arXiv AI
Jun 9
DeltaBox: Scaling Stateful AI Agents with Millisecond-Level Sandbox Checkpoint/Rollback
arXiv:2605. 22781v2 Announce Type: replace-cross Abstract: LLM-powered AI agents require high-frequency state exploration (e.
AEC-DS: Adaptive Erasure Coding with PDP-Triggered Reputation and QoS-Aware Migration for Decentralized Storage
arXiv:2607. 17460v1 Announce Type: new Abstract: In decentralized storage systems, audit results are often not used directly to guide later redundancy and shard-placement decisions, which can lead to inefficient resource allocation and delayed recovery.
Related stories
arXiv Machine Learning
Jul 8
PHOENIX: Resilient LLM Training with Hot-Swapping via Zero-Overhead Checkpoint
arXiv:2607. 01646v2 Announce Type: replace Abstract: State-of-the-art large language model (LLM) training takes tens of thousands of graphics processing units (GPUs) for months and encounters failures across the software and hardware stack.
arXiv AI
Jul 14
The Hidden Footprint: Making Storage a First-Class Metric for LLM Agent Evaluation
arXiv:2607. 11149v1 Announce Type: new Abstract: LLM agent benchmarks measure task completion, reliability, and inference cost, but not the persistent data an agent run leaves on disk, including logs, context snapshots, checkpoints, and debug traces.
arXiv AI
22h ago
The Acknowledgment Point Is the System: Durable Policy-Decision Receipts for AI Audit Evidence
arXiv:2608. 17176v1 Announce Type: cross Abstract: An AI audit record is useful only if its durability and trust boundary are explicit.
arXiv AI
Jul 13
Blockchain-Linked Auditable Decision Management for Telecom/IoT Fraud-Control Requests
arXiv:2607. 09259v1 Announce Type: cross Abstract: Telecom fraud-control studies often stop at detector-level classification, but deployment use requires request-level policy resolution, lifecycle traceability, and auditability.
arXiv Machine Learning
Jul 3
DeadPool: Resilient LLM Training with Hot-Swapping via Zero-Overhead Checkpoint
arXiv:2607. 01646v1 Announce Type: new Abstract: State-of-the-art large language model (LLM) training takes tens of thousands of graphics processing units (GPUs) for months and encounters failures across the software and hardware stack.
arXiv AI
Jun 3
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.
arXiv AI
Jun 30
Always-OnAgents:A Survey of Persistent Memory, State, and Governance in LLMAgents
arXiv:2606. 30306v1 Announce Type: cross Abstract: Always-on agents are systems whose future behavior depends on durable state accumulated across earlier interactions.
Hugging Face Trending Papers
Jul 13
The Hidden Footprint: Making Storage a First-Class Metric for LLM Agent Evaluation
LLM agent benchmarks measure task completion, reliability, and inference cost, but not the persistent data an agent run leaves on disk, including logs, context snapshots, checkpoints, and debug traces. We introduce AgentFootprint, a cross-framework benchmark of post-run agent storage footprint.
arXiv AI
Jun 11
SPEAR: A System for Post-Quantization Error-Adaptive Recovery Enabling Efficient Low-Bit LLM Serving
arXiv:2606. 11244v1 Announce Type: cross Abstract: Efficient large language model (LLM) serving is increasingly constrained by deployment cost.
arXiv AI
Aug 10
TEPA: Revoking Stale Memories for Conflict-Robust Language Agents
arXiv:2608. 07429v1 Announce Type: new Abstract: Long-term memory enables language agents to reuse past facts, preferences, and task experience.
arXiv AI
Jun 10
Regimes: An Auditable, Held-Out-Gated Improvement Loop Demonstrated on LongMemEval with ActiveGraph
arXiv:2606. 10241v1 Announce Type: new Abstract: Autonomous improvement loops are hard to trust because the improvement process is usually external scaffolding bolted onto the agent: failures go unlogged, diagnoses cannot be replayed, and promote-or-discard decisions land in a side database rather than the agent's own history.