5 papers
Collection-Date Assignment Redirects Answers in Temporal QA
Minsu Oh, Seunghui Jwa, Soo Kyun Kim +1
A collection date records when a source revision was acquired, not when its contents changed. Can assigning this metadata redirect temporal question answering despite unchanged evi…
Evaluating Compressed Memory: Dependence, Utility, and Content Benefit
Minsu Oh, Seunghui Jwa, Chanjun Park +1
Does a language model answer better because its compressed memory contains useful document information? Replacing memory vectors with zeros can lower a trained model's score withou…
POLAR: Ontology-Guided Risk Prevention for Tool-Calling LLM Agents
Yunju Kang, Seonghyeon Cho, Irene Li +2
LLM tool-use agents operate in dynamic environments where many actions carry operational risk. However, most safety mechanisms react only after errors manifest. Existing pre-emptiv…
Shared Stopping Decisions Change Answers in HQQ Cache Quantization
Seunghui Jwa, Minsu Oh, Chanjun Park +1
Language-model systems batch questions for throughput, but unrelated questions should not change a target's answer when its input and numerical execution are fixed. We study compre…
EvoSkill Injection: Red-Teaming Autonomous Skill Generation and Evolution in Self-Evolving Agents
Doyun Kim, Chanwoo Kim, Sugyeong Eo +2
LLM-based agent systems increasingly adopt skill-based architectures to reduce repetitive reasoning costs and improve stable, efficient task execution. Recent studies propose self-…