arXiv subjects

Zifan Peng

Publications and source records attributed to Zifan Peng.

25 records · Page 2Linked to original sources

arXiv2025

Thought Manipulation: External Thought Can Be Efficient for Large Reasoning Models

Recent advancements in large reasoning models (LRMs) have demonstrated the effectiveness of scaling test-time computation to enhance reasoning capabilities on various tasks. However, LRMs often suffer from an ``overthinking'' problem, where the model generates excessively redundant reasoning steps with limited performance gains. In this work, we empirically reveal an important characteristic of LRM behaviors that placing external CoTs generated by smaller models between the thinking token (\texttt{ } and \texttt{ }) can effectively manipulate the model to generate fewer thoughts. Building on this finding, we propose a simple yet efficient pipeline, \Method, to enable LRMs to bypass unnecessary intermediate steps, thereby significantly reducing computational costs. We conduct extensive experiments to evaluate the utility and efficiency of \Method. For instance, when applied to QwQ-32B on the LiveBench/Code dataset, \Method keeps the original performance while reducing output token counts by approximately 30\%, with minimal overhead introduced by the CoT generator. Furthermore, we identify two suboptimal modes, blindly following flawed external thoughts and unnecessary rethinking, and show that simple mitigations, such as difficulty-aware fallbacks, can further improve performance. Overall, \Method offers a practical, general, and efficient way to optimize LRM inference, making powerful reasoning models more accessible and scalable for real-world applications.

cs.CL↗

arXiv2025

GasAgent: A Multi-Agent Framework for Automated Gas Optimization in Smart Contracts

Smart contracts are trustworthy, immutable, and automatically executed programs on the blockchain. Their execution requires the Gas mechanism to ensure efficiency and fairness. However, due to non-optimal coding practices, many contracts contain Gas waste patterns that need to be optimized. Existing solutions mostly rely on manual discovery, which is inefficient, costly to maintain, and difficult to scale. Recent research uses large language models (LLMs) to explore new Gas waste patterns. However, it struggles to remain compatible with existing patterns, often produces redundant patterns, and requires manual validation/rewriting. To address this gap, we present GasAgent, the first multi-agent system for smart contract Gas optimization that combines compatibility with existing patterns and automated discovery/validation of new patterns, enabling end-to-end optimization. GasAgent consists of four specialized agents, Seeker, Innovator, Executor, and Manager, that collaborate in a closed loop to identify, validate, and apply Gas-saving improvements. Experiments on 100 verified real-world contracts demonstrate that GasAgent successfully optimizes 82 contracts, achieving an average deployment Gas savings of 9.97%. In addition, our evaluation confirms its compatibility with existing tools and validates the effectiveness of each module through ablation studies. To assess broader usability, we further evaluate 500 contracts generated by five representative LLMs across 10 categories and find that GasAgent optimizes 79.8% of them, with deployment Gas savings ranging from 4.79% to 13.93%, showing its usability as the optimization layer for LLM-assisted smart contract development.

cs.AI↗

arXiv2025

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search

Recent advancements in Large Language Models (LLMs) have significantly enhanced the capabilities of AI-Powered Search Engines (AIPSEs), offering precise and efficient responses by integrating external databases with pre-existing knowledge. However, we observe that these AIPSEs raise risks such as quoting malicious content or citing malicious websites, leading to harmful or unverified information dissemination. In this study, we conduct the first safety risk quantification on seven production AIPSEs by systematically defining the threat model, risk type, and evaluating responses to various query types. With data collected from PhishTank, ThreatBook, and LevelBlue, our findings reveal that AIPSEs frequently generate harmful content that contains malicious URLs even with benign queries (e.g., with benign keywords). We also observe that directly querying a URL will increase the number of main risk-inclusive responses, while querying with natural language will slightly mitigate such risk. Compared to traditional search engines, AIPSEs outperform in both utility and safety. We further perform two case studies on online document spoofing and phishing to show the ease of deceiving AIPSEs in the real-world setting. To mitigate these risks, we develop an agent-based defense with a GPT-4.1-based content refinement tool and a URL detector. Our evaluation shows that our defense can effectively reduce the risk, with only a minor cost of reducing available information by approximately 10.7%. Our research highlights the urgent need for robust safety measures in AIPSEs.

cs.CR↗

arXiv2025

Cross-Chain Options: A Bridgeless, Universal, and Efficient Approach

Options are fundamental to blockchain-based financial services, offering essential tools for risk management and price speculation, which enhance liquidity, flexibility, and market efficiency in decentralized finance (DeFi). Despite the growing interest in options for blockchain-resident assets, such as cryptocurrencies, current option mechanisms face significant challenges, including a high reliance on trusted third parties, limited asset support, high trading delays, and the requirement for option holders to provide upfront collateral. In this paper, we present a protocol that addresses the aforementioned issues. Our protocol is the first to eliminate the need for holders to post collateral when establishing options in trustless service environments (i.e. without a cross-chain bridge), which is achieved by introducing a guarantee from the option writer. Its universality allows for cross-chain options involving nearly \textit{any} assets on \textit{any} two different blockchains, provided the chains' programming languages can enforce and execute the necessary contract logic. Another key innovation is reducing option position transfer latency, which uses Double-Authentication-Preventing Signatures (DAPS). Our evaluation demonstrates that the proposed scheme reduces option transfer latency to less than half of that in existing methods. Rigorous security analysis proves that our protocol achieves secure option trading, even when facing adversarial behaviors.

cs.CR↗

arXiv2025

Humanizing LLMs: A Survey of Psychological Measurements with Tools, Datasets, and Human-Agent Applications

As large language models (LLMs) are increasingly used in human-centered tasks, assessing their psychological traits is crucial for understanding their social impact and ensuring trustworthy AI alignment. While existing reviews have covered some aspects of related research, several important areas have not been systematically discussed, including detailed discussions of diverse psychological tests, LLM-specific psychological datasets, and the applications of LLMs with psychological traits. To address this gap, we systematically review six key dimensions of applying psychological theories to LLMs: (1) assessment tools; (2) LLM-specific datasets; (3) evaluation metrics (consistency and stability); (4) empirical findings; (5) personality simulation methods; and (6) LLM-based behavior simulation. Our analysis highlights both the strengths and limitations of current methods. While some LLMs exhibit reproducible personality patterns under specific prompting schemes, significant variability remains across tasks and settings. Recognizing methodological challenges such as mismatches between psychological tools and LLMs' capabilities, as well as inconsistencies in evaluation practices, this study aims to propose future directions for developing more interpretable, robust, and generalizable psychological assessment frameworks for LLMs.

cs.CY↗

arXiv2025

SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines

Large language models (LLMs) have demonstrated remarkable proficiency in mainstream academic disciplines such as mathematics, physics, and computer science. However, human knowledge encompasses over 200 specialized disciplines, far exceeding the scope of existing benchmarks. The capabilities of LLMs in many of these specialized fields-particularly in light industry, agriculture, and service-oriented disciplines-remain inadequately evaluated. To address this gap, we present SuperGPQA, a comprehensive benchmark that evaluates graduate-level knowledge and reasoning capabilities across 285 disciplines. Our benchmark employs a novel Human-LLM collaborative filtering mechanism to eliminate trivial or ambiguous questions through iterative refinement based on both LLM responses and expert feedback. Our experimental results reveal significant room for improvement in the performance of current state-of-the-art LLMs across diverse knowledge domains (e.g., the reasoning-focused model DeepSeek-R1 achieved the highest accuracy of 61.82% on SuperGPQA), highlighting the considerable gap between current model capabilities and artificial general intelligence. Additionally, we present comprehensive insights from our management of a large-scale annotation process, involving over 80 expert annotators and an interactive Human-LLM collaborative system, offering valuable methodological guidance for future research initiatives of comparable scope.

cs.CL↗

arXiv2024

FairRelay: Fair and Cost-Efficient Peer-to-Peer Content Delivery through Payment Channel Networks

Peer-to-Peer (P2P) content delivery, known for scalability and resilience, offers a decentralized alternative to traditional centralized Content Delivery Networks (CDNs). A significant challenge in P2P content delivery remains: the fair compensation of relayers for their bandwidth contributions. Existing solutions employ blockchains for payment settlements, however, they are not practical due to high on-chain costs and over-simplified network assumptions. In this paper, we introduce FairRelay, a fair and cost-efficient protocol that ensures all participants get fair payoff in complex content delivery network settings. We introduce a novel primitive, Enforceable Accumulative Hashed TimeLock Contract (Enforceable A-HTLC), designed to guarantee payment atomicity - ensuring all participants receive their payments upon successful content delivery. The fairness of FairRelay is proved using the Universal Composability (UC) framework. Our evaluation demonstrates that, in optimistic scenarios, FairRelay employs zero on-chain costs. In pessimistic scenarios, the on-chain dispute costs for relayers and customers are constant, irrespective of the network complexity. Specifically, empirical results indicate that the on-chain dispute costs for relayers and customers are 24,902 gas (equivalent to 0.01 USD on Optimism L2) and 290,797 gas (0.07 USD), respectively. In a 10-hop relay path, FairRelay introduces less than 1.5% additional overhead compared to pure data transmission, showcasing the efficiency of FairRelay.

cs.CR↗