Entity · paper

Freeform Preference Learning for Robotic Manipulation

paperactiveprovisionalfreeform-preference-learning-for-robotic-manipulation-199824bb·1 events·first seen Jul 1, 2026

Aliases: Freeform Preference Learning for Robotic Manipulation

Co-occurring entities

More like this (12)

Freeform Preference Learning Learning Action Priors for Cross-embodiment Robot Manipulation bi-manual robotic manipulation Geometric Action Model for Robot Policy Learning General Preference Reinforcement Learning multi-fingered robotic hand Preference-Aware Rubric Learning Gravity-Weighted Direct Preference Optimization Drifting Preference Optimization Reward Modeling for Multi-Agent Orchestration Operator Learning Training LLMs to Enforce Multi-Level Instruction Hierarchies via Gravity-Weighted Direct Preference Optimization

Recent events (1)

6arXiv · cs.LG·Jul 1, 2026·source ↗

Freeform Preference Learning enables multi-axis natural-language reward design for robot manipulation

Freeform Preference Learning (FPL) replaces binary preference labels in robot learning with natural-language preference axes (e.g., speed, safety, carefulness), allowing annotators to provide pairwise preferences along each axis. A language-conditioned reward model is trained from these annotations and used to optimize a reward-conditioned policy across multiple human-specified dimensions. Evaluated on four real-world and two simulated long-horizon manipulation tasks, FPL outperforms sparse-reward and binary-preference baselines by 38 percentage points, and enables test-time behavioral steering without retraining.

Evaluation and Benchmarking Agent and Tool Ecosystem Freeform Preference Learning Freeform Preference Learning for Robotic Manipulation +1 more