paper-with-me

홈 › Papers

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

2026-05-08 · Zixuan Xie, Xinyu Liu, Rohan Chandra, Shangtong Zhang arxiv

In-context reinforcement learning (ICRL) refers to the ability of RL agents to adapt to new tasks at inference time without parameter updates by conditioning on additional context. Recent empirical studies further demonstrate that Chain-of-Thought (CoT) generation can amplify this ICRL capability. This paper is the first to provide a theoretical understanding on how CoT interacts with ICRL. We conduct our analysis in a policy evaluation setup with linear Transformer. We prove that with specific Transformer parameters, the CoT generation process is equivalent to repeatedly executing temporal difference learning updates. Additionally, we provide finite sample convergence analysis showing that the policy evaluation error decreases geometrically with CoT length and eventually saturates at a statistical floor determined by the context length. We also prove that the desired Transformer parameters are a global minimizer of the pretraining loss, providing a theoretical understanding on the empirical emergence of those parameters.

📄 PDF Abstract BibTeX arXiv:2605.07123

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

RLP: Reinforcement as a Pretraining Objective

2025-09-26 · Ali Hatamizadeh, Syeda Nahida Akter, Shrimai Prabhumoye, Jan Kautz 외 arxiv

The dominant paradigm for training large reasoning models starts with pre-training using next-token prediction loss on vast amounts of data. Reinforcement learning, while powerful in scaling reasoning, is introduced only…

Reinforcement Learning

HRoT: Hybrid prompt strategy and Retrieval of Thought for Table-Text Hybrid Question Answering

2023-09-22 · Tongxu Luo, Fangyu Lei, Jiahe Lei, Weihao Liu 외

Answering numerical questions over hybrid contents from the given tables and text(TextTableQA) is a challenging task. Recently, Large Language Models (LLMs) have gained significant attention in the NLP community. With th…

In-Context LearningQuestion AnsweringRetrieval

History-Aware Cross-Attention Reinforcement: Self-Supervised Multi Turn and Chain-of-Thought Fine-Tuning with vLLM

2025-06-08 · Andrew Kiruluta, Andreas Lemos, Priscilla Burity

We present CAGSR-vLLM-MTC, an extension of our Self-Supervised Cross-Attention-Guided Reinforcement (CAGSR) framework, now implemented on the high-performance vLLM runtime, to address both multi-turn dialogue and chain-o…

Audio-DeepThinker: Progressive Reasoning-Aware Reinforcement Learning for High-Quality Chain-of-Thought Emergence in Audio Language Models

2026-04-20 · Xiang He, Chenxing Li, Jinting Wang, Yan Rong 외 arxiv

Large Audio-Language Models (LALMs) have made significant progress in audio understanding, yet they primarily operate as perception-and-answer systems without explicit reasoning processes. Existing methods for enhancing …

Reinforcement Learning

Chain-of-Thought Prompting for Demographic Inference with Large Multimodal Models

2024-05-24 · Yongsheng Yu, Jiebo Luo

Conventional demographic inference methods have predominantly operated under the supervision of accurately labeled data, yet struggle to adapt to shifting social landscapes and diverse cultural contexts, leading to narro…

Zero-Shot Learning