LLM-Flax automates neuro-symbolic robotic task planning with three LLM stages for rule generation, failure recovery, and zero-shot scoring, outperforming manual baselines on MazeNamo grids.
Learning neuro-symbolic skills for bilevel planning
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
fields
cs.RO 5years
2026 5verdicts
UNVERDICTED 5representative citing papers
ReStruct steers robot policies at inference time by reconfiguring task structure with neural automata and synchronous products, claiming up to 25% gains over VLA models in success and preference adherence.
ENAP extracts an emergent Mealy automaton from visuomotor trajectories to act as a high-level planner for a low-level residual policy, yielding up to 27% higher success than end-to-end VLA policies in low-data regimes.
Bilevel optimization with 3R recovery for neuro-symbolic long-horizon planning under logical constraints achieves 80% failure reduction and 57% time reduction on benchmarks.
Human2Any transfers human video demonstrations to robots by representing tasks as object-object interactions and composing learned priors with robot-side planning.
citing papers explorer
-
LLM-Flax : Generalizable Robotic Task Planning via Neuro-Symbolic Approaches with Large Language Models
LLM-Flax automates neuro-symbolic robotic task planning with three LLM stages for rule generation, failure recovery, and zero-shot scoring, outperforming manual baselines on MazeNamo grids.
-
Inference-Time Robot Behavior Steering through Physically-Aware Reconfiguration of Task-Structure
ReStruct steers robot policies at inference time by reconfiguring task structure with neural automata and synchronous products, claiming up to 25% gains over VLA models in success and preference adherence.
-
Emergent Neural Automaton Policies: Learning Symbolic Structure from Visuomotor Trajectories
ENAP extracts an emergent Mealy automaton from visuomotor trajectories to act as a high-level planner for a low-level residual policy, yielding up to 27% higher success than end-to-end VLA policies in low-data regimes.
-
Neuro-Symbolic Learning for Long-Horizon Task Planning Under Complex Logical Constraints
Bilevel optimization with 3R recovery for neuro-symbolic long-horizon planning under logical constraints achieves 80% failure reduction and 57% time reduction on benchmarks.
-
Human2Any: Human-to-Robot Transfer via Constraint-Aware Compositional Planning
Human2Any transfers human video demonstrations to robots by representing tasks as object-object interactions and composing learned priors with robot-side planning.