Safety
šØBreaking new study: memory in LLM agents still canāt really be trusted, even after over trillion dollars has gone into the development of ā¦
šØBreaking new study: memory in LLM agents still canāt really be trusted, even after over trillion dollars has gone into the development of the field. Excited to share our new paper: āUseful Memories B
šØBreaking new study: memory in LLM agents still canāt really be trusted, even after over trillion dollars has gone into the development of the field. Excited to share our new paper: āUseful Memories Become Faulty When Continuously Updated by LLMs. Can LLM agents keep improving by turning past experience into compact, reusable memories? We find this is much more fragile than it looks. Continuously consolidated memories can perfā¦
Source: Gary Marcus (X) | 2026-05-17