6 papers
T-SMART: Mechanism-Level Attribution for Tool-Augmented Time-Series Question Answering
Ivan Delgado, Himansi Gupta, Bishal Khatri +4
Large language models (LLMs) can struggle with time-series question answering (TS-QA), especially when numerical signals are serialized as text and require explicit computation. To…
LIMBO: Lifelong Inference-Time Memory and Budget Optimization for LLM Agents
Siddharth Sharma, Nilesh Prasad Pandey, Onat Gungor +1
As LLM agents become integrated into increasingly complex workflows, they must continually acquire new capabilities while retaining competence on previously learned tasks. Lifelong…
COPA: Continual Preference Optimization for Adaptive Prompt Injection Defense
Roshan Sood, Onat Gungor, Tajana Rosing
LLMs remain vulnerable to prompt injection attacks, where adversarial instructions embedded in user inputs or external content manipulate model behavior and bypass safeguards. Exis…
G-MARK: Grounded Multi-Agent Reasoning for Cooperative Driving via Knowledge Graphs
Bhavya Gupta, Onat Gungor, Tajana Rosing
Autonomous driving systems must operate under partial observability, where safety-critical objects may be occluded or visible only to neighboring connected vehicles. Vehicle-to-veh…
AgentKVShift: Efficient KV Cache Reuse for Agentic Memory Systems
Nilesh Prasad Pandey, Jason Kong, Lanxiang Hu +5
Memory-augmented LLM agents maintain context across hundreds of interactions through agentic memory systems that actively curate retrieved content with LLM-generated metadata such…
LifeAgentBench: Benchmarking LLMs for Long-Horizon, Cross-Dimensional Lifestyle Health Reasoning
Ye Tian, Zihao Wang, Onat Gungor +2
Personalized lifestyle health analysis requires long-horizon, multi-dimensional reasoning over heterogeneous lifestyle signals, and recent advances in mobile sensing and large lang…