2025 "reasoning capabilities" Papers

16 papers found

Activation-Guided Consensus Merging for Large Language Models

Yuxuan Yao, Shuqi LIU, Zehua Liu et al.

NEURIPS 2025posterarXiv:2505.14009
1
citations

d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning

Siyan Zhao, Devaansh Gupta, Qinqing Zheng et al.

NEURIPS 2025spotlightarXiv:2504.12216
75
citations

Finding and Reactivating Post-Trained LLMs' Hidden Safety Mechanisms

Mingjie Li, Wai Man Si, Michael Backes et al.

NEURIPS 2025poster
1
citations

From Artificial Needles to Real Haystacks: Improving Retrieval Capabilities in LLMs by Finetuning on Synthetic Data

Zheyang Xiong, Vasilis Papageorgiou, Kangwook Lee et al.

ICLR 2025posterarXiv:2406.19292
19
citations

General-Reasoner: Advancing LLM Reasoning Across All Domains

Xueguang Ma, Qian Liu, Dongfu Jiang et al.

NEURIPS 2025posterarXiv:2505.14652
81
citations

GRIP: A Graph-Based Reasoning Instruction Producer

Jiankang Wang, Jianjun Xu, Xiaorui Wang et al.

NEURIPS 2025posterarXiv:2412.08864
2
citations

Mixture of Parrots: Experts improve memorization more than reasoning

Samy Jelassi, Clara Mohri, David Brandfonbrener et al.

ICLR 2025posterarXiv:2410.19034
14
citations

Preference Optimization for Reasoning with Pseudo Feedback

Fangkai Jiao, Geyang Guo, Xingxing Zhang et al.

ICLR 2025posterarXiv:2411.16345
34
citations

ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models

Mingjie Liu, Shizhe Diao, Ximing Lu et al.

NEURIPS 2025posterarXiv:2505.24864
99
citations

RAST: Reasoning Activation in LLMs via Small-model Transfer

Siru Ouyang, Xinyu Zhu, Zilin Xiao et al.

NEURIPS 2025posterarXiv:2506.15710
1
citations

Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models

Yiran Guo, Lijie Xu, Jie Liu et al.

NEURIPS 2025posterarXiv:2505.23564
15
citations

SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond

Junteng Liu, Yuanxiang Fan, Jiang Zhuo et al.

NEURIPS 2025posterarXiv:2505.19641
21
citations

The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity

Parshin Shojaee, Iman Mirzadeh, Keivan Alizadeh vahid et al.

NEURIPS 2025posterarXiv:2506.06941
257
citations

Thinker: Learning to Think Fast and Slow

Stephen Chung, Wenyu Du, Jie Fu

NEURIPS 2025posterarXiv:2505.21097
5
citations

When Can Model-Free Reinforcement Learning be Enough for Thinking?

Josiah Hanna, Nicholas Corrado

NEURIPS 2025posterarXiv:2506.17124

Wider or Deeper? Scaling LLM Inference-Time Compute with Adaptive Branching Tree Search

Yuichi Inoue, Kou Misaki, Yuki Imajuku et al.

NEURIPS 2025spotlightarXiv:2503.04412
18
citations