| Boosting Large Language Models with Socratic Method for Conversational Mathematics Teaching | Jul 24, 2024 | Math | CodeCode Available | 1 |
| MathViz-E: A Case-study in Domain-Specialized Tool-Using Agents | Jul 24, 2024 | Math | CodeCode Available | 1 |
| LEAN-GitHub: Compiling GitHub LEAN repositories for a versatile LEAN prover | Jul 24, 2024 | Automated Theorem ProvingMath | CodeCode Available | 4 |
| Nerva: a Truly Sparse Implementation of Neural Networks | Jul 24, 2024 | Math | CodeCode Available | 1 |
| TaskGen: A Task-Based, Memory-Infused Agentic Framework using StrictJSON | Jul 22, 2024 | Language ModelingLanguage Modelling | CodeCode Available | 3 |
| Toward Adaptive Reasoning in Large Language Models with Thought Rollback | Jul 21, 2024 | Arithmetic ReasoningMath | CodeCode Available | 1 |
| Generalization v.s. Memorization: Tracing Language Models' Capabilities Back to Pretraining Data | Jul 20, 2024 | Language ModellingMachine Translation | —Unverified | 0 |
| Learning Goal-Conditioned Representations for Language Reward Models | Jul 18, 2024 | GSM8KMath | CodeCode Available | 1 |
| Weak-to-Strong Reasoning | Jul 18, 2024 | GSM8KMath | CodeCode Available | 2 |
| Prover-Verifier Games improve legibility of LLM outputs | Jul 18, 2024 | Math | CodeCode Available | 0 |
