arXiv AI June 3, 2026 By Hina Dixit, Punit Kumar, Irene Tenison, Nevasini Sasikumar

Echelon: Auditable Aggregate-Only Language-Model Adaptation Across Privacy Boundaries

arXiv:2606. 02958v1 Announce Type: cross Abstract: Cross-organization language-model adaptation increasingly faces hard governance constraints: in many deployments, device-level model state-parameters, activations, optimizer state, and per-device updates-cannot be exported outside an administrative boundary.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv Machine Learning

Aug 12

Benchmarking LLM-Guided Control-Plane Policies for Backend Fault Isolation in HAProxy

arXiv:2608. 10532v1 Announce Type: cross Abstract: Static load balancers cannot mitigate a backend that is degraded rather than down: round-robin and least-connections keep routing traffic to a server returning HTTP 500s until an operator intervenes.

By Aman Chauhan, Vishnu Pendyala

llms benchmarks safety

arXiv AI

Jul 24

Routing Subspaces: Auditing Evaluation-to-Deployment Mismatch in Fine-Tuned Language Models

arXiv:2607. 20436v1 Announce Type: cross Abstract: Safety evaluations often assume that behavior observed during testing reflects behavior in ordinary use, but fine-tuning can break this assumption.

By Phongsakon Mark Konrad, Toygar Tanyel, Serkan Ayvaz

llms fine-tuning safety

arXiv AI

Jul 24

Autonomous Topology Mutation: Safe Runtime Restructuring for Multi-Agent LLM Systems with Capability, State, and Shadow Invariants

arXiv:2607. 20488v1 Announce Type: new Abstract: Multi-agent LLM frameworks typically fix their team topology at boot time.

By Bronislav Sidik, Chaya Levi, Nizzan Kimhi

llms agents efficiency benchmarks safety

arXiv AI

Jul 7

Elastic Gang: Per-Token Membership Change for a Hard-Barriered LLM Inference Gang Co-Scheduled with OS Processes

arXiv:2607. 04668v1 Announce Type: cross Abstract: On-device LLM decoding is a hard-barriered CPU-SIMD computation that wants every core for milliseconds per token, while the rest of the OS wants those same cores continuously.

By Daeyeon Son

llms efficiency safety

arXiv AI

Jul 22

Phionyx: A Deterministic AI Runtime Architecture with Structured State Management and Pre-Response Governance

arXiv:2607. 18246v1 Announce Type: new Abstract: We present Phionyx, a deterministic AI runtime architecture derived from the broader Echoism interaction framework that introduces a governance-first approach to AI engineering: treating large language model (LLM) outputs as noisy sensor measurements rather than direct decisions.

By Ali Toygar Abak

llms agents benchmarks safety

arXiv AI

Aug 10

Policy-Masked Private Experts: Auditable and Reversible Capability Access Control in Sparse MoE Models

arXiv:2608. 06690v1 Announce Type: cross Abstract: Most language-model access controls regulate behavior while leaving the same computation available to every request.

By Zhuoheng Huang, Mukesh Singh

agents fine-tuning benchmarks safety

Related stories

Benchmarking LLM-Guided Control-Plane Policies for Backend Fault Isolation in HAProxy

Routing Subspaces: Auditing Evaluation-to-Deployment Mismatch in Fine-Tuned Language Models

Autonomous Topology Mutation: Safe Runtime Restructuring for Multi-Agent LLM Systems with Capability, State, and Shadow Invariants

Elastic Gang: Per-Token Membership Change for a Hard-Barriered LLM Inference Gang Co-Scheduled with OS Processes

Phionyx: A Deterministic AI Runtime Architecture with Structured State Management and Pre-Response Governance

Policy-Masked Private Experts: Auditable and Reversible Capability Access Control in Sparse MoE Models