4 papers · 1 filter
Overthinking Loops in Agents: A Structural Risk via MCP Tools
Yohan Lee, Jisoo Jang, Seoyeon Choi +2
Tool-using LLM agents increasingly coordinate real workloads by selecting and chaining third-party tools based on text-visible metadata such as tool names, descriptions, and return…
Finding Diamonds in Conversation Haystacks: A Benchmark for Conversational Data Retrieval
Yohan Lee, Yongwoo Song, Sangyeop Kim
We present the Conversational Data Retrieval (CDR) benchmark, the first comprehensive test set for evaluating systems that retrieve conversation data for product insights. With 1.6…
Pre-Storage Reasoning for Episodic Memory: Shifting Inference Burden to Memory for Personalized Dialogue
Sangyeop Kim, Yohan Lee, Sanghwa Kim +2
Effective long-term memory in conversational AI requires synthesizing information across multiple sessions. However, current systems place excessive reasoning burden on response ge…
What Really Matters in Many-Shot Attacks? An Empirical Study of Long-Context Vulnerabilities in LLMs
Sangyeop Kim, Yohan Lee, Yongwoo Song +1
We investigate long-context vulnerabilities in Large Language Models (LLMs) through Many-Shot Jailbreaking (MSJ). Our experiments utilize context length of up to 128K tokens. Throu…