Papers with MATH500
LiTS: A Modular Framework for LLM Tree Search (2026.acl-demo)
Copied to clipboard
| Challenge: | Existing tree search methods are task-specific and require substantial reimplementation effort when adapting to new domains. |
| Approach: | They propose a Python framework for LLM reasoning via tree search that decomposes tree search into three reusable components that plug into algorithms like MCTS and BFS. |
| Outcome: | The proposed framework decomposes tree search into three reusable components that plug into algorithms like MCTS and BFS. |
Towards Hierarchical Multi-Step Reward Models for Enhanced Reasoning in Large Language Models (2026.findings-acl)
Copied to clipboard
Teng Wang, Jiang Zhangyi, Zhenqi He, Hailei Gong, Shenyang Tong, Wenhan Yang, Zeyu Li, Yanan Zheng, Zifan He, Zewen Ye, Shengjie Ma, Jianping Zhang
| Challenge: | Existing Process Reward Models (PRMs) are vulnerable to reward hacking and require expensive, large-scale annotation of reasoning steps. |
| Approach: | They propose a reward model approach which evaluates both individual and consecutive reasoning steps from fine-grained and coarse-grounded level. |
| Outcome: | Empirical results show that the proposed model performs better than existing PRMs and is more robust than existing models. |
To Code or not to Code? Adaptive Tool Integration for Math Language Models via Expectation-Maximization (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing tools that integrate chain-of-thought reasoning and code execution lack metacognitive awareness to integrate tools. |
| Approach: | They propose a framework that synergizes structured exploration with off-policy RL optimization to create a cycle between metacognitive tool-use decisions and evolving capabilities. |
| Outcome: | The proposed framework improves over 11% on MATH500 and 9.4% on AIME without o1-like CoT. |
PILOT: Planning via Internalized Latent Optimization Trajectories for Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models lack the capacity to formulate global strategies due to latency and availability constraints. |
| Approach: | They propose a framework to internalize the strategic oversight of large models into intrinsic Latent Guidance by synthesizing a query-conditioned Latent Guide. |
| Outcome: | The proposed framework outperforms strong baselines on mathematical and coding benchmarks with negligible inference latency. |
Think Hard Only When Needed: A Hybrid Best-of-N and Beam Search for Efficient Test-Time Compute (2026.findings-eacl)
Copied to clipboard
| Challenge: | Large language models (LLMs) exhibit remarkable reasoning and planning capabilities, yet their substantial inference-time cost significantly impedes deployment in resourceconstrained applications. |
| Approach: | They propose a hybrid inference pipeline that combines beam search and Best-of-N . THROW generates shorter initial trajectories and evaluates them using PRMs . |
| Outcome: | THROW achieves 1.54 and 14.38 latency speedups and 35.7% and 80.4% token reductions on average compared to Best-of-N and beam search . |
Prompting Test-Time Scaling Is A Strong LLM Reasoning Data Augmentation (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models exhibit strong reasoning when guided by chain-of-thought exemplars . collecting large, high-quality reasoning datasets remains laborious and resource-intensive . |
| Approach: | They propose a prompt-space data augmentation framework for enhancing LLM reasoning . they use a pool of 90 randomly selected reasoning instances to elicit diverse reasoning trajectories . |
| Outcome: | The proposed framework improves accuracy over small-data benchmarks and generalization on out-of-domain reasoning evaluations. |
Structured Pruning for Diverse Best-of-N Reasoning Optimization (2025.findings-acl)
Copied to clipboard
| Challenge: | Extensive experiments on the MATH dataset demonstrate that our method significantly outperforms traditional best-of-N and random head selection strategies. |
| Approach: | They propose a contrastive learning framework that dynamically selects the optimal head and layer to prune during inference by aligning question embeddings with head embedds. |
| Outcome: | The proposed approach outperforms best-of-N and random head selection strategies on the MATH500 and GSM8K datasets. |
Diverse Multi-tool Aggregation with Large Language Models for Enhanced Math Reasoning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Multi-TAG uses multiple tools to solve complex math problems over multiple reasoning steps. |
| Approach: | They propose a tool-based LLM framework that leverages multiple tools to solve math problems. |
| Outcome: | The proposed framework outperforms baselines that use individual tools with the same number of runs and significantly outperformed standard baselines. |
The Impact of Language Mixing on Bilingual LLM Reasoning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies show multilingual speakers intentionally switch languages during reasoning . enforcing monolingual decoding reduces accuracy by 5.6 percentage points . |
| Approach: | They find that multilingual speakers intentionally switch languages during reasoning . enforcing monolingual decoding reduces accuracy by 5.6 percentage points . authors suggest that language mixing is not merely a byproduct of multilingual training . |
| Outcome: | The proposed model can be used to predict whether a language switch would benefit or harm reasoning. |
Activation Steering for Chain-of-Thought Compression (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models produce intermediate explanations, commonly referred to as chains of thought (CoTs), but the generated rationales are typically verbose, consuming many additional tokens, and thus degrading throughput and increasing inference energy consumption. |
| Approach: | They propose to generate concise reasoning traces by directly adjusting internal representations via activation steering. |
| Outcome: | The proposed method reduces generated token length by 69.4% across five reasoning benchmarks while maintaining accuracy. |
AlgBench: To What Extent Do Large Reasoning Models Understand Algorithms? (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing benchmarks for algorithmic reasoning fail to answer a critical question: do LRMs master algorithmic thinking? Empirical evaluations on leading LRM models reveal substantial performance heterogeneity, while models perform well on non-optimized tasks, accuracy drops sharply to around 49% on globally optimized algorithms. |
| Approach: | They propose an algorithm-centric benchmark that evaluates large reasoning models under an algorithmic paradigm. |
| Outcome: | Empirical evaluations on leading LRMs reveal substantial performance heterogeneity . models perform well on non-optimized tasks, accuracy drops sharply to around 49% . |
Thinking Economically: A Hierarchical Framework for Adaptive-Complexity Reasoning in LLMs (2026.findings-acl)
Copied to clipboard
Yubo Gao, Haotian Wu, Hong Chen, Junquan Huang, Yibo Yan, Jungang Li, Zihao Dongfang, Sicheng Tao, PS Tan, Jie Zhang, Xuming Hu
| Challenge: | Existing efficiency methods for Chain-of-Thought (CoT) generate excessively long rationales without commensurate accuracy gains. |
| Approach: | They propose a training framework that operationalizes this principle through coarse-to-fine budgeting. |
| Outcome: | Experiments on GSM8K and MATH500 show that HAB surpasses standard CoT in accuracy and reduces token usage, achieving stronger performance-efficiency trade-off than baselines. |