COEVO: Co-Evolutionary Framework for Joint Functional Correctness and PPA Optimization in LLM-Based RTL Generation

• URL: http://arxiv.org/abs/2604.15001v2
• Date: Fri, 17 Apr 2026 09:58:55 GMT
• Title: COEVO: Co-Evolutionary Framework for Joint Functional Correctness and PPA Optimization in LLM-Based RTL Generation
• Abstract summary: COEVO is a co-evolutionary framework that unifies correctness and PPA optimization within a single evolutionary loop.<n>COEVO formulates correctness as a continuous co-optimization dimension alongside area, delay, and power, enabled by an enhanced testbench.<n> evaluated on VerilogEval 2.0 and RTLLM 2.0, COEVO achieves 97.5% and 94.5% Pass@1 with GPT-5.4-mini.
• Score: 13.387204340085944
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: LLM-based RTL code generation methods increasingly target both functional correctness and PPA quality, yet existing approaches universally decouple the two objectives, optimizing PPA only after correctness is fully achieved. Whether through sequential multi-agent pipelines, evolutionary search with binary correctness gates, or hierarchical reward dependencies, partially correct but architecturally promising candidates are systematically discarded. Moreover, existing methods reduce the multi-objective PPA space to a single scalar fitness, obscuring the trade-offs among area, delay, and power. To address these limitations, we propose COEVO, a co-evolutionary framework that unifies correctness and PPA optimization within a single evolutionary loop. COEVO formulates correctness as a continuous co-optimization dimension alongside area, delay, and power, enabled by an enhanced testbench that provides fine-grained scoring and detailed diagnostic feedback. An adaptive correctness gate with annealing allows PPA-promising but partially correct candidates to guide the search toward jointly optimal solutions. To preserve the full PPA trade-off structure, COEVO employs four-dimensional Pareto-based non-dominated sorting with configurable intra-level sorting, replacing scalar fitness without manual weight tuning. Evaluated on VerilogEval 2.0 and RTLLM 2.0, COEVO achieves 97.5\% and 94.5\% Pass@1 with GPT-5.4-mini, surpassing all agentic baselines across four LLM backbones, while attaining the best PPA on 43 out of 49 synthesizable RTLLM designs.

Related papers

• Breaking $\ extit{Winner-Takes-All}$: Cooperative Policy Optimization Improves Diverse LLM Reasoning [53.42577591449649]
  Group Cooperative Policy Optimization shifts the training paradigm from rollout competition to team cooperation.<n>GCPO replaces independent rollout scoring with team-level credit assignment.<n>It redistributes the collective team reward to each single rollout according to its average marginal contribution to the team.
  arXiv  Detail & Related papers  (2026-05-12T03:20:24Z)
• HMACE: Heterogeneous Multi-Agent Collaborative Evolution for Combinatorial Optimization [19.90781293176099]
  HMACE is a Heterogeneous Multi-Agent Collaborative Evolution framework.<n>It decomposes each evolutionary generation into an autonomous, role-specialized loop with four coordinated agents.<n>It guides the search toward diverse and promising behaviors while avoiding redundant evaluations.
  arXiv  Detail & Related papers  (2026-05-08T04:02:28Z)
• FedPDPO: Federated Personalized Direct Preference Optimization for Large Language Model Alignment [55.97027207627]
  Fed PDPO (Federated Personalized Direct Preference Optimization) is a personalized framework for preference alignment of large language models (LLMs)<n>It adopts a parameter-efficient fine-tuning architecture where each client maintains a frozen pretrained LLM backbone augmented with a Low-Rank Adaptation (LoRA) adapter, enabling communication-efficient aggregation.<n>Experiments on multiple preference datasets demonstrate state-of-the-art performance, achieving up to 4.80% average accuracy improvements in federated intra-domain and cross-domain settings.
  arXiv  Detail & Related papers  (2026-03-20T08:24:49Z)
• POET: Power-Oriented Evolutionary Tuning for LLM-Based RTL PPA Optimization [15.350025051608064]
  We propose POET (Power-Oriented Evolutionary Tuning), a framework that addresses both challenges.<n>For functional correctness, POET introduces a differential-testing-based testbench generation pipeline that treats the original design as a functional.<n>For PPA optimization, POET employs an LLM-driven evolutionary mechanism with non-dominated sorting, power-first intra-level ranking, and proportional survivor selection.
  arXiv  Detail & Related papers  (2026-03-19T03:19:32Z)
• GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization [133.27496265096445]
  We show how to apply Group Relative Policy Optimization under multi-reward setting without examining its suitability.<n>We then introduce Group reward-Decoupled Normalization Policy Optimization (GDPO), a new policy optimization method to resolve these issues.<n>GDPO consistently outperforms GRPO, demonstrating its effectiveness and generalizability for multi-reward reinforcement learning optimization.
  arXiv  Detail & Related papers  (2026-01-08T18:59:24Z)
• Anchoring Values in Temporal and Group Dimensions for Flow Matching Model Alignment [61.80228667422234]
  VGPO redefines value estimation across both temporal and group dimensions.<n>It transforms the sparse terminal reward into dense, process-aware value estimates.<n>It replaces standard group normalization with a novel process enhanced by absolute values to maintain a stable optimization signal.
  arXiv  Detail & Related papers  (2025-12-13T16:31:26Z)
• REvolution: An Evolutionary Framework for RTL Generation driven by Large Language Models [2.127921199213507]
  Large Language Models (LLMs) are used for Register-Transfer Level (RTL) code generation.<n>This paper introduces REvolution, a framework that combines Evolutionary Computation (EC) with LLMs for automatic RTL generation and optimization.
  arXiv  Detail & Related papers  (2025-10-24T12:50:35Z)
• Single-stream Policy Optimization [21.214853668053234]
  We introduce Single-stream Policy Optimization (SPO)<n>SPO replaces per-group baselines with a persistent, KL-adaptive value tracker and normalizes advantages globally across the batch.<n>Being group-free, SPO enables higher throughput and scales effectively in long-horizon or tool-integrated settings.
  arXiv  Detail & Related papers  (2025-09-16T16:39:11Z)
• LLM4CMO: Large Language Model-aided Algorithm Design for Constrained Multiobjective Optimization [54.35609820607923]
  Large language models (LLMs) offer new opportunities for assisting with algorithm design.<n>We propose LLM4CMO, a novel CMOEA based on a dual-population, two-stage framework.<n>LLMs can serve as efficient co-designers in the development of complex evolutionary optimization algorithms.
  arXiv  Detail & Related papers  (2025-08-16T02:00:57Z)
• Large language models as uncertainty-calibrated optimizers for experimental discovery [4.968931211284832]
  We show that training language models through the uncertainty-aware objectives of traditional optimization methods enables their use as reliable overconfidence guided by natural language interfaces.<n>Our method nearly doubles the discovery rate of high-yielding reaction conditions, from 24% to 43% in 50 experimental starting from 10 unsuccessful conditions.
  arXiv  Detail & Related papers  (2025-04-08T17:59:57Z)
• REBEL: Reinforcement Learning via Regressing Relative Rewards [59.68420022466047]
  We propose REBEL, a minimalist RL algorithm for the era of generative models.<n>In theory, we prove that fundamental RL algorithms like Natural Policy Gradient can be seen as variants of REBEL.<n>We find that REBEL provides a unified approach to language modeling and image generation with stronger or similar performance as PPO and DPO.
  arXiv  Detail & Related papers  (2024-04-25T17:20:45Z)
• BALPA: A Balanced Primal-Dual Algorithm for Nonsmooth Optimization with Application to Distributed Optimization [39.67743321086165]
  We propose a novel primal-dual proximal splitting algorithm (PD-PSA) for the composite optimization problem with equality constraints. In BALPA, the dual update is designed as a proximal point for a time-varying quadratic function, which balances the implementation of primal and dual update. We propose a version of BALPA (S-BALPA) and apply the developed BALPA to devise a new distributed optimization algorithm.
  arXiv  Detail & Related papers  (2022-12-06T09:18:31Z)

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.