Multi-Agent Learning with Cooperation-Driven Optimization Dynamics
本文提出一种多智能体合作机制，通过信息交换减少模型复杂度并保持性能，使用投票、多数和加权平均等策略实现合作，减少了训练参数数量。
0 citationsRead paper
Selected work
Representative Papers
Sociotechnical Aspects of Tor Relay Rejection
研究探讨了Tor项目版本过期政策对网络维护及用户匿名性的影响，通过用户调研和网络模拟方法分析其社会技术层面的后果。
0 citationsRead paper
Detecting HTTP Status Code Misuses in REST APIs via Static and Dynamic Analysis
本文通过静态和动态分析方法检测REST API中HTTP状态码的误用问题，基于2625个实际API规范制定了30条使用规则，并实现工具来识别违规情况。
0 citationsRead paper
Jokes Aside: Measuring the Semantic Distance of Double Meanings
研究使用词嵌入方法改进了幽默评分预测模型，引入对称性指标衡量双关语语义距离，但模型在预测幽默评分上表现不佳。
0 citationsRead paper
Case study: proving sqrt(2) irrational with LPTP and an LLM
This work formalizes a proof of the irrationality of √2 within a logic programming framework and investigates the feasibility of leveraging large language models (LLMs) to assist in constructing machine-verifiable mathematical proofs. By integrating the LPTP logic program theorem prover with an LLM, the study develops a complete formal proof from basic predicates in a natural-deduction style. It presents the first successful collaboration between an LLM and LPTP to generate a human-readable yet fully machine-verifiable proof of the irrationality of √2, which has been rigorously validated by LPTP. The results demonstrate the effectiveness of human–AI cooperation in formal mathematics and offer a novel pathway toward AI-assisted theorem proving.
0 citationsRead paper
Recent publications
Latest Papers
Multi-Agent Learning with Cooperation-Driven Optimization Dynamics
本文提出一种多智能体合作机制，通过信息交换减少模型复杂度并保持性能，使用投票、多数和加权平均等策略实现合作，减少了训练参数数量。
0 citationsRead paper
Sociotechnical Aspects of Tor Relay Rejection
研究探讨了Tor项目版本过期政策对网络维护及用户匿名性的影响，通过用户调研和网络模拟方法分析其社会技术层面的后果。
0 citationsRead paper
Detecting HTTP Status Code Misuses in REST APIs via Static and Dynamic Analysis
本文通过静态和动态分析方法检测REST API中HTTP状态码的误用问题，基于2625个实际API规范制定了30条使用规则，并实现工具来识别违规情况。
0 citationsRead paper
Jokes Aside: Measuring the Semantic Distance of Double Meanings
研究使用词嵌入方法改进了幽默评分预测模型，引入对称性指标衡量双关语语义距离，但模型在预测幽默评分上表现不佳。
0 citationsRead paper
Case study: proving sqrt(2) irrational with LPTP and an LLM
This work formalizes a proof of the irrationality of √2 within a logic programming framework and investigates the feasibility of leveraging large language models (LLMs) to assist in constructing machine-verifiable mathematical proofs. By integrating the LPTP logic program theorem prover with an LLM, the study develops a complete formal proof from basic predicates in a natural-deduction style. It presents the first successful collaboration between an LLM and LPTP to generate a human-readable yet fully machine-verifiable proof of the irrationality of √2, which has been rigorously validated by LPTP. The results demonstrate the effectiveness of human–AI cooperation in formal mathematics and offer a novel pathway toward AI-assisted theorem proving.
0 citationsRead paper