paper-with-me

홈 › Papers

Grounded Scaling: Why Agentic AI Needs Deterministic Environments

2026-06-21 · Liang Ding, Xintong Wang arxiv

Long-chain agent execution fails exponentially in environments designed for human tolerance: with per-step determinism $δ< 1$, $k$-step chain success degrades as $δ^k$. The AGI-to-ASI scaling debate (Genewein et al., 2026) has so far framed progress as a race between compute growth and a list of frictions (data wall, abstraction barrier, embodied bottleneck, multi-agent trust); we argue that environment determinism is a complementary binding axis cutting across all four, for the broad class of agentic AI tasks whose outcomes are verifiable economically, physically, or through multi-party settlement. Three formal results pin down the regime: a Determinism-Efficiency Bound on chain-task success, a Verifier-Goodharting Floor on flywheel ceilings under imperfect rewards, and a convergence condition for environment-side skill evolution. We operationalise the framework as a Supply Certainty Index (SCI) over five measurable properties, a five-level Determinism Maturity Model (DMM) as adoption ladder, and a falsifiable open-question programme (OQ1-OQ5) with explicit null results that would force retraction. The position is platform-agnostic. We engage three competing positions: sim-to-real sufficiency, alignment sufficiency, and AI-as-normal-technology.

📄 PDF Abstract BibTeX arXiv:2606.22495

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

DockSmith: Scaling Reliable Coding Environments via an Agentic Docker Builder

2026-01-31 · Jiaran Zhang, Luck Ma, Fanqi Wan, Di Qi 외 arxiv

Reliable Docker-based environment construction is a dominant bottleneck for scaling execution-grounded training and evaluation of software engineering agents. We introduce DockSmith, a specialized agentic Docker builder …

Towards General Agentic Intelligence via Environment Scaling

2025-09-16 · Runnan Fang, Shihao Cai, Baixuan Li, Jialong Wu 외 arxiv

Advanced agentic intelligence is a prerequisite for deploying Large Language Models in practical, real-world applications. Diverse real-world APIs demand precise, robust function-calling intelligence, which needs agents …

Scaling Agentic Capabilities via Grounded Interaction Synthesis

2026-06-01 · Wenhang Shi, Jinhao Dong, Yiren Chen, Zhe Zhao 외 arxiv

General agentic intelligence hinges on the ability to interact with diverse real-world tools to complete complex tasks, a capability fundamentally tied to the quality of interaction data. To bypass the prohibitive costs …

CuES: A Curiosity-driven and Environment-grounded Synthesis Framework for Agentic RL

2025-12-01 · Shinji Mai, Yunpeng Zhai, Ziqian Chen, Cheng Chen 외 arxiv

Large language model based agents are increasingly deployed in complex, tool augmented environments. While reinforcement learning provides a principled mechanism for such agents to improve through interaction, its effect…

Reinforcement Learning

Masked Diffusion Language Models are Strong and Steerable Text-Based World Models for Agentic RL

2026-05-07 · Darshan Deshpande hf

Recent growth in reinforcement learning (RL) has surfaced a need for diverse, specialized training environments. Hand-curated environments with fixed task and reward difficulties become ineffective signals as model perfo…