:: Library Catalog

Cover Image

Saved in:

Bibliographic Details
Main Author:	Li, Yuanhang
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	https://arxiv.org/abs/2604.03562
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Validated Intent Compilation for Constrained Routing in LEO Mega-Constellations
by: Li, Yuanhang
Published: (2026)

When Does Multimodal AI Help? Diagnostic Complementarity of Vision-Language Models and CNNs for Spectrum Management in Satellite-Terrestrial Networks
by: Li, Yuanhang
Published: (2026)

Probing Embodied LLMs: When Higher Observation Fidelity Hurts Problem Solving
by: Zenkri, Oussama, et al.
Published: (2026)

When Corrective Hints Hurt: Prompt Design in Reasoner-Guided Repair of LLM Overcaution on Entailed Negations under OWL~2~DL
by: Qi, Yijiashun, et al.
Published: (2026)

When More Thinking Hurts: Overthinking in LLM Test-Time Compute Scaling
by: Zhou, Shu, et al.
Published: (2026)

The Pitfalls of Memorization: When Memorization Hurts Generalization
by: Bayat, Reza, et al.
Published: (2024)

When "Better" Prompts Hurt: Evaluation-Driven Iteration for LLM Applications
by: Commey, Daniel
Published: (2026)

DeliberationBench: When Do More Voices Hurt? A Controlled Study of Multi-LLM Deliberation Protocols
by: Kaushal, Vaarunay, et al.
Published: (2025)

When Correct Demonstrations Hurt: Rethinking the Role of Exemplars in In-Context Learning
by: Qiu, Chenghao, et al.
Published: (2026)

Not All Queries Need Rewriting: When Prompt-Only LLM Refinement Helps and Hurts Dense Retrieval
by: Kotte, Varun
Published: (2026)

When Verification Hurts: Asymmetric Effects of Multi-Agent Feedback in Logic Proof Tutoring
by: Yasir, Tahreem, et al.
Published: (2026)

When RAG Hurts: Diagnosing and Mitigating Attention Distraction in Retrieval-Augmented LVLMs
by: Zhao, Beidi, et al.
Published: (2026)

When Ethics and Payoffs Diverge: LLM Agents in Morally Charged Social Dilemmas
by: Backmann, Steffen, et al.
Published: (2025)

When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning
by: Zhang, Xiaoyun, et al.
Published: (2025)

When Context Hurts: The Crossover Effect of Knowledge Transfer on Multi-Agent Design Exploration
by: Vigraham, Saranyan
Published: (2026)

Evaluating Social Bias in RAG Systems: When External Context Helps and Reasoning Hurts
by: Parihar, Shweta, et al.
Published: (2026)

When Trust Collides: Decoding Human-LLM Cooperation Dynamics through the Prisoner's Dilemma
by: Jiang, Guanxuan, et al.
Published: (2025)

When Shared Knowledge Hurts: Spectral Over-Accumulation in Model Merging
by: Li, Yayuan, et al.
Published: (2026)

When Reasoning Models Hurt Behavioral Simulation: A Solver-Sampler Mismatch in Multi-Agent LLM Negotiation
by: Andric, Sandro
Published: (2026)

Reward-Guided Speculative Decoding for Efficient LLM Reasoning
by: Liao, Baohao, et al.
Published: (2025)

Context Length Alone Hurts LLM Performance Despite Perfect Retrieval
by: Du, Yufeng, et al.
Published: (2025)

Privacy-Aware Spectrum Pricing and Power Control Optimization for LEO Satellite Internet-of-Things
by: Shen, Bowen, et al.
Published: (2024)

The State-Action-Reward-State-Action Algorithm in Spatial Prisoner's Dilemma Game
by: Yang, Lanyu, et al.
Published: (2024)

OccuReward: LLM-Guided Occupant-Centric Reward Shaping for Demographic Equity in Grid-Interactive Buildings
by: Zaregarizi, Shadmehr, et al.
Published: (2026)

LLM Reasoning with Process Rewards for Outcome-Guided Steps
by: Rezaei, Mohammad, et al.
Published: (2026)

Collaborative Space Object Detection with Multi-Satellite Viewpoints in LEO Constellations
by: Qu, Xingyu, et al.
Published: (2026)

When Reasoning Hurts: Source-Aware Evaluation of Frontier LLMs for Clinical SOAP Note Generation
by: Faisal, Faizan
Published: (2026)

More Test-Time Compute Can Hurt: Overestimation Bias in LLM Beam Search
by: Dalal, Gal, et al.
Published: (2026)

LEO-Split: A Semi-Supervised Split Learning Framework over LEO Satellite Networks
by: Lin, Zheng, et al.
Published: (2025)

AI Assistance Reduces Persistence and Hurts Independent Performance
by: Liu, Grace, et al.
Published: (2026)

Masked IRL: LLM-Guided Reward Disambiguation from Demonstrations and Language
by: Hwang, Minyoung, et al.
Published: (2025)

Know When to Explore: Difficulty-Aware Certainty as a Guide for LLM Reinforcement Learning
by: Li, Ang, et al.
Published: (2025)

Gradient Compression May Hurt Generalization: A Remedy by Synthetic Data Guided Sharpness Aware Minimization
by: Gu, Yujie, et al.
Published: (2026)

Learning a Reward Function for User-Preferred Appliance Scheduling
by: Čović, Nikolina, et al.
Published: (2023)

AltNet: Addressing the Plasticity-Stability Dilemma in Reinforcement Learning
by: Maheshwari, Mansi, et al.
Published: (2025)

DSevolve: Enabling Real-Time Adaptive Scheduling on Dynamic Shop Floor with LLM-Evolved Heuristic Portfolios
by: Huang, Jin, et al.
Published: (2026)

VORTEX: Aligning Task Utility and Human Preferences through LLM-Guided Reward Shaping
by: Xiong, Guojun, et al.
Published: (2025)

Reward Models Identify Consistency, Not Causality
by: Xu, Yuhui, et al.
Published: (2025)

SAFER: Probing Safety in Reward Models with Sparse Autoencoder
by: Shi, Wei, et al.
Published: (2025)

Systems with Switching Causal Relations: A Meta-Causal Perspective
by: Willig, Moritz, et al.
Published: (2024)