arXiv AI
Jun 24
LemonHarness Technical Report
arXiv:2606. 24311v1 Announce Type: new Abstract: As large language model (LLM) agents are applied to longer tasks, they increasingly modify workspace state across multiple rounds of iteration.
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.
Related stories
arXiv Machine Learning
Jun 19
Execution-State Capsules: Graph-Bound Execution-State Checkpoint and Restore for Low-Latency, Small-Batch, On-Device Physical-AI Serving
arXiv:2606. 20537v1 Announce Type: new Abstract: Mainstream LLM serving systems reuse prefix work mainly through paged or radix key-value (KV) caches.
arXiv AI
Jul 23
AgentCgroup: Understanding and Controlling OS Resources of AI Agents
arXiv:2602. 09345v3 Announce Type: replace-cross Abstract: AI agents are increasingly deployed in multi-tenant cloud environments, where they execute diverse tool calls within sandboxed containers, each call with distinct resource demands and rapid fluctuations.
arXiv AI
Jun 29
DataStates-LLM: Scalable Checkpointing for Transformer Models Using Composable State Providers
arXiv:2601. 16956v1 Announce Type: cross Abstract: The rapid growth of Large Transformer-based models, specifically Large Language Models (LLMs), now scaling to trillions of parameters, has necessitated training across thousands of GPUs using complex hybrid parallelism strategies (e.
arXiv AI
Jul 28
SpecBox: Speculative Sandbox Scheduling for Efficient LLM Agent Serving
arXiv:2607. 23933v1 Announce Type: cross Abstract: As LLM agents increasingly rely on the Model Context Protocol (MCP) to invoke isolated external sandboxes, disaggregated sandbox deployment introduces a fundamental tension between resource utilization and interactive tail latency.
arXiv Machine Learning
Aug 18
Belayer: Efficient Fault Tolerance for LLM Agentic RL Training
arXiv:2608. 14635v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly trained with reinforcement learning in long-horizon, sandboxed environments.
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.
arXiv AI
Jul 28
CORVUS: Context Optimization and Reduction Via Underlying Synchronization for LLM Coding Agents
arXiv:2607. 22711v1 Announce Type: cross Abstract: LLM coding agents operate by constructing trajectories that accumulate reasoning, tool calls, and results to enable multi-step decision-making.
arXiv AI
Jun 30
Agent libOS: A Runtime Substrate for Capability-Controlled Self-Evolving LLM Agents
arXiv:2606. 03895v2 Announce Type: replace-cross Abstract: Large language model (LLM) agents are becoming long-running software actors rather than fixed tool users.
Hugging Face Trending Papers
Jun 22
Concordia: JIT-Compiled Persistent-Kernel Checkpointing for Fault-Tolerant LLM Inference
Long-running LLM agents keep valuable state resident on GPUs: KV caches, request schedulers, communication state, and sometimes online adapters. Losing this state after a GPU or communicator failure can discard minutes to hours of work, yet existing recovery mechanisms either restart the whole serving stack or require application-specific checkpoint logic inside every attention and runtime component.
arXiv AI
Jun 3
Agent libOS: A Library-OS-Inspired Runtime for Long-Running, Capability-Controlled LLM Agents
arXiv:2606. 03895v1 Announce Type: cross Abstract: Large language model (LLM) agents are evolving from request-response assistants into long-running software actors: they maintain state across model calls, fork subtasks, wait for external events, request human authority, generate tools, and perform side effects that must be resumed and audited.
arXiv AI
Sep 12
Memory Compression for High-Fanout Agent Sandboxes
The paper introduces AgentZip, a memory compression system tailored for high‑fanout AI‑agent sandboxes. It exploits template‑relative and cross‑sandbox redundancy, expands compression to any profitable page, and shifts overhead control to restore‑time prefetching. The approach aligns compression with LLM waiting periods, achieving up to 8.7× memory reduction and reducing slowdown to 1.40× while preserving most savings.