| Guided by Gut: Efficient Test-Time Scaling with Reinforced Intrinsic Confidence | May 23, 2025 | GPULarge Language Model | —Unverified | 0 |
| The Unreasonable Effectiveness of Model Merging for Cross-Lingual Transfer in LLMs | May 23, 2025 | Cross-Lingual TransferMath | —Unverified | 0 |
| RaDeR: Reasoning-aware Dense Retrieval Models | May 23, 2025 | MathMathematical Problem-Solving | CodeCode Available | 1 |
| Amplify Adjacent Token Differences: Enhancing Long Chain-of-Thought Reasoning with Shift-FFN | May 22, 2025 | Mathematical Reasoning | —Unverified | 0 |
| Tropical Attention: Neural Algorithmic Reasoning for Combinatorial Algorithms | May 22, 2025 | Adversarial AttackBenchmarking | —Unverified | 0 |
| Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains | May 22, 2025 | Mathematical ReasoningReinforcement Learning (RL) | —Unverified | 0 |
| EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning | May 22, 2025 | GSM8KMath | CodeCode Available | 0 |
| MCP-RADAR: A Multi-Dimensional Benchmark for Evaluating Tool Use Capabilities in Large Language Models | May 22, 2025 | Mathematical Reasoning | —Unverified | 0 |
| Dynamic Sampling that Adapts: Iterative DPO for Self-Aware Mathematical Reasoning | May 22, 2025 | Mathematical ReasoningReinforcement Learning (RL) | —Unverified | 0 |
| SMART: Self-Generating and Self-Validating Multi-Dimensional Assessment for LLMs' Mathematical Problem Solving | May 22, 2025 | DiagnosticMathematical Problem-Solving | —Unverified | 0 |
| KTAE: A Model-Free Algorithm to Key-Tokens Advantage Estimation in Mathematical Reasoning | May 22, 2025 | Mathematical Reasoningreinforcement-learning | CodeCode Available | 1 |
| HOFT: Householder Orthogonal Fine-tuning | May 22, 2025 | Machine TranslationMathematical Reasoning | —Unverified | 0 |
| Bottlenecked Transformers: Periodic KV Cache Abstraction for Generalised Reasoning | May 22, 2025 | Mathematical Reasoning | —Unverified | 0 |
| MAPS: A Multilingual Benchmark for Global Agent Performance and Security | May 21, 2025 | Code GenerationMath | —Unverified | 0 |
| Towards Spoken Mathematical Reasoning: Benchmarking Speech-based Models over Multi-faceted Math Problems | May 21, 2025 | BenchmarkingMath | —Unverified | 0 |
| SSR: Speculative Parallel Scaling Reasoning in Test-time | May 21, 2025 | DiversityMath | —Unverified | 0 |
| Learning to Rank Chain-of-Thought: An Energy-Based Approach with Outcome Supervision | May 21, 2025 | GSM8KLearning-To-Rank | —Unverified | 0 |
| Can LLMs understand Math? -- Exploring the Pitfalls in Mathematical Reasoning | May 21, 2025 | MathMathematical Reasoning | —Unverified | 0 |
| Trajectory Bellman Residual Minimization: A Simple Value-Based Method for LLM Reasoning | May 21, 2025 | Language ModelingLanguage Modelling | —Unverified | 0 |
| RL Tango: Reinforcing Generator and Verifier Together for Language Reasoning | May 21, 2025 | MathMathematical Reasoning | CodeCode Available | 2 |
| MM-Agent: LLM as Agents for Real-world Mathematical Modeling Problem | May 20, 2025 | Mathematical Reasoningscientific discovery | CodeCode Available | 3 |
| Beyond the First Error: Process Reward Models for Reflective Mathematical Reasoning | May 20, 2025 | Mathematical Reasoning | —Unverified | 0 |
| SCOPE: Compress Mathematical Reasoning Steps for Efficient Automated Process Annotation | May 20, 2025 | Mathematical Reasoning | CodeCode Available | 0 |
| Text Generation Beyond Discrete Token Sampling | May 20, 2025 | Code GenerationMathematical Reasoning | —Unverified | 0 |
| Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models | May 20, 2025 | Instruction FollowingMathematical Reasoning | CodeCode Available | 1 |
