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. |
Similar Papers
Improving Large Language Models Function Calling and Interpretability via Guided-Structured Templates (2025.emnlp-main)
Copied to clipboard
Hy Dang, Tianyi Liu, Zhuofeng Wu, Jingfeng Yang, Haoming Jiang, Tao Yang, Pei Chen, Zhengyang Wang, Helen Wang, Huasheng Li, Bing Yin, Meng Jiang
| Challenge: | Large language models (LLMs) have strong reasoning and tool-use capabilities, yet fail in real-world tool-interactions due to incorrect parameterization, poor tool selection, or misinterpretation of user intent. |
| Approach: | They propose a curriculum-inspired framework that leverages structured reasoning templates to guide LLMs through more deliberate step-by-step instructions for generating function calls. |
| Outcome: | The proposed framework reduces tool-use errors and improves interpretability and transparency of tool-using agents. |
EvoCoT: Overcoming the Exploration Bottleneck in Reinforcement Learning for LLMs (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to reinforcement learning with verifiable reward (RLVR) are limited by difficulty or lack of exploration. |
| Approach: | They propose a self-evolving curriculum learning framework based on chain-of-thought reasoning optimization that constrains exploration space by self-generating and verifying CoT trajectories. |
| Outcome: | The proposed framework enables LLMs to solve previously unsolved problems without external supervision and is compatible with various RL fine-tuning methods. |
A Joint Optimization Framework for Enhancing Efficiency of Tool Utilization in LLM Agents (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing efforts for tool utilization involve an LLM agent that contains instructions on using the description of the available tools to determine and call the tools required to solve the problem. |
| Approach: | They propose to optimize the context of LLM agents by combining the instructions provided in agent prompts and tool descriptions to enhance their interaction. |
| Outcome: | The proposed framework improves both the instructions provided in agent prompt and tool description, enhancing their interaction. |
Towards Autonomous Tool Utilization in Language Models: A Unified, Efficient and Scalable Framework (2024.lrec-main)
Copied to clipboard
| Challenge: | Recent advances in tool learning for large language models have led to a new trend to allow LLMs to leverage external tools. |
| Approach: | They propose a framework for fine-tuning language models that categorizes queries into three different types . they also introduce an "instruct, execute, and reformat" strategy specifically designed for efficient data annotation . |
| Outcome: | The proposed framework surpasses open-source language models and GPT-3.5/4 on multiple evaluation metrics. |
AdaptFlow: Adaptive Workflow Optimization via Meta-Learning (2025.findings-emnlp)
Copied to clipboard
Runchuan Zhu, Bowen Jiang, Lingrui Mei, Fangkai Yang, Lu Wang, Haoxiang Gao, Fengshuo Bai, Pu Zhao, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang
| Challenge: | Existing approaches to large language models rely on static templates or manual workflows. |
| Approach: | AdaptFlow is a language-based meta-learning framework inspired by model-agnostic meta- learning. |
| Outcome: | AdaptFlow outperforms manual and automated workflows on question answering, code generation and mathematical reasoning benchmarks. |
SAAS: Solving Ability Amplification Strategy for Enhanced Mathematical Reasoning in Large Language Models (2024.emnlp-industry)
Copied to clipboard
| Challenge: | Existing approaches to enhance mathematical reasoning and problem-solving abilities of Large Language Models (LLMs) despite their remarkable performance across domains, a notable challenge persists in the realm of mathematical reasoning. |
| Approach: | They propose a sequential learning approach that integrates the Chain-of-Thought and the Program-ofThough. |
| Outcome: | The proposed approach achieves state-of-the-art (SOTA) performance by integrating CoT and PoT learning. |
EMTIR-GRPO: Efficient Multi-Tool Augmented Large Language Models via Reinforcement Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Tool-integrated reasoning (TIR) enables large language models to invoke external tools for tasks beyond their internal capacity but often suffers from tool overuse. |
| Approach: | They propose an algorithm that uses a composite reward to model tool costs and tool efficiency. |
| Outcome: | The proposed algorithm models heterogeneous tool costs and encourages more cost-effective tool-use strategies. |
Think Faster Than Words: Efficient LLM Chain-of-Thought Reasoning via Dynamic Shortcut Decoding (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods that prune or employ early stopping to reduce latency often compromise reasoning reliability. |
| Approach: | They propose a shortcut decoding framework that integrates probes over internal hidden states with step-level entropy to detect convergence of reasoning during generation and adaptively selects between a fast-exit path and a stability-verified path to remove redundant steps while preserving answer correctness. |
| Outcome: | The proposed framework reduces token usage by approximately 35% and maintains accuracy comparable to full CoT decoding. |
How Do Humans Write Code? Large Models Do It the Same Way Too (2024.emnlp-main)
Copied to clipboard
| Challenge: | Program-of-Thought (PoT) replaces natural language-based Chain-ofThough (CoT) but introduces more reasoning errors, such as incorrect formulas or flawed logic, compared to CoT. |
| Approach: | They propose a method that integrates CoT and Program-of-Thought to achieve more accurate reasoning and reinforcement learning. |
| Outcome: | The proposed method achieves an average improvement of 6.5% on the Llama-Base model and 4.3% on the Mistral-Bass model across 8 mathematical calculation datasets. |
Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs (2025.emnlp-main)
Copied to clipboard
Dayu Yang, Tianyang Liu, Daoan Zhang, Antoine Simoulin, Xiaoyi Liu, Yuwei Cao, Zhaopu Teng, Xin Qian, Grey Yang, Jiebo Luo, Julian McAuley
| Challenge: | Recent breakthrough models like OpenAI-o1 and DeepSeek-R1 show powerful task-solving capabilities, particularly advances in reasoning. |
| Approach: | They propose future research directions that may deepen the synergy, ultimately advancing LLM performance in both complex reasoning and code intelligence. |
| Outcome: | The proposed research may deepen the synergy, ultimately advancing LLM performance in both complex reasoning and code intelligence. |