arXiv AI
When Correct Memory Goes Wrong: Fuzzing Persistent Memory Use in LLM Agents
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jul 7
MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems
arXiv:2605. 28732v2 Announce Type: replace-cross Abstract: Memory is essential for enabling large language models to support long-horizon reasoning, yet existing memory systems remain unreliable and difficult to debug.
arXiv Computation and Language
Sep 22
EvalMem: An Operation-Level Diagnostic Framework for Long-Term Memory Systems
arXiv:2609.22231v1 Announce Type: new Abstract: Long-horizon interactions with LLM-based assistants require memory systems that preserve and update user states, preferences, and interaction histories...
arXiv AI
Jul 31
MemSecBench: Tracking Agent Memory Poisoning from Persistence to Consequence and Repair
arXiv:2607. 27080v1 Announce Type: cross Abstract: Memory systems allow agents to retain and reuse information from past interactions, but they can also let malicious content persist.
arXiv Machine Learning
Jun 19
The Correctness Illusion in LLM-Generated GPU Kernels
arXiv:2606. 20128v1 Announce Type: cross Abstract: Benchmarks for LLM-generated GPU kernels (KernelBench, TritonBench, GEAK) score correctness through fixed-shape, small-sample allclose-style checks.
arXiv AI
Sep 7
Forgetting Without Restarting: Execution-State Unlearning for Stateful LLM Agents
arXiv:2609. 04875v1 Announce Type: cross Abstract: Long-running LLM agents are stateful: beyond the transcript they accrete compressed summaries, plaintext memory, pending tool plans, and, under every serving API, a KV cache.
arXiv AI
Sep 10
SWE-Test: Benchmarking LLM Vulnerability Discovery via Input Prediction
arXiv:2609.06229v1 Announce Type: cross Abstract: Vulnerability discovery is becoming an important ability of large language model (LLM) agents: agents that silently miss real defects leave critical...