CIPL: A Channel-Aware Framework for Recoverable Privacy Leakage in LLM Agents
arXiv:2609.21686v1 Announce Type: cross Abstract: Privacy leakage in LLM agents is commonly evaluated within individual components such as memory, retrieval,…
by ODEFTO AI Labs
arXiv:2609.21686v1 Announce Type: cross Abstract: Privacy leakage in LLM agents is commonly evaluated within individual components such as memory, retrieval,…
arXiv:2609.20130v1 Announce Type: cross Abstract: Recent memory-augmented repository-level program repair methods reuse historical repair experiences to improve LLM-based issue resolution.…
arXiv:2609.19170v1 Announce Type: new Abstract: Emphatic temporal-difference learning (ETD) stabilizes the expected off-policy TD update and changes its projection geometry,…
arXiv:2609.19137v2 Announce Type: replace-cross Abstract: Video generation models have advanced rapidly and can now synthesize plausible videos of robot manipulation…
arXiv:2609.20139v1 Announce Type: cross Abstract: Vision-language models (VLMs) are fragile under image corruption. We find that the wording of the…
arXiv:2609.18462v2 Announce Type: replace-cross Abstract: FastWAM-style world action models enable efficient action-only inference, but generalize poorly under visual distribution shifts.…
Nature Machine Intelligence, Published online: 18 September 2026; doi:10.1038/s42256-026-01312-x Living organisms continuously monitor their internal physiological states while interacting with…