arXiv AI October 1, 2026 By Muhammad Huzaifa, Sina Mavali, Thorsten Eisenhofer

Safety of Latent Communication in Multi-Agent Systems

The paper investigates latent communication in multi‑agent systems, where agents exchange information in internal representation space via lightweight trainable links. It demonstrates that even benign training of these links can increase harmful compliance, and that attackers can exploit or poison the links to amplify this effect. A reinforcement‑learning attack further boosts harmful compliance while maintaining benign task performance, but adjusting rewards toward safer behavior can repair compromised links without updating the agents.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Aug 11

Benchmarking the Robustness of Agentic Systems to Adversarially-Induced Harms

arXiv:2508. 16481v3 Announce Type: replace Abstract: Ensuring the safe use of agentic systems requires a thorough understanding of the range of malicious behaviors these systems may exhibit.

By Jonathan N\"other, Adish Singla, Goran Radanovic

llms agents benchmarks safety

arXiv Machine Learning

Jul 1

When Embedding-Based Defenses Fail: Rethinking Safety in LLM-Based Multi-Agent Systems

arXiv:2605. 01133v3 Announce Type: replace-cross Abstract: Large language model (LLM)-powered multi-agent systems (MAS) enable agents to communicate and share information, achieving strong performance on complex tasks.

By Lingxi Zhang, Guangtao Zheng, Hanjie Chen

llms rag agents safety

arXiv Computation and Language

Aug 25

Safety Training May Persist Through Helpfulness Optimization in LLM Agents

arXiv:2603.02229v2 Announce Type: replace-cross Abstract: Safety post-training has been studied extensively in single-step "chat" settings where safety typically refers to refusing harmful requests....

By Benjamin Plaut

llms agents reinforcement-learning benchmarks safety

arXiv Machine Learning

Aug 5

Token Buncher: Shielding LLMs from Harmful Reinforcement Learning Fine-Tuning

arXiv:2508. 20697v4 Announce Type: replace Abstract: As large language models (LLMs) continue to grow in capability, so do the risks of harmful misuse through fine-tuning.

By Weitao Feng, Lixu Wang, Peizhuo Lv, Tianyi Wei, Jie Zhang, Chongyang Gao, Sinong Zhan, Wei Dong

llms reinforcement-learning fine-tuning safety

arXiv AI

Jun 4

RUBAS: Rubric-Based Reinforcement Learning for Agent Safety

arXiv:2606. 04051v1 Announce Type: cross Abstract: The evolution of LLMs into tool-enabled agents creates a new class of safety challenges associated with real-world execution rather than simple text generation.

By Xian Qi Loye, Qinglin Su, Zhexin Zhang, Shiyao Cui, Qi Zhu, Fei Mi, Hongning Wang, Minlie Huang

llms agents reinforcement-learning benchmarks safety

arXiv AI

Jun 2

Safety Alignment of LMs via Non-cooperative Games

arXiv:2512. 20806v3 Announce Type: replace Abstract: Ensuring the safety of language models (LMs) while maintaining their usefulness remains a critical challenge in AI alignment.

By Anselm Paulus, Ilia Kulikov, Brandon Amos, R\'emi Munos, Ivan Evtimov, Kamalika Chaudhuri, Arman Zharmagambetov

llms agents reinforcement-learning fine-tuning safety

One email a morning, machine-written

Related stories

Benchmarking the Robustness of Agentic Systems to Adversarially-Induced Harms

When Embedding-Based Defenses Fail: Rethinking Safety in LLM-Based Multi-Agent Systems

Safety Training May Persist Through Helpfulness Optimization in LLM Agents

Token Buncher: Shielding LLMs from Harmful Reinforcement Learning Fine-Tuning

RUBAS: Rubric-Based Reinforcement Learning for Agent Safety

Safety Alignment of LMs via Non-cooperative Games