Beyond Scaling: Self-Evolving LLM Agents for Hardware Kernel Optimization via an Experience-Driven Workflow and Experience Graph Memory

• URL: http://arxiv.org/abs/2608.25570v1
• Date: Wed, 26 Aug 2026 09:27:39 GMT
• Title: Beyond Scaling: Self-Evolving LLM Agents for Hardware Kernel Optimization via an Experience-Driven Workflow and Experience Graph Memory
• Abstract summary: Existing kernel-optimization agents seldom preserve a decision, its observed execution feedback, and the later decisions that use that evidence.<n>We present KOPE, an experience-driven framework for hardware kernel optimization.
• Score: 19.236924182307085
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Hardware kernel optimization requires repeated compilation, correctness testing, profiling, and revision. LLM agents can automate parts of this process, and stronger foundation models, longer context windows, and longer execution horizons have improved optimization within individual tasks. These advances alone do not enable an agent to learn from completed optimization runs. Existing kernel-optimization agents seldom preserve a decision, its observed execution feedback, and the later decisions that use that evidence. Retaining every prior trajectory is also impractical because an expanding history competes with the current task for context. We present KOPE, an experience-driven framework for hardware kernel optimization. KOPE records optimization trajectories with correctness and performance feedback in Experience Graph Memory, then uses Active Context Management and Injection to retrieve relevant experience under a fixed token budget. The graph retains decision order, observed outcomes, and alternative branches, allowing evidence collected on the target hardware to inform later optimization steps and tasks. Under the same GLM-5.2 setting, the geometric mean of KOPE's per-operator speedups is $1.54\times$ that of CANNBot, the strongest competing baseline. In a complete 53-operator ablation, Active Context Management and Injection raises pass rate from 60.0\% to 84.6\%, increases the evaluator-reported positive-field geometric mean from 0.0382 to 0.0661, and reduces optimization token consumption from 15.9B to 1.113B tokens relative to passive agent-led context construction. Enabling Experience Graph Memory raises full-suite pass rate from 55.2\% to 84.6\% and yields a $1.43\times$ geometric-mean speedup on valid timing comparisons. These results support continual optimization through external experience while the foundation model remains fixed.

Related papers

• COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization [55.60171725587438]
  Large language model (LLM) agents can benefit from reusable skills distilled from prior task experience.<n>Existing skill optimization methods often rely on costly execution-based evaluation and substantial task data.<n>We introduce textbfCOBRA-Skills, an efficient framework that formulates skill optimization as budgeted sequential optimization over a dynamically evolving candidate space.
  arXiv  Detail & Related papers  (2026-09-10T15:12:24Z)
• LLM4LLM: Bridging Kernel Benchmarks and Real Deployment via Closed-Loop Agentic Optimization [7.393546440833148]
  Large language models have become increasingly capable agents for low-level code and kernel optimization.<n>We introduce LLM4LLM, a deployment-aware closed-loop optimization framework.<n>It improves end-to-end latency for every evaluated model, achieving 3.91$times$/6.98$times$ geometric-mean speedups on A100/H100.
  arXiv  Detail & Related papers  (2026-08-22T08:12:16Z)
• Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0 [53.71882250666667]
  Most reported gains from agent-optimization methods are one-shot.<n>This does not test the setting that matters for deployed agents.<n>We compare three approaches to agent-harness optimization.
  arXiv  Detail & Related papers  (2026-07-15T16:36:04Z)
• From Noisy Traces to Root Causes: Structural Trajectory Analysis and Causal Extraction for Agent Optimization [13.259841042680724]
  We introduce STRACE, a framework that constructs high signal-noise optimization contexts.<n> STRACE mines failure patterns to filter redundant traces and retain representative failures.<n>It significantly outperforms standard context-filtering baselines.
  arXiv  Detail & Related papers  (2026-07-08T17:57:27Z)
• PERFOPT-Bench: Evaluating Coding Agents on Software Performance Optimization [18.924749191192433]
  Performance optimization is a distinct agentic task.<n>We introduce PERFOPT-Bench, a benchmark for evaluating this full performance-engineering loop.
  arXiv  Detail & Related papers  (2026-07-08T08:32:18Z)
• optimize_anything: A Universal API for Optimizing any Text Parameter [98.42497715725356]
  We show a single AI-based optimization system-supporting single-task search, multi-task search with cross-problem transfer, and generalization to unseen inputs.<n>We show for the first time that text optimization with LLM-based search is a general-purpose problem-solving paradigm.
  arXiv  Detail & Related papers  (2026-05-19T10:18:12Z)
• Optimas: An Intelligent Analytics-Informed Generative AI Framework for Performance Optimization [0.6117371161379209]
  Optimas is a modular, fully automated, end-to-end generative AI framework built on a multi-agent workflow.<n>It maps performance diagnostics to established, literature-backed code transformations.<n>It generates 100% correct code and improves performance in over 98.82% of experiments.
  arXiv  Detail & Related papers  (2026-04-26T21:34:51Z)
• AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation [59.964989458924585]
  AdaExplore is an agent framework that enables self-improvement via accumulated execution feedback for performance-critical kernel code generation.<n>In the adaptation stage, the agent synthesizes tasks and converts recurring failures into a reusable memory of validity rules.<n>In the search stage, the agent organizes candidate kernels as a tree and alternates between small local refinements and larger structural regeneration.
  arXiv  Detail & Related papers  (2026-04-17T18:25:03Z)
• AscendOptimizer: Episodic Agent for Ascend NPU Operator Optimization [13.951709632040908]
  We present Ascendr, an episodic agent that bootstraps this missing expertise by turning execution into experience.<n>Ascendr achieves a 1.19x geometric-mean speedup over the open-source baseline, with 49.61% of operators their references, outperforming strong agent and search baselines.
  arXiv  Detail & Related papers  (2026-03-24T08:54:53Z)
• MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Learning [73.27233666920618]
  We propose MemSearcher, an agent workflow that iteratively maintains a compact memory and combines the current turn with it.<n>At each turn, MemSearcher fuses the user's question with the memory to generate reasoning traces, perform search actions, and update memory to retain only information essential for solving the task.<n>We introduce multi-context GRPO, an end-to-end RL framework that jointly optimize reasoning, search strategies, and memory management of MemSearcher Agents.
  arXiv  Detail & Related papers  (2025-11-04T18:27:39Z)
• In-the-Flow Agentic System Optimization for Effective Planning and Tool Use [73.72524040856052]
  AgentFlow is a trainable, in-the-flow agentic framework that coordinates four modules (planner, executor, verifier, generator) through an evolving memory.<n>Flow-GRPO tackles long-horizon, sparse-reward credit assignment by converting multi-turn optimization into a sequence of tractable single-turn policy updates.<n>AgentFlow with a 7B-scale backbone outperforms top-performing baselines with average accuracy gains of 14.9% on search, 14.0% on agentic, 14.5% on mathematical, and 4.1% on scientific tasks.
  arXiv  Detail & Related papers  (2025-10-07T05:32:44Z)
• DARS: Dynamic Action Re-Sampling to Enhance Coding Agent Performance by Adaptive Tree Traversal [55.13854171147104]
  Large Language Models (LLMs) have revolutionized various domains, including natural language processing, data analysis, and software development.<n>We present Dynamic Action Re-Sampling (DARS), a novel inference time compute scaling approach for coding agents.<n>We evaluate our approach on SWE-Bench Lite benchmark, demonstrating that this scaling strategy achieves a pass@k score of 55% with Claude 3.5 Sonnet V2.
  arXiv  Detail & Related papers  (2025-03-18T14:02:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.