SharedKV-BT: Node-Local Typed Decisions for Behavior-Tree Agents
cs.RO, cs.CL
Submitted: 2026-10-05
Updated: 2026-10-05
Sources
- Language Models are Few-Shot Learners
- Blockwise Parallel Decoding for Deep Autoregressive Models
- On the Fly Adaptation of Behavior Tree-Based Policies through Reinforcement Learning
- Robot Behavior-Tree-Based Task Generation with Large Language Models
- HBTP: Heuristic Behavior Tree Planning with Large Language Model Reasoning
- VLM-driven Behavior Tree for Context-aware Task Planning
- Code as Policies: Language Model Programs for Embodied Control
- PaLM-E: An Embodied Multimodal Language Model
- Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents
- Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
- ProgPrompt: Generating Situated Robot Task Plans using Large Language Models
- Inner Monologue: Embodied Reasoning through Planning with Language Models
- Surface Form Competition: Why the Highest Probability Answer Isn't Always Right
- Calibrate Before Use: Improving Few-Shot Performance of Language Models
- Efficient Guided Generation for Large Language Models
- Toolformer: Language Models Can Teach Themselves to Use Tools
- LLM-as-Jev: LLMs Are Already Jev-Style Decision Models -- When and How to Fine-Tune Them
- SGLang: Efficient Execution of Structured Language Model Programs
- Hydragen: High-Throughput LLM Inference with Shared Prefixes
- ArborKV: Structure-Aware KV Cache Management for Scaling Tree-based LLM Reasoning
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- ARC: A Reasoning Recipe for Robot Foundation Models
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies