Adaptive Coverage Reward Mechanism

Concept

Adaptive Coverage Reward Mechanism (ACRM) is the module-aware extrinsic reward component of HiFuzz, a hierarchical reinforcement-learning framework for CPU fuzzing. It treats module focus as a multi-armed bandit problem and uses a UCB-style dynamic weighting scheme to shift reward toward under-covered hardware modules.

First seen 7/10/2026

Last seen 7/10/2026

Evidence 6 chunks

Wiki v1

WIKI

Overview

The Adaptive Coverage Reward Mechanism (ACRM) is a reward-shaping mechanism used in HiFuzz for hardware fuzzing. HiFuzz combines a macro-level Program Agent and a micro-level Basic Block Agent; ACRM provides balanced module-level coverage feedback as part of that framework. Its purpose is to reduce the weakness of optimizing a single global coverage score, where easy-to-cover modules can dominate the reward and hide under-covered components.

Mechanism

READ FULL ARTICLE →

NEIGHBORHOOD

No graph connections found for this entity yet. It may appear in future ingestion runs.

explore full graph →

RELATIONSHIPS

5 connections

HiFuzz ← uses 100% 2e

HiFuzz uses an Adaptive Coverage Reward Mechanism to balance module-level exploration.

Upper Confidence Bound uses → 100% 2e

The Adaptive Coverage Reward Mechanism uses UCB for dynamic module weighting.

HiFuzz part of → 100% 2e

The ACRM is a feedback component of HiFuzz for balanced module-level coverage.

Multi-Armed Bandit uses → 100% 1e

The module selection in ACRM is formulated as a Multi-Armed Bandit problem.

Module-Level Coverage Weighting ← part of 90% 1e

Module-level coverage weighting is the core mechanism of the ACRM.

LINKED ENTITIES

4 links

Multi-Armed Bandit USES Extracted graph relationship

HiFuzz PART_OF Extracted graph relationship

Module-Level Coverage Weighting PART_OF Extracted graph relationship

Upper Confidence Bound USES Extracted graph relationship

CITATIONS

9 sources

9 citations — click to expand

[1] ACRM is used in HiFuzz to provide balanced module-level coverage feedback. HiFuzz: Hierarchical Reinforcement Learning for Semantic-Aware and Adaptive CPU Fuzzing

[2] ACRM formulates module selection as a Multi-Armed Bandit problem and uses a UCB-based dynamic weighting approach. HiFuzz: Hierarchical Reinforcement Learning for Semantic-Aware and Adaptive CPU Fuzzing

[3] ACRM computes module weights from historical mean coverage gain, module saturation, a dynamic beta parameter, and softmax temperature. HiFuzz: Hierarchical Reinforcement Learning for Semantic-Aware and Adaptive CPU Fuzzing

[4] The ACRM extrinsic reward is the weighted sum of coverage gains across modules and is passed to the Program Agent. HiFuzz: Hierarchical Reinforcement Learning for Semantic-Aware and Adaptive CPU Fuzzing

[5] The UCB term shifts attention from saturated modules toward under-covered modules and reduces masking from aggregate coverage. HiFuzz: Hierarchical Reinforcement Learning for Semantic-Aware and Adaptive CPU Fuzzing

[6] In the Rocket ablation, ACRM contributes +44.15% over the DQN+PPO baseline, while the full HiFuzz system reaches +51.87%. HiFuzz: Hierarchical Reinforcement Learning for Semantic-Aware and Adaptive CPU Fuzzing

[7] The DQN+PPO ablation baseline preserves the hierarchical Program Agent / Basic Block Agent split while removing semantic intrinsic feedback and adaptive module weighting. HiFuzz: Hierarchical Reinforcement Learning for Semantic-Aware and Adaptive CPU Fuzzing

[8] HiFuzz is implemented in Python on Cocotb, Verilator, and Spike, with a Rainbow DQN Program Agent and PPO Basic Block Agent, and is evaluated on Rocket, BOOM, and CVA6. HiFuzz: Hierarchical Reinforcement Learning for Semantic-Aware and Adaptive CPU Fuzzing

[9] The paper notes that its 24-hour multi-fuzzer coverage curves were not averaged over many random seeds and identifies broader multi-seed reporting as useful future work. HiFuzz: Hierarchical Reinforcement Learning for Semantic-Aware and Adaptive CPU Fuzzing