The study evaluates safety properties of a controlled MCP-to-A2A agent configuration by measuring verbatim field egress across ten record scenarios under three labeling conditions (CONFIDENTIAL, no header, PUBLIC – OK TO SHARE). Using four models repeated four times each, 480 trials were conducted, and the results show that adding a PUBLIC header is descriptively linked to higher verbatim egress, with the effect varying strongly by model. The study releases code, byte‑pinned traces, and an offline analysis pipeline as a public artifact.
By Arpan Kumar Mahapatra
arXiv:2602. 11510v3 Announce Type: replace Abstract: Multi-agent Large Language Model (LLM) systems create privacy risks that current output-only benchmarks cannot measure.
By Faouzi El Yagoubi, Godwin Badu-Marfo, Ranwa Al Mallah
arXiv:2608. 11392v1 Announce Type: cross Abstract: Long-running agents periodically compact their context, replacing the transcript with a model-generated summary.
By Ted Kwartler, Alan Aqrawi, Arian Abbasi
arXiv:2608. 12476v1 Announce Type: new Abstract: Long-term agent memory is usually treated as select--store--retrieve, but retrieval does not decide whether contradictory, superseded, retracted, deleted, or stale records may support an outgoing claim.
By Guodong Xu
Large language model agents coordinate tasks via multi‑role, multi‑stage workflows that transform upstream state into intermediate artifacts such as summaries and plans. The study shows that when these artifacts are transformed—through compression, plan assimilation, or other handoff methods—the strict action‑binding constraints on upstream state can be weakened, turning mandatory requirements into optional information. In 1,296 synthetic episodes, direct handoff preserved all safety blockers, whereas transformed handoffs frequently deactivated or forbidden actions, but restoring full state fields or applying downstream verification can recover preservation.
By Yiheng Sun, Huifei Wang, Yancheng Zhu, Zhenyu Li, Zebin Zhao, Yifan Yuan
arXiv:2606. 00152v1 Announce Type: cross Abstract: LLM-based agents are rapidly advancing, autonomously invoking external tools to complete multi-step tasks for users.
By Mingxuan Zhang, Jiahui Han, Dadi Guo, Songze Li, Guanchu Wang, Na Zou, Dongrui Liu, Xia Hu
arXiv:2606. 22528v2 Announce Type: replace Abstract: Modern LLM agents increasingly rely on context compaction, summarization, or eviction to keep long-running sessions within a token budget.
By Shiyang Chen
arXiv:2608. 16055v1 Announce Type: new Abstract: Existing agent benchmarks ask whether the agent finished the task.
By Bowen Li, Guojun Wang
The paper investigates how persistent memory in AI agents can lead to over‑trust in stale facts, creating a "Memory Trust Gap" that worsens as model capability increases. Using a benchmark with Benefit and Safety suites across Qwen3 models of varying sizes, the authors show that larger models are more prone to harmful over‑trust, especially when metadata is absent or misleading. They also demonstrate that mitigation strategies such as exposing metadata or pre‑resolving conflicts improve accuracy, but the effectiveness depends on model size and dataset.
By Jundong Hu, Shekar Ramachandran
arXiv:2606. 19356v1 Announce Type: cross Abstract: When multi-agent LLM systems produce bad answers, not all failures are equal: some answers are grounded in the right material but incomplete, while others are simply ungrounded and should be stopped.
By Anantha Sharma
arXiv:2606. 25449v1 Announce Type: cross Abstract: A language model's memory can be worse than having no memory at all.
By Alex Kwon
A language model's memory can be worse than having no memory at all. Give a model a memory that kept a wrong conclusion but dropped the work behind it, and it emits that stale value as a confident answer; give the same model an empty memory and it abstains.