Maximizing LLM Utility While Managing LLM Fallibility
cs.RO
Submitted: 2026-11-12
Updated: 2026-11-12
Terminology
Sources
- Evidence-Gated LLM Priors for Multi-Objective Bayesian Optimization
- Correlation-Aware Contextual Bandits with Surrogate Rewards for LLM Routing
- Toward Safe LLM Agents: A Survey of Specification, Verification, and Enforcement
- LLM+P: Empowering Large Language Models with Optimal Planning Proficiency
- Programming Manufacturing Robots with Imperfect AI: LLMs as Tuning Experts for FDM Print Configuration Selection
- Safe LLM-Controlled Robots with Formal Guarantees via Reachability Analysis
- ParetoBandit: Budget-Paced Adaptive Routing for Non-Stationary LLM Serving
Related papers
- Rethinking Actions: Continuity-Aware Priors for World-Model Planning
- MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation