TCSExam: Evaluating Frontier LLMs on the Full Range of TCS Research
cs.AI, cs.CL
Submitted: 2026-11-05
Updated: 2026-11-05
Code: https://github.com/harbor-framework/harbor
Project page: https://bertdobbelaere.github.io/sorting_networks.html
Terminology
Sources
- ProofNet: Autoformalizing and Formally Proving Undergraduate-Level Mathematics
- Decoupling via Affine Spectral-Independence: Beck-Fiala and Koml'os Bounds Beyond Banaszczyk
- Parallel Repetition for $3$-Player XOR Games
- MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering
- Seed-Prover: Deep and Broad Reasoning for Automated Theorem Proving
- TCS-BENCH: Benchmarking State-of-the-Art Generative AI Theoretical Computer Science Research Ability
- DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression
- Formal Conjectures: An Open and Evolving Benchmark for Verified Discovery in Mathematics
- FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AI
- Improved lower bounds on the maximum size of graphs with girth 5
- miniCTX: Neural Theorem Proving with (Long-)Contexts
- Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs
- Kimi K3: Open Frontier Intelligence
- Constructing error-correcting binary codes using transitive permutation groups
- CombiBench: Benchmarking LLM Capability for Combinatorial Mathematics
- FrontierCS: Evolving Challenges for Evolving Intelligence
- Unified Scaling of Polar Codes: Error Exponent, Scaling Exponent, Moderate Deviations, and Error Floors
- On the communication complexity of XOR functions
- The Alon-Jaeger-Tarsi conjecture via group ring identities
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents