agent/papers/items/2026-2606-28958-when-latent-agents-lie-kv-cache-integrity-in-multi-agent-llm-collaboration.md

Paper: When Latent Agents Lie: KV-Cache Integrity in Multi-Agent LLM Collaboration

---

type: paper title: "When Latent Agents Lie: KV-Cache Integrity in Multi-Agent LLM Collaboration" authors: Luís Brito, Carlos Baquero year: 2026 venue: arXiv url: https://arxiv.org/abs/2606.28958 code_url: source: arxiv collected_at: 2026-07-08 published_at: 2026-06-27 updated_at: 2026-06-27 status: queued relevance: high topics:

• agent-safety
• memory
• multi-agent
• reasoning methods:

benchmarks:

models:

datasets:

• cs.MA related_concepts:

related_jobs:

related_experiments:

related_projects:

collection_score: 17 collection_queries: llm-agent, multi-agent-llm

One-line Takeaway

Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.

Why Collected

• matched queries: llm-agent, multi-agent-llm
• inferred topics: agent-safety, memory, multi-agent, reasoning
• arXiv categories: cs.MA
• collection score: 17

Review Checklist

• Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
• Does it include a benchmark, dataset, code, or reproducible experimental setup?
• Should it be promoted from queued to skimmed or summarized?

Links

• arXiv: https://arxiv.org/abs/2606.28958