Using large language models for embodied planning introduces systematic safety risks

↘ Related papers

• When Can LLMs Learn to Reason with Weak Supervision?
  Salman Rahman37% match
• Learning from Less: Measuring the Effectiveness of RLVR in Low Data and Compute Regimes
  Justin Bauer34% match
• Scale-free adaptive planning for deterministic dynamics & discounted rewards
  Peter L. Bartlett34% match
• Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data
  Zhenwen Liang33% match
• Semantic Step Prediction: Multi-Step Latent Forecasting in LLM Reasoning Trajectories via Step Sampling
  Yidi Yuan29% match