Cover Image

Nonsense Helps: Prompt Space Perturbation Broadens Reasoning Exploration

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Huang, Langlin, Huang, Chengsong, Li, Jinyuan, Cai, Donghong, Yang, Yuyi, Huang, Jiaxin
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Process Rewards with Learned Reliability
by: Li, Jinyuan, et al.
Published: (2026)

RelayLLM: Efficient Reasoning via Collaborative Decoding
by: Huang, Chengsong, et al.
Published: (2026)

Divide, Reweight, and Conquer: A Logit Arithmetic Approach for In-Context Learning
by: Huang, Chengsong, et al.
Published: (2024)

POSS: Position Specialist Generates Better Draft for Speculative Decoding
by: Huang, Langlin, et al.
Published: (2025)

Efficient Test-Time Scaling via Self-Calibration
by: Huang, Chengsong, et al.
Published: (2025)

G-Zero: Self-Play for Open-Ended Generation from Zero Data
by: Huang, Chengsong, et al.
Published: (2026)

Training Data Efficiency in Multimodal Process Reward Models
by: Li, Jinyuan, et al.
Published: (2026)

R-Zero: Self-Evolving Reasoning LLM from Zero Data
by: Huang, Chengsong, et al.
Published: (2025)

VisPlay: Self-Evolving Vision-Language Models from Images
by: He, Yicheng, et al.
Published: (2025)

CrossWordBench: Evaluating the Reasoning Capabilities of LLMs and LVLMs with Controllable Puzzle Generation
by: Leng, Jixuan, et al.
Published: (2025)

MATH-Perturb: Benchmarking LLMs' Math Reasoning Abilities against Hard Perturbations
by: Huang, Kaixuan, et al.
Published: (2025)

PrAg-PO: Prompt Augmented Policy Optimization for Robust and Diverse Mathematical Reasoning
by: Lu, Wenquan, et al.
Published: (2026)

Can Stories Help LLMs Reason? Curating Information Space Through Narrative
by: Javadi, Vahid Sadiri, et al.
Published: (2024)

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners
by: Zeng, Weihao, et al.
Published: (2024)

TTCS: Test-Time Curriculum Synthesis for Self-Evolving
by: Yang, Chengyi, et al.
Published: (2026)

Guided Self-Evolving LLMs with Minimal Human Supervision
by: Yu, Wenhao, et al.
Published: (2025)

Talking Nonsense: Probing Large Language Models' Understanding of Adversarial Gibberish Inputs
by: Cherepanova, Valeriia, et al.
Published: (2024)

When "A Helpful Assistant" Is Not Really Helpful: Personas in System Prompts Do Not Improve Performances of Large Language Models
by: Zheng, Mingqian, et al.
Published: (2023)

Theory of Space: Can Foundation Models Construct Spatial Beliefs through Active Exploration?
by: Zhang, Pingyue, et al.
Published: (2026)

Efficient Prompt Tuning by Multi-Space Projection and Prompt Fusion
by: Lan, Pengxiang, et al.
Published: (2024)

Prompt-SAW: Leveraging Relation-Aware Graphs for Textual Prompt Compression
by: Ali, Muhammad Asif, et al.
Published: (2024)

Decomposing Representation Space into Interpretable Subspaces with Unsupervised Learning
by: Huang, Xinting, et al.
Published: (2025)

TabDLM: Free-Form Tabular Data Generation via Joint Numerical-Language Diffusion
by: Cai, Donghong, et al.
Published: (2026)

Knapsack RL: Unlocking Exploration of LLMs via Optimizing Budget Allocation
by: Li, Ziniu, et al.
Published: (2025)

Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents
by: Song, Yifan, et al.
Published: (2024)

H3Fusion: Helpful, Harmless, Honest Fusion of Aligned LLMs
by: Tekin, Selim Furkan, et al.
Published: (2024)

Better LLM Reasoning via Dual-Play
by: Zhang, Zhengxin, et al.
Published: (2025)

Input-Time Scaling: Adding Noise and Irrelevance into Less-Is-More Drastically Improves Reasoning Performance and Efficiency
by: Huang, Rapheal, et al.
Published: (2025)

From Reasoning Chains to Verifiable Subproblems: Curriculum Reinforcement Learning Enables Credit Assignment for LLM Reasoning
by: Jiang, Xitai, et al.
Published: (2026)

ECCO: Evidence-Driven Causal Reasoning for Compiler Optimization
by: Pan, Haolin, et al.
Published: (2026)

Leveraging Large Language Models with Chain-of-Thought and Prompt Engineering for Traffic Crash Severity Analysis and Inference
by: Zhen, Hao, et al.
Published: (2024)

Conversational Orientation Reasoning: Egocentric-to-Allocentric Navigation with Multimodal Chain-of-Thought
by: Huang, Yu Ti
Published: (2025)

PISanitizer: Preventing Prompt Injection to Long-Context LLMs via Prompt Sanitization
by: Geng, Runpeng, et al.
Published: (2025)

Capacity-Aware Inference: Mitigating the Straggler Effect in Mixture of Experts
by: He, Shwai, et al.
Published: (2025)

HAPO: Training Language Models to Reason Concisely via History-Aware Policy Optimization
by: Huang, Chengyu, et al.
Published: (2025)

PIArena: A Platform for Prompt Injection Evaluation
by: Geng, Runpeng, et al.
Published: (2026)

Tree-OPO: Off-policy Monte Carlo Tree-Guided Advantage Optimization for Multistep Reasoning
by: Huang, Bingning, et al.
Published: (2025)

Selective Prompting Tuning for Personalized Conversations with LLMs
by: Huang, Qiushi, et al.
Published: (2024)

Temporal Consistency for LLM Reasoning Process Error Identification
by: Guo, Jiacheng, et al.
Published: (2025)

Formalizing and Benchmarking Prompt Injection Attacks and Defenses
by: Liu, Yupei, et al.
Published: (2023)