The paper investigates whether AI agents truly understand computer architecture by comparing their performance when the same 15‑dimensional accelerator design space is presented either as meaningful architectural knobs or as anonymous variables. Using the AutoTuring framework, the authors find that agents with architectural knowledge outperform blind agents on a nine‑kernel FP16 GEMM benchmark, yet a critic loop can largely recover this advantage. The study highlights that architectural knowledge and structured critique act as substitutes rather than complements in improving agent performance.
Agents are increasingly asked to design hardware, and increasingly reported to succeed. Such reports establish that a design improved; they cannot establish why. An agent that improves an accelerator...
The paper introduces Formulaic, a workflow that separates the tasks of an agentic language-model agent, a mathematical solver, and verification to co-design AI hardware and software. The agent iteratively refines problem formulations from the computation graph down to the chip, using templates that guarantee correctness. Experiments on NVIDIA GB10 and a simulated Ventus GPU show significant speedups for Qwen models and faster verification through proof reuse.
The paper introduces $ au^ au$-Bench, a benchmark that turns the construction of AI agents into a measurable task. In this environment a developer agent receives real business records, client requirements, a production API, an existing codebase, and constraints on cost and models, and must deliver a complete customer‑service agent. The benchmark evaluates performance by deploying the agent against simulated users, revealing that current state‑of‑the‑art models achieve only 23.9% success while an expert‑written reference scores 82.2%.
Humanize is a multi‑agent workflow for agentic coding that uses explicit, mechanically enforced decisions—called judgement engineering—to separate planning, implementation, review, and learning. A human approves a plan contract, a builder agent implements it in rounds, and a reviewer agent from another vendor decides completion, with deterministic hooks and 72 mechanical gates ensuring that a defect survives only if both models miss it. The system has been deployed in over 68 versions in 108 days, earned 1,468 GitHub stars, and powered applications such as a 567‑file gem5 build‑system migration, Kernel Design Agents that excelled in MLSys 2026 contests, and Humanize Olympiad Agents that achieved top scores in multiple international competitions and high rankings on PutnamBench and Lean‑Eval. whyItMatters":"Humanize demonstrates that a structured, multi‑agent approach with explicit mechanical gates can improve reliability and performance in automated code generation, as evidenced by its adoption, star count, and success in competitive benchmarks."
arXiv:2610.27797v1 Announce Type: new Abstract: 6G will be designed faster than it can be built: AI-driven search already proposes physical-layer algorithms at machine speed, while carrying a single...
The paper introduces the concept of substrate blindness, where AI agents lack execution context in their planning. By providing a 128 MB RAM and 10 s wall‑time contract to large language models, the authors show that agents generate code that uses less memory, runs faster, and incorporates structural changes such as bounded blocking and in‑place buffers. Across three leading models, contract disclosure improved resource usage and correctness, demonstrating that minimal execution contracts can guide agents to produce more efficient programs.
InfraDev is a new benchmark comprising 36 tasks derived from real-world pull requests to Megatron‑LM, vLLM, and verl, designed to test coding agents on infrastructure development for training, inference, and reinforcement learning across many GPUs. Each task requires agents to reimplement multi‑file changes and run correctly, with grading that includes hidden probes and a prompt exposing only the interfaces used. The benchmark reveals that current frontier models resolve only about 39% of tasks, with probes rejecting a third of submissions that pass official tests, and that structural and state errors dominate failures.
Agentic Architect is a new framework that uses large language models to automatically evolve and optimize CPU microarchitectural designs. Starting from a seed design, the LLM proposes code changes, which are compiled, simulated, and evaluated against performance, area, and power constraints, with results feeding back into subsequent iterations. The framework was tested on prefetching, cache replacement, and branch prediction, achieving notable speedups and area reductions compared to state‑of‑the‑art designs.
The paper argues that evaluating agents as fixed models is insufficient, proposing instead to treat them as configurable systems. Using a new benchmark of four scientific tasks, the authors analyze how five configuration aspects—task information, reasoning, self‑verification, time budget, and backbone model—affect performance, noting that about 54% of outcome variance arises from run‑to‑run differences even with the same settings. The study finds that providing more task information has the strongest impact, while interactions among settings (e.g., extra time only helps with adequate information or model capability) and the choice of verification tools significantly shape agent behavior.
arXiv:2607. 13034v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly automate multi-step engineering and informatics workflows, yet they rarely ask how much effort a task actually requires.
The paper proposes adding a verification layer to large language model agents, using a V-model design where each step of the agent’s plan has a dedicated verifier. In a pilot study on the MuSiQue dataset, verified configurations outperformed unverified ones, with deterministic gates correcting most errors at zero cost. The authors plan to extend the architecture to full integration and evaluate it over the next year.
arXiv:2607. 21268v1 Announce Type: cross Abstract: In many social-science research tasks, such as economics, LLM-based agents must produce outputs for which no cheap, task-complete, machine-readable correctness signal exists.