Overthinking Loops in Agents: A Structural Risk via MCP Tools
Paper • 2602.14798 • Published • 1
Yohan Lee
l-yohai
AI & ML interests
Large Language Models
Organizations
authored a
paper 4 months ago
authored 4
papers 9 months ago
HEISIR: Hierarchical Expansion of Inverted Semantic Indexing for Training-free Retrieval of Conversational Data using LLMs
Paper • 2503.04141 • Published
Finding Diamonds in Conversation Haystacks: A Benchmark for Conversational Data Retrieval
Paper • 2510.02938 • Published
Pre-Storage Reasoning for Episodic Memory: Shifting Inference Burden to Memory for Personalized Dialogue
Paper • 2509.10852 • Published
What Really Matters in Many-Shot Attacks? An Empirical Study of Long-Context Vulnerabilities in LLMs
Paper • 2505.19773 • Published