TCSExam 基准测试：评估前沿 LLM 在理论计算机科学研究中的能力
TCSExam: Evaluating Frontier LLMs on the Full Range of TCS Research
理论计算机科学版的 LLM 考试来了：GPT-6 Astra 和 Opus 5.5 分别拿下两个版本第一，还真能推进一些开放猜想的特殊情形，做研究的人可以看看这套用 Lean 验证的评测框架。
TCSExam 是一个覆盖理论计算机科学（TCS）全领域研究的统一评测框架，考察定理证明、求解器工程、构造方法以及求解开放猜想的能力。TCSExam-Full 包含 100 个专家审核的任务，提交结果由 Lean 内核或可执行任务检查器验证；TCSExam-Lite 从中选出 20 个任务，在相同单次尝试预算下减少 80% 的任务尝试量。评测结果显示，GPT-6 Astra 在 Full 版以 71.9 的 TCSExam Index 排名第一，Opus 5.5 在 Lite 版以 72.3 领先，两个版本的排名在八个共同评测的智能体上高度一致（Spearman ρ=0.93）。评测还产出了改进的求解器输出和数学构造，并获得了开放猜想尝试中经独立验证的特殊情形与界。
TCSExam: Evaluating Frontier LLMs on the Full Range of TCS Research
Can large language models (LLMs) advance theoretical computer science and resolve its long-standing open conjectures? To study progress toward this goal, we introduce TCSExam, a unified framework and benchmark covering the full range of TCS research. It evaluates theorem proving, solver engineering, and constructions alongside direct attempts to resolve open conjectures, capturing both concrete research accomplishments and progress toward long-standing research goals. TCSExam-Full contains 100 expert-reviewed tasks, with submissions checked by the Lean kernel or an executable task checker. TCSExam-Lite selects 20 tasks, five per track, reducing the number of task attempts by 80% at the same per-attempt budget. We evaluate eight agents on Full and nine on Lite. The TCSExam Index combines all four tracks: GPT-6 Astra leads Full (71.9), and Opus 5.5 leads Lite (72.3). Full and Lite rankings are strongly aligned across eight shared agents (Spearman's $ρ=0.93$), supporting Lite as a compact, discriminative benchmark. The evaluations yield improved solver outputs and mathematical constructions, together with independently verified special cases and bounds from open-conjecture attempts. TCSExam provides an extensible framework with task sources, Docker build recipes, and evaluation tools for reproducible use.