introduces NEXUS, a modular framework designed for continual learning in embodied agents. Different from prior works that treat symbolic artifacts merely as static interfaces, NEXUS leverages them for symbolic grounding and knowledge evolution. The framework explicitly decouples physical feasibility from safety specifications: capability of agents is improved through closed-loop execution feedback, while probabilistic risk assessments are grounded into deterministic hard constraints to establish a rigorous pre-action defense. Experiments on SafeAgentBench demonstrate that NEXUS achieves superior task success rates while effectively refusing unsafe instructions, exhibiting robust defense against adversarial attacks, and progressively improving planning efficiency through knowledge accumulation.