← Back to all news
arXiv AI By Matteo Merler, Giovanni Bonetta, Davide Zago, Rossella Cancelliere, Bernardo Magnini

Selective Agent Guidance via Entropy: Learning Autonomous Policies from Imperfect VLM Teachers

Read the original on arXiv AI →

The paper introduces SAGE, a framework that selectively queries a Vision‑Language Model (VLM) teacher only when the learner is uncertain, using the teacher’s suggestions to guide training and distill them into a lightweight reinforcement learning policy. SAGE weights teacher actions by environment‑derived advantages, allowing the policy to improve beyond the imperfect VLM. Experiments on sparse‑reward visual reasoning and navigation tasks show that the learned policies can act without VLM guidance at evaluation, reduce VLM usage during training, and sometimes outperform the teacher itself.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Sep 21

Prompt-Driven Exploration: Language as an Exploration Space for VLA Reinforcement Learning

arXiv:2607.08837v4 Announce Type: replace-cross Abstract: Exploration is essential to RL since a policy cannot improve by repeatedly sampling the behaviors it already prefers. Standard methods inject...

By Sunshine Jiang, John Marangola, David Zhang, Raghuram Kowdeed, Ruiyang Luo, Nitish Dashora, Richard Li, Pulkit Agrawal, Zhang-Wei Hong
llmsreinforcement-learningroboticsmultimodal
More like this →
arXiv AI
Aug 28

Decoupling Planning and Control for Instructable Agents

The paper introduces Instruct-to-Act, a system that decouples planning and control by combining a vision‑language model (VLM) planner with a world‑model controller. The VLM generates sparse, high‑level text instructions, while the controller executes them at high frequency, trained via relabeling rollouts with synthetic instructions and joint optimization of behavior cloning, reward, and world‑model objectives. Across seven embodied environments—including multi‑agent settings—this approach outperforms controller‑only and direct VLM action methods, maintains fast control, and allows swapping pretrained VLM planners without fine‑tuning, achieving competitive results with strong baselines on most tasks.

By Zineng Tang, Kelsey R. Allen, Sjoerd van Steenkiste, Ishita Dasgupta, Alane Suhr
llmsagentsreinforcement-learningroboticsfine-tuningmultimodal
More like this →
arXiv Machine Learning
Oct 7

Generalizable Dense Reward for Long-Horizon Robotic Tasks

arXiv:2604.00055v2 Announce Type: replace-cross Abstract: Existing robotic foundation policies are trained primarily via large-scale imitation learning. While such models demonstrate strong capabilit...

By Silong Yong, Stephen Sheng, Carl Qi, Xiaojie Wang, Evan Sheehan, Anurag Shivaprasad, Yaqi Xie, Katia Sycara, Yesh Dattatreya
llmsreinforcement-learningroboticsfine-tuningmultimodalbenchmarks
More like this →
arXiv AI
Oct 12

MENTOR: Learning from Failure with On-Policy Pedagogical Intervention

The paper introduces MENTOR, a multi‑agent framework that provides on‑policy pedagogical intervention to address zero‑reward collapse in reinforcement learning from verifiable rewards. MENTOR diagnoses failures in real time and generates targeted prompts to guide the learning agent, integrating seamlessly with existing policy optimization pipelines such as GRPO. Experiments on math and code generation tasks show that MENTOR significantly reduces collapse, achieving up to 78.3% relative gains on Llama‑3.2‑3B‑Instruct.

By Guanlan Yue, Hang Yu, Xiaoyong Huang, Ruipeng Li, Wei Zhang, Bingchang Liu, Rui Wang
llmsagentsreinforcement-learningbenchmarks
More like this →