First International Workshop on Agentic Approaches to Computer Architecture
Co-located with MICRO 2026, on November 1. A forum for exploring how reasoning-capable AI agents redefine the design of computer architectures and systems.
The rise of reasoning-capable AI marks a paradigm shift for many design tasks, including computer architecture and systems design. Autonomous AI agents are now capable of completing long-horizon tasks, such as multi-step planning, algorithmic design, and tool manipulation, that were once carried out by expert human architects. The A3 (Agentic Approaches to Architecture) workshop explores how this evolution redefines the design of computer systems, exploring new AI-driven methodologies.
The objective of A3 is to catalyze a community around agentic methodologies for computer architecture. The workshop will strive to become a forum for presenting early-stage work in this nascent area, and synthesizing best practices through panel discussions and expert talks.
As a focused subset of the broader ML-for-Systems space, A3 centers on agentic methodologies for computer architecture. These workflows incorporate the following aspects.
Real-time monitoring of architectural and system telemetry, from cache-miss distributions and OS resources to thermal and power envelopes.
Moving beyond "if-then" logic to dynamic planning. Agents use logic engines (LLMs or RL) to decompose goals (e.g., "minimize latency under a 10W constraint") into actionable sequences.
Agents exerting direct control, such as calling EDA APIs, triggering RTL simulations, managing architectural simulations, operating-system support, or reconfiguring hardware registers in situ.
Systems maintain a "log" of outcomes to avoid past failures. If an action yields sub-optimal results, the agent re-reasons and pivots its strategy.
Architectures and systems that are agent-facing, including abstractions, interfaces, and programmability requirements that cut across microarchitecture, computer architecture, operating systems, and VLSI.
Short research papers, position pieces, and crazy ideas that use agentic methodologies to push boundaries up and down the hardware/software stack. Submissions should range from 2 to 4 pages and be in two-column format. Presenting a paper at A3 does not preclude future conference publication.
View the Call for Papers → Call for ProposalsA month-long hands-on CHIA hackathon sponsored by Google, with free access to GCP, Gemini, and other Google AI platforms. Participants develop agentic approaches to solve real-world problems in architecture, VLSI, HW/SW co-design, and compilers. Solutions are built in the open-source CHIA framework to enable rapid prototyping and to foster a reusable and composable ecosystem of AI-driven co-design flows. Every team that submits a proposal receives compute credits and can compete: the top three final projects will receive cash prizes ($750, $500, $250) and will be invited to give a talk at the A3 Workshop, and all participants will be invited to present a poster.
View the Hackathon CFP →This will be a half-day workshop featuring the following sessions:
A3 is jointly organized by Google/Google DeepMind, UC Berkeley, Carnegie Mellon University, and NVIDIA. The organizers can be reached at: a3-workshop@eecs.berkeley.edu
Thanks to Google for sponsoring A3 and the A3 CHIA hackathon!