arXiv AI
Should SLMs be in the Driver's Seat? A Study of Local Models as Interpreters in Cloud-Written Agent Programs
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Oct 1
AgBench: Agentic AI Benchmarks for Personal AI Devices
arXiv:2609.38652v1 Announce Type: new Abstract: Agentic AI systems increasingly rely on cloud-hosted large language models for planning, tool use, and iterative execution, raising concerns about API...
arXiv AI
Oct 15
CoMIC: Collaborative Memory and Insights Circulation for Long-Horizon LLM Agents in Web Cloud-Edge Systems
arXiv:2606.00756v2 Announce Type: replace Abstract: LLM-based Web agents are increasingly deployed on edge servers to carry out long-horizon tasks on behalf of users with low latency. However, the li...
arXiv AI
Aug 11
SkillSmith: Enhancing Locally Deployed Agents via Automatic Skill Construction and Evolution
arXiv:2608. 08037v1 Announce Type: new Abstract: LLM-based agent frameworks now act as personal assistants for multi-step tasks.
arXiv AI
Aug 18
From LLM Inference to Agentic Workloads: Characterization and Implications for Serving Systems
arXiv:2608. 15127v1 Announce Type: cross Abstract: Agentic applications are shifting AI serving from isolated model inference to long-running workloads in which LLMs coordinate tools, environments, and persistent state.
arXiv AI
Oct 7
Do I Need the Cloud? Uncertainty-Aware Step-Level Handoff for Small Language Model Agents
The paper introduces STEPGATE, an uncertainty‑aware handoff framework that evaluates each step of a small language model (SLM) agent and selectively escalates difficult steps to a stronger model. On a 52‑task single‑step benchmark, the Qwen2.5‑1.5B/7B pair achieved 82.7% task success with only 30.8% escalation, outperforming local‑only and random escalation baselines. In multi‑turn tests, STEPGATE reached 69.0% trajectory success and 84.0% action success while using only 30.0% cloud actions, demonstrating that step‑level escalation can close much of the performance gap to a stronger backend with fewer remote tokens.
arXiv Computation and Language
5d ago
Agentic World Modeling for Agent Test-time Scaling without Environment Replica
Agentic World Modeling (AWM) redefines next-observation prediction as a multi-turn evidence-acquisition task, allowing agents to query a real environment safely and construct observations without mutating shared state. Integrated with trajectory-level test-time scaling, AWM enables parallel exploration over a single shared environment, outperforming single-shot simulation by 40.07% and trained world-model baselines by 12.36% on benchmarks such as τ-bench, AppWorld, and OfficeBench. This approach provides a practical foundation for safe and scalable agentic test-time scaling in shared, non-resettable environments.