paper-with-me

홈 › Papers

Beyond Scaling: Agents Are Heading to the Edge

2026-05-18 · Chunlin Tian, Dongqi Cai, Wanru Zhao, Nicholas D. Lane arxiv

The bottleneck of useful agentic intelligence has shifted from compressing world knowledge into a single model to executing a coordinated system. This position paper argues that personal-agent architecture must move to the edge because the core properties of agentic intelligence tasks, particularly their structural coupling with high-fidelity local context and the need for zero-latency execution loops, do not sit well with cloud-centric designs. We develop this claim through three structural shifts. First, the Prefrontal Turn: the main marginal lever of capability has moved from pre-training scale to framework-level executive control. Such control must remain physically close to the environment of action if the agent is to preserve cognitive alignment. Second, the Data-Geography Paradox, the ``dark matter'' of agentic data (local file hierarchies, real-time sensor streams, and transient OS states) degrades, disappears, or loses meaning once prepared for cloud transmission, thereby cutting the agent off from ground-truth context. Third, the interaction-alignment loop, the only economically and ecologically sustainable source of agentic refinement data is the high-fidelity implicit preference signal produced through real-time local interaction. Third, the interaction-alignment loop, the only economically and ecologically sustainable source of agentic refinement data is the high-fidelity implicit preference signal produced through real-time local interaction. We conclude with falsifiable predictions for the next deployment cycle of personal agents.

📄 PDF Abstract BibTeX arXiv:2605.18535

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Categorizing Wireheading in Partially Embedded Agents

2019-06-21 · Arushi Majha, Sayan Sarkar, Davide Zagami

$\textit{Embedded agents}$ are not explicitly separated from their environment, lacking clear I/O channels. Such agents can reason about and modify their internal parts, which they are incentivized to shortcut or $\texti…

EZREAL: Enhancing Zero-Shot Outdoor Robot Navigation toward Distant Targets under Varying Visibility

2025-09-17 · Tianle Zeng, Jianwei Peng, Hanjing Ye, Guangcheng Chen 외 arxiv

Zero-shot object navigation (ZSON) in large-scale outdoor environments faces many challenges; we specifically address a coupled one: long-range targets that reduce to tiny projections and intermittent visibility due to p…

Robot NavigationImage Rescaling

Avoiding Wireheading with Value Reinforcement Learning

2016-05-10 · Tom Everitt, Marcus Hutter

How can we design good goals for arbitrarily intelligent agents? Reinforcement learning (RL) is a natural approach. Unfortunately, RL does not work well for generally intelligent agents, as RL agents are incentivised to …

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Emergence of Addictive Behaviors in Reinforcement Learning Agents

2018-11-14 · Vahid Behzadan, Roman V. Yampolskiy, Arslan Munir

This paper presents a novel approach to the technical analysis of wireheading in intelligent agents. Inspired by the natural analogues of wireheading and their prevalent manifestations, we propose the modeling of such ph…

Q-Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

FS-Researcher: Test-Time Scaling for Long-Horizon Research Tasks with File-System-Based Agents

2026-02-02 · Chiwei Zhu, Benfeng Xu, Mingxuan Du, Shaohan Wang 외 arxiv

Deep research is emerging as a representative long-horizon task for large language model (LLM) agents. However, long trajectories in deep research often exceed model context limits, compressing token budgets for both evi…