mlsanityData to 14 Oct 2026

SharedKV-BT: Node-Local Typed Decisions for Behavior-Tree Agents

arXiv 2610.07327 ↗First posted 5 Oct 2026cs.RO cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Agent tasks require sequences of interdependent decisions. Autoregressive models support more flexible decision interfaces than conventional classifiers but incur the latency of token-by-token generation. Recent shared-prefix methods reduce this cost by reusing encoded context and scoring multiple decisions in parallel, but do not model decision dependencies or verify execution. We propose SharedKV-BT, where each active node of a behavior tree (BT) exposes stage-local fields and candidates, and Shared-KV scores the candidates in parallel and passes the selected decision to a separate execution system. We tested SharedKV-BT on robot manipulation, mobile navigation, and computer-use tasks. Across three tasks, SharedKV-BT made typed decisions 2.36-4.15 times faster than prompt-matched autoregressive decoding. On the manipulation task, node-local Shared-KV improved joint decision accuracy from 75% to 94% and closed-loop success from 0% to 60%. Fixed-score policy replay showed that stage gating prevented out-of-order actions and external postconditions prevented premature completion.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 24 of its 50 references that are in the map. First posted on arXiv 5 Oct 2026.

Builds on

24 of 50 references.

References · 24

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2025Qwen3 Technical Reportcited by 8,820
  3. 2024Qwen2.5 Technical Reportcited by 4,942
  4. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  5. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,348
  6. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,071
  7. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,392
  8. 2022Code as Policies: Language Model Programs for Embodied Controlcited by 1,210
  9. 2023SGLang: Efficient Execution of Structured Language Model Programscited by 1,141
  10. 2022Inner Monologue: Embodied Reasoning through Planning with Language Modelscited by 1,081
  11. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,035
  12. 2022ProgPrompt: Generating Situated Robot Task Plans using Large Language Modelscited by 611
12 more
  1. 2020robosuite: A Modular Simulation Framework and Benchmark for Robot Learningcited by 511
  2. 2018Blockwise Parallel Decoding for Deep Autoregressive Modelscited by 323
  3. 2021Surface Form Competition: Why the Highest Probability Answer Isn't Always Rightcited by 263
  4. 2024Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scalecited by 223
  5. 2023Efficient Guided Generation for Large Language Modelscited by 200
  6. 2024Hydragen: High-Throughput LLM Inference with Shared Prefixescited by 73
  7. 2023Robot Behavior-Tree-Based Task Generation with Large Language Modelscited by 23
  8. 2024HBTP: Heuristic Behavior Tree Planning with Large Language Model Reasoningcited by 4
  9. 2025VLM-driven Behavior Tree for Context-aware Task Planningcited by 4
  10. 2026ArborKV: Structure-Aware KV Cache Management for Scaling Tree-based LLM Reasoningcited by 4
  11. 2026LLM-as-Jev: LLMs Are Already Jev-Style Decision Models -- When and How to Fine-Tune Themcited by 4
  12. 2025On the Fly Adaptation of Behavior Tree-Based Policies through Reinforcement Learningcited by 1

Built on by

Not cited yet.