Cover Image

Convergence and Emergence of In-Context Reinforcement Learning with Chain of Thought

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xie, Zixuan, Liu, Xinyu, Chandra, Rohan, Zhang, Shangtong
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Towards Provable Emergence of In-Context Reinforcement Learning
by: Wang, Jiuqi, et al.
Published: (2025)

Beyond Linear Attention: Softmax Transformers Implement In-Context Reinforcement Learning
by: Xie, Zixuan, et al.
Published: (2026)

Almost Sure Convergence Rates of Stochastic Approximation and Reinforcement Learning via a Poisson-Moreau Drift
by: Liu, Xinyu, et al.
Published: (2026)

Finite Sample Analysis of Linear Temporal Difference Learning with Arbitrary Features
by: Xie, Zixuan, et al.
Published: (2025)

Almost Sure Convergence Rates and Concentration of Stochastic Approximation and Reinforcement Learning with Markovian Noise
by: Qian, Xiaochi, et al.
Published: (2024)

Linear $Q$-Learning Does Not Diverge in $L^2$: Convergence Rates to a Bounded Set
by: Liu, Xinyu, et al.
Published: (2025)

Extensions of Robbins-Siegmund Theorem with Applications in Reinforcement Learning
by: Liu, Xinyu, et al.
Published: (2025)

A Survey of In-Context Reinforcement Learning
by: Moeini, Amir, et al.
Published: (2025)

Safe In-Context Reinforcement Learning
by: Moeini, Amir, et al.
Published: (2025)

Group Fairness in Multi-Task Reinforcement Learning
by: Song, Kefan, et al.
Published: (2025)

MathlibPR: Pull Request Merge-Readiness Benchmark for Formal Mathematical Libraries
by: Xie, Zixuan, et al.
Published: (2026)

Prompt-Driven Domain Adaptation for End-to-End Autonomous Driving via In-Context RL
by: Khurram, Aleesha, et al.
Published: (2025)

Experience Replay Addresses Loss of Plasticity in Continual Learning
by: Wang, Jiuqi, et al.
Published: (2025)

Towards Formalizing Reinforcement Learning Theory
by: Zhang, Shangtong
Published: (2025)

Reward Is Enough: LLMs Are In-Context Reinforcement Learners
by: Song, Kefan, et al.
Published: (2025)

Convergence of Two-Timescale Markovian Stochastic Approximations with Applications in Reinforcement Learning
by: Mahadevan, Vagul, et al.
Published: (2026)

Transformers Can Learn Temporal Difference Methods for In-Context Reinforcement Learning
by: Wang, Jiuqi, et al.
Published: (2024)

Almost Sure Convergence of Linear Temporal Difference Learning with Arbitrary Features
by: Wang, Jiuqi, et al.
Published: (2024)

Doubly Optimal Policy Evaluation for Reinforcement Learning
by: Liu, Shuze Daniel, et al.
Published: (2024)

Efficient Multi-Policy Evaluation for Reinforcement Learning
by: Liu, Shuze Daniel, et al.
Published: (2024)

Efficient Policy Evaluation with Safety Constraint for Reinforcement Learning
by: Chen, Claire, et al.
Published: (2024)

In-Context Decision Transformer: Reinforcement Learning via Hierarchical Chain-of-Thought
by: Huang, Sili, et al.
Published: (2024)

Almost Sure Convergence of Differential Temporal Difference Learning for Average Reward Markov Decision Processes
by: Blaser, Ethan, et al.
Published: (2026)

The ODE Method for Stochastic Approximation and Reinforcement Learning with Markovian Noise
by: Liu, Shuze Daniel, et al.
Published: (2024)

Counterfactual Explanations for Continuous Action Reinforcement Learning
by: Dong, Shuyang, et al.
Published: (2025)

CRASH: Challenging Reinforcement-Learning Based Adversarial Scenarios For Safety Hardening
by: Kulkarni, Amar, et al.
Published: (2024)

Transformers Provably Learn to Internalize Chain-of-Thought
by: Huang, Yixiao, et al.
Published: (2026)

Transformers Learn to Implement Multi-step Gradient Descent with Chain of Thought
by: Huang, Jianhao, et al.
Published: (2025)

Towards Large Language Models that Benefit for All: Benchmarking Group Fairness in Reward Models
by: Song, Kefan, et al.
Published: (2025)

On the Divergence of Differential Temporal Difference Learning without Local Clocks
by: Antrobius, David, et al.
Published: (2026)

Revisiting a Design Choice in Gradient Temporal Difference Learning
by: Qian, Xiaochi, et al.
Published: (2023)

Efficient Policy Evaluation with Offline Data Informed Behavior Policy Design
by: Liu, Shuze, et al.
Published: (2023)

Eliciting Chain-of-Thought Reasoning for Time Series Analysis using Reinforcement Learning
by: Parker, Felix, et al.
Published: (2025)

Emergence of Superposition: Unveiling the Training Dynamics of Chain of Continuous Thought
by: Zhu, Hanlin, et al.
Published: (2025)

Emergence of In-Context Reinforcement Learning from Noise Distillation
by: Zisman, Ilya, et al.
Published: (2023)

MathlibLemma: Folklore Lemma Generation and Benchmark for Formal Mathematics
by: Liu, Xinyu, et al.
Published: (2026)

Learning to Correct: Calibrated Reinforcement Learning for Multi-Attempt Chain-of-Thought
by: Ildiz, Muhammed Emrullah, et al.
Published: (2026)

Learning to Remember: End-to-End Training of Memory Agents for Long-Context Reasoning
by: Zhang, Kehao, et al.
Published: (2026)

Reinforcing Chain-of-Thought Reasoning with Self-Evolving Rubrics
by: Sheng, Leheng, et al.
Published: (2026)

ExpThink: Experience-Guided Reinforcement Learning for Adaptive Chain-of-Thought Compression
by: Bian, Tingcheng, et al.
Published: (2026)