paper-with-me

Papers

Test-time Recursive Thinking: Self-Improvement without External Feedback

2026-02-03 · Yufan Zhuang, Chandan Singh, Liyuan Liu, Yelong Shen, Dinghuai Zhang, Jingbo Shang, Jianfeng Gao, Weizhu Chen arxiv

Modern Large Language Models (LLMs) have shown rapid improvements in reasoning capabilities, driven largely by reinforcement learning (RL) with verifiable rewards. Here, we ask whether these LLMs can self-improve without the need for additional training. We identify two core challenges for such systems: (i) efficiently generating diverse, high-quality candidate solutions, and (ii) reliably selecting correct answers in the absence of ground-truth supervision. To address these challenges, we propose Test-time Recursive Thinking (TRT), an iterative self-improvement framework that conditions generation on rollout-specific strategies, accumulated knowledge, and self-generated verification signals. Using TRT, open-source models reach 100% accuracy on AIME-25/24, and on LiveCodeBench's most difficult problems, closed-source models improve by 10.4-14.8 percentage points without external feedback.

📄 PDF Abstract BibTeX arXiv:2602.03094

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

PRefLexOR: Preference-based Recursive Language Modeling for Exploratory Optimization of Reasoning and Agentic Thinking

2024-10-16 · Markus J. Buehler

PRefLexOR (Preference-based Recursive Language Modeling for Exploratory Optimization of Reasoning) combines preference optimization with concepts from Reinforcement Learning to enable models to self-teach through iterati…

Language ModelingLanguage ModellingMulti-agent Integration

The Art of SOCRATIC QUESTIONING: Recursive Thinking with Large Language Models

2023-05-24 · Jingyuan Qi, Zhiyang Xu, Ying Shen, Minqian Liu 외

Chain-of-Thought (CoT) prompting enables large language models to solve complex reasoning problems by generating intermediate steps. However, confined by its inherent single-pass and sequential generation process, CoT he…

Language ModellingMathMMLUQuestion Answering+1

RTQA : Recursive Thinking for Complex Temporal Knowledge Graph Question Answering with Large Language Models

2025-09-04 · Zhaoyan Gong, Juan Li, Zhiqiang Liu, Lei Liang 외 arxiv

Current temporal knowledge graph question answering (TKGQA) methods primarily focus on implicit temporal constraints, lacking the capability of handling more complex temporal queries, and struggle with limited reasoning …

Graph Question Answering

Recursive Self-Aggregation Unlocks Deep Thinking in Large Language Models

2025-09-30 · Siddarth Venkatraman, Vineet Jain, Sarthak Mittal, Vedant Shah 외 arxiv

Test-time scaling methods improve the capabilities of large language models (LLMs) by increasing the amount of compute used during inference to make a prediction. Inference-time compute can be scaled in parallel by choos…

Reinforcement Learning

MatryoshkaThinking: Recursive Test-Time Scaling Enables Efficient Reasoning

2025-10-11 · Hongwei Chen, Yishu Lei, Dan Zhang, Bo Ke 외 arxiv

Test-time scaling has emerged as a promising paradigm in language modeling, wherein additional computational resources are allocated during inference to enhance model performance. Recent approaches, such as DeepConf, hav…