2 papers
cs.CR2026
SMSR: Certified Defence Against Runtime Memory Poisoning in Persistent LLM Agent Systems
Tarun Sharma
Retrieval-augmented generation (RAG) agents increasingly run with persistent memory that accumulates across user sessions. This creates a new attack surface: an adversary interacti…
cs.CL2025
Premise-Augmented Reasoning Chains Improve Error Identification in Math reasoning with LLMs
Sagnik Mukherjee, Abhinav Chinta, Takyoung Kim +2
Chain-of-Thought (CoT) prompting enhances mathematical reasoning in large language models (LLMs) by enabling detailed step-by-step solutions. However, due to the verbosity of LLMs,…