Skip to content

Plan Right, Then Plan Tight: Symbolic RL for Efficient Embodied Reasoning

Jun 2026 · arXiv.org · Vol abs/2606.31260 · 0 citations · 32 references
Computer Science

TL;DR

This work shows that a single BDDL specification, automatically constructed from open-world video evidence or curated tasks, can serve as a shared interface for data construction, plan verification, and reward design and introduces GroupAdapt, a difficulty-aware length schedule that uses the in-batch group pass rate as a zero-cost signal so that hard prompts get wider length tolerance and automatically tighten as their pass rate improves.

Abstract

Embodied task planning asks an agent to turn a natural-language instruction into an executable sequence of actions in a physical scene, and is a building block for household, assistive, and service robots. Recent prompting-based and reinforcement-learning planners generate fluent action text but lack a cheap deterministic check that the produced plan is valid in the target world, while high-fidelity simulation is too slow to serve as an inner-loop training signal. The general problem is therefore how to obtain verifiable supervision and rewards for embodied planners without relying on string-level matching or full simulation. Here we show that a single BDDL specification, automatically constructed from open-world video evidence or curated tasks, can serve as a shared interface for data construction, plan verification, and reward design. A video-to-BDDL parser, an LLM verifier, and a lightweight symbolic engine together supply dense feedback at millisecond latency. We further introduce GroupAdapt, a difficulty-aware length schedule that uses the in-batch group pass rate as a zero-cost signal so that hard prompts get wider length tolerance and automatically tighten as their pass rate improves. Under the guidance of the proposed verifier and GroupAdapt schedule, the 8B planner attains a Strict-Pass score of 97.3 on BEHAVIOR-1000, yielding a 25.9 percent relative improvement over the Qwen3-8B baseline. This result exceeds the strongest large-model baseline by 3.5 percent, while simultaneously compressing the response length by 79 percent to 207 tokens, demonstrating both effectiveness and efficiency.

View source

Similar papers

Review Open access Jul 2026

Large Language Models for Task Planning in Embodied AI: A Survey

A structured taxonomy is presented that organizes existing work into three complementary paradigms that represent dominant architectural tendencies in current LLM-based embodied task planning research, and compares these paradigms along dimension of accuracy, robustness, scalability, efficiency, and sim-to-real transfer.

Zhen Zhang · 0 citations
Open access Aug 2026

Large Language Model-Driven Symbolic Planning for Long-Horizon Robotic Manipulation Tasks

VLA-SP (Vision-Language-Action via Symbolic Planning), a two-stage Embodied Vision-Language-Action framework, enabling fully automated robotic execution from speech and vision inputs is proposed, demonstrating the strong interpretability, executability, and cross-platform applicability of the framework.

Hanzhuo Zhang, Jiahao Xu, Yicheng Xu et al. · 0 citations
Preprint Jul 2026

A Few Words Go a Long Way: Language Guided Robot Policy Synthesis

The results demonstrate that the synthesized skill library enables the system to transfer to novel tasks with decreasing human intervention, providing a steerable and data-efficient alternative to black-box robot learning.

Daphne Chen, A. Jain, E. Goossen et al. · 0 citations
Preprint Aug 2026

From Solver Feedback to Faithful Plans: Multi-Role Reinforcement Learning for Symbolic Planning

Reliable planning requires converting natural-language instructions into executable symbolic specifications, yet large language models remain brittle without costly PDDL annotations and may exploit solver success in semantically unfaithful ways. We study how to learn faithful natural-language-to-PDDL formalization using only solver feedback, without human-written demonstrations. We propose a solvergrounded multi-role reinforcement learning framework where a single language model acts as an Actor, Judge, and Editor for generation, verification, and repair. The Actor proposes PDDL specifications, the Judge provides a solver-calibrated quality signal, and the Editor performs bounded diagnostic-conditioned refinement. On PlanBench, our method improves average success from 35.5% for LLM+P to 70.8%, achieves 66.3% faithful success, and reduces semantic drift to 6.4%. These results show that organizing solver feedback into generation, verification, and repair roles enables more scalable and faithful annotation-free symbolic planning

Cheng Zhang, Yikai Mao, Shan Liu et al. · 0 citations
#artificial intelligence Preprint Aug 2026

Teach and Grow: An Agent-Centered Architecture for General Robot Learning

End-to-end vision-language-action (VLA) and world-action models offer an elegant route to general-purpose robotics, but their reliability is bounded by validated physical coverage. When an unfamiliar object, sensor, embodiment, or contact falls outside that coverage and no validated fallback exists, correcting the failure requires new robot data, a policy update, and regression testing. This recurring burden is the retraining tax. Unlike text, embodied data must often be created by operating machines. We present Teach-and-Grow Learning (TGL), an agent-centered architecture for general robot learning. In its general form, a multimodal agent turns a few successful demonstrations into reusable Skill Blocks: closed-loop behaviors for meaningful subgoals. In a new scene, the agent grounds and composes these blocks, selects learned or geometric tools, observes the physical outcome, and revises the route when execution departs from intent. A Skill Library stores executable behavior, while structured Experience Memory carries forward success, failure, and repair. New tasks are acquired without task-specific policy retraining. Our LIBERO evaluation attains state-of-the-art performance; controlled studies expose skill induction, persistent reuse, and agent-directed adaptation. Finally, we propose the Teach-and-Grow scaling-law hypothesis: if X denotes effective reusable experience, future-task error and teaching demand should approach irreducible floors as power laws in X. The architecture therefore treats deployment as a period of continued learning, in which one task can make the next easier.

Chang Nie, Zhe Liu, Hesheng Wang · 0 citations
Preprint Aug 2026

HarnessWAM: Bridging Prediction and Deliberation in World Action Models

Results demonstrate that model-external structured state maintenance and closed-loop agentic decision making can effectively extend the local control capabilities of WAMs into embodied task execution that is plannable, verifiable, and recoverable.

Zhaopeng Gu, Bingke Zhu, Tianxin Lin et al. · 0 citations