VeriChat: An Agentic Conversational AI Assistant for Hardware Security Verification

A Survey of Fuzzing Techniques for Large Language Model Agents: Challenges, Methods, and Future Directions

With the rapid development of large language models (LLMs), LLM-based agents are evolving from single-turn text generators into autonomous decision-making systems capable of task planning, tool invocation, memory retrieval, and environmental interaction. However, the openness of agent environments and the nondeterminism of model-driven decision logic introduce security and reliability risks that are difficult to capture with conventional software testing. Fuzzing, as an automated and scalable vulnerability discovery technique, provides a promising approach for assessing the robustness of LLM agent systems. This paper presents a systematic survey of fuzzing techniques for LLM agents. First, we analyze the distinctive architecture of LLM agents and summarize three representative threat categories: indirect prompt injection, planning hallucination, and tool abuse. Second, we review existing fuzzing methods from three perspectives: test-case generation and mutation, environment simulation and interaction monitoring, and test-oracle construction. Particular attention is paid to LLM-enhanced fuzzers that exploit the semantic understanding and generation capabilities of LLMs to improve mutation quality and attack effectiveness. Finally, we connect the main technical challenges with an actionable research roadmap, including semantic coverage, cost-aware execution, reproducible oracles, multi-agent fuzzing, gray-box guidance, and automated repair.

AMTFV: Agentic Mathematical Tool-Flow Verification for LLM Self-Correction

Large language models have demonstrated strong mathematical problem-solving capabilities, yet reliably verifying their candidate answers remains challenging. Existing representative methods mainly revise outputs through natural-language reflection or assist verification by directly generating verification programs; the former may not reliably support exact computation, whereas the latter prematurely couples mathematical modeling with low-level implementation. We propose AMTFV (Agentic Mathematical Tool-Flow Verification). By introducing Mathematical Tool Flow (MTF) as an interrupt--execute--resume interface, AMTFV decouples verification modeling from concrete execution and supports exact computation through a mathematical toolbox. Specifically, the verification agent first constructs a verification workflow, encodes the mathematical objects and computational intent requiring reliable execution in an MTF request, and sends it to the mathematical toolbox agent. The latter parses the request, generates executable calls, and dispatches them to the backend for exact computation. Tool outputs then support candidate-answer adjudication, answer revision, and verification-workflow revision. We evaluate AMTFV on five challenging mathematical reasoning datasets with seven model configurations from DeepSeek, GPT, and Gemini. Experimental results show that AMTFV outperforms the representative baselines evaluated in this study overall; under an individual model configuration, it improves average accuracy over the strongest baseline by up to 8.3 percentage points, with larger gains on samples of medium and high verification complexity.

NiyamAI - An Intent-Bound AI Agent with Cryptographically Verifiable Guardrails using Zero-Knowledge Proofs

MACGen: Toward Functionally Correct and Secure Code Generation via Multi-Agent Collaboration

Despite their strong ability to generate code, large language models often fail to produce secure code, as their outputs frequently contain security vulnerabilities. Secure code generation is inherently challenging because it requires solving a multi-objective problem: functional correctness and security. Existing approaches address this challenge by injecting external security knowledge or by using agentic feedback and iterative refinement. However, guideline retrieval often leaves the generator to translate generic advice into task-specific secure implementations, while shared-dialogue multi-agent feedback can blur role boundaries and suffer from context bloat. We present MACGen, a multi-agent framework that integrates planning, security analysis, code synthesis and refinement to jointly optimize security and functionality. A planner constructs a step-by-step plan to satisfy functional requirements. A security advisor identifies likely CWEs and synthesizes task-specific guidelines, a coder then generates code grounded in these artifacts, and a reviewer issues perspective-separated feedback. Rather than sharing full dialogue histories, each agent receives only structured artifacts from upstream stages, enforcing role specialization and reducing uncontrolled context growth. On CWEval and BaxBench, MACGen improves F&S@1 over direct prompting by 19.61 and 10.57 percentage points (pp) on average, respectively.

Bridging the Trust Gap: A Hybrid Intuitive-Rational Architecture for Certified University Assistants

Large Language Models (LLMs) have improved conversational access to university services, but their answers remain difficult to verify in regulation-sensitive domains. This paper presents a proof-of-concept neuro-symbolic architecture for “certified” academic advising. The system combines ParsyBot as a conversational interface with a Prologbased reasoning layer constructed from selected clauses of the Başkent University Undergraduate Education and Exam Regulation. In the proposed architecture, the LLM does not make normative decisions. It assists the drafting of symbolic rules, maps a small set of controlled natural-language intents into Prolog queries and verbalizes the symbolic output. The compliance decision itself is produced by the Prolog engine. We demonstrate the approach on representative clauses concerning attendance-based F2 failure, resit ineligibility, GGA-based enrollment restriction, course repetition, and a lightweight planning scenario. The results show how an LLM-based university assistant can be connected to an auditable and reproducible symbolic layer, while preserving a clear separation between linguistic interaction and formal regulatory reasoning.

Reverse Engineering of Chatbot Behaviour for Automated Testing

A reverse engineering technique is presented for extracting a behavioural model of a deployed chatbot through the automated exploration of its functionality via Large Language Models through the automated exploration of its functionality via Large Language Models.