# Local Agentic Theory For Mobile Games — Shafik Quoraishee & Joanne Song, The New York Times

## Executive summary

The presentation outlines 'Local Agentic Theory' for mobile games, arguing that the future of AI gaming lies in decentralized, on-device agents rather than centralized cloud models. These local agents use advanced techniques (like LLM reasoning over game state) to provide highly personalized experiences. Furthermore, this approach allows accessibility features to move beyond static toggles, enabling real-time, dynamic tuning of gameplay difficulty and interaction controls based on the user's live context (e.g., tracking eye gaze or shaky taps).

## Key takeaways

- Local Computation is Essential for Mobile AI: Running AI locally minimizes latency, avoids expensive cloud inference calls, and ensures privacy by keeping computation within the device's security zone. This allows advanced AI features to function reliably even without constant internet connectivity (e.g., in a subway tunnel).
- Agentic Systems vs. Reinforcement Learning (RL): While RL models train by changing weights through cycles, an agentic system uses language models and in-context learning to reason over the game's state space. This allows for a more dynamic loop that adapts to new situations using local device functionality.
- The Device Budget Constraint: Local agents must operate within strict resource budgets: time (fitting planning into a single 16ms frame for 60Hz refresh rates), space (managing model weights and state history compression), and energy (optimizing processing to prevent rapid battery drain).
- Accessibility as a Graded Dial, Not Toggles: Traditional fixed-state games are limited by static menus. The proposed model uses international standards like WCAG 2.2 to build dynamic player states. Agents can actively monitor user input (e.g., tracking eye gaze or analyzing shaky taps) and dynamically adjust controls—such as resizing targets or injecting exit routes from focus traps—to meet the player's real-time needs.

## Technical details

- AI Architecture: The shift is moving from traditional Finite State Machines (FSM) and Reinforcement Learning (RL) to agentic systems, which utilize LLMs for reasoning over the game state. Models like EfficientZero are noted as state-of-the-art sample efficient RL models.
- Performance Constraints: The agent's planning must fit within a strict time budget (e.g., 16ms per frame at 60Hz). The system uses constraint graphs to manage space, time, and energy constraints simultaneously.
- Accessibility Standards: The design grounds itself in WCAG 2.2 (Perceivable, Operable, Understandable, Robust). The concept of accessibility is shifting from binary pass/fail to a graded scale that tunes dials like 'input tolerance' and 'step granularity' based on real-time user context.

## Practical implications

- Game development can incorporate highly responsive and empathetic AI that actively audits the user interface in real-time.
- The focus shifts from building fixed game states to creating systems that negotiate between challenge and accessibility on a continuous dial.
- Future mobile applications will leverage specialized hardware like Neural Processing Units (NPUs) for efficient, low-power agentic workloads.

## Topics

Artificial Intelligence, Mobile Computing, Game Development, Accessibility Design, Agentic Systems, The New York Times Mini Crossword, WCAG 2.2 / WCAG 3.0

Source: https://www.youtube.com/watch?v=418t26CVz-w