State Trace Rationale As Auxiliary Task in Reinforcement Learning

arXiv:2609.36867 · cs.AI · Submitted 2026-09-29 · Read on arXiv

cs.AI

Submitted: 2026-09-29

Updated: 2026-09-29

Terminology

• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• Learning with Latent Language
• BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• Reinforcement Learning with Unsupervised Auxiliary Tasks
• Language as an Abstraction for Hierarchical Deep Reinforcement Learning
• Proximal Policy Optimization Algorithms
• Data-Efficient Reinforcement Learning with Self-Predictive Representations
• Reflexion: Language Agents with Verbal Reinforcement Learning
• Human-Timescale Adaptation in an Open-Ended Task Space
• Open-Ended Learning Leads to Generally Capable Agents
• Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions
• ReAct: Synergizing Reasoning and Acting in Language Models

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems