STRUCTURED REASONING

ROGRAG: A Robustly Optimized GraphRAG Framework (2025.acl-demo)

Challenge:	Large language models (LLMs) exhibit strong reasoning capabilities but typically require expensive post-training to reach high performance.
Approach:	They propose to use token-level Adaptive Routing to steer frozen LLMs toward structured reasoning entirely at inference time.
Outcome:	Extensive experiments show that TARo significantly improves reasoning performance by up to +22.4% over base model and +8.4% .

Copied to clipboard

Zhefan Wang, Huanjun Kong, Jie Ying, Wanli Ouyang, Nanqing Dong

Step-by-Step Fact Verification System for Medical Claims with Explainable Reasoning (2025.naacl-short)

Challenge:	Existing pipelines for large language models struggle with specialized or emerging topics which are rarely seen in the training corpus.
Approach:	They propose a multi-stage retrieval mechanism that integrates dual-level with logic form retrieval methods to improve retrieval robustness without increasing computational cost.
Outcome:	The proposed framework outperforms Qwen2.5-7B-Instruct and outperformed mainstream methods on seedbench and significantly improves the performance of each component.

Copied to clipboard

Juraj Vladika, Ivana Hacajova, Florian Matthes

MIRA: Empowering One-Touch AI Services on Smartphones with MLLM-based Instruction Recommendation (2025.acl-industry)

Challenge:	Fact verification (FV) aims to assess the veracity of a claim based on relevant evidence.
Approach:	They propose to use iterative fact verification to assess the veracity of a claim based on relevant evidence.
Outcome:	The proposed system improves on three medical fact-checking datasets and evaluates with multiple settings including different LLMs, external web search, and structured reasoning using logic predicates.

Copied to clipboard

Zhipeng Bian, Jieming Zhu, Xuyang Xie, Quanyu Dai, Zhou Zhao, Zhenhua Dong

Abstraction-of-Thought Makes Language Models Better Reasoners (2024.findings-emnlp)

Challenge:	generative AI is revolutionizing how users interact with smartphones, transforming how they interact with them.
Approach:	They propose a framework for task instruction recommendation that enables intuitive one-touch AI tasking on smartphones.
Outcome:	The proposed framework shows significant improvements in recommendation accuracy and coherence and intent alignment with predefined instruction candidates.

Copied to clipboard

Ruixin Hong, Hongming Zhang, Xiaoman Pan, Dong Yu, Changshui Zhang

SymBa: Symbolic Backward Chaining for Structured Natural Language Reasoning (2025.naacl-long)

Challenge:	Abstract reasoning is a key to generalization in human reasoning, but eliciting language models to perform reasoning with abstraction remains unexplored.
Approach:	They propose a new structured reasoning format called Abstraction-of-Thought (AoT) this approach elicits language models to first contemplate on the abstract level before incorporating concrete details .
Outcome:	The proposed model outperforms the prevailing Chain-of-Thought (CoT) reasoning on 23 unseen tasks.

Copied to clipboard

Jinu Lee, Wonseok Hwang

SIRAJ: Diverse and Efficient Red-Teaming for LLM Agents via Distilled Structured Reasoning (2026.findings-eacl)

Challenge:	Among different methods for structured reasoning, we focus on backward chaining, where the goal is recursively decomposed into subgoals by searching and applying rules.
Approach:	They propose a backward chaining system that integrates a symbolic solver and an LLM to improve the performance of LLM-based reasoning.
Outcome:	The proposed system improves deductive, relational, and arithmetic reasoning benchmarks compared to baselines.

Copied to clipboard

Kaiwen Zhou, Ahmed Elgohary, A S M Iftekhar, Amin Saied

From Implicit Exploration to Structured Reasoning: Guideline and Refinement for LLMs (2025.findings-emnlp)

Challenge:	Existing red-teaming frameworks do not cover all the risks associated with arbitrary black-box LLMs.
Approach:	They propose a generic red-teaming framework for arbitrary black-box LLM agents that iteratively constructs and refines model-based adversarial attacks based on the execution trajectories of former attempts.
Outcome:	The proposed model improves attack success rate by 100%, surpassing the 671B Deepseek-R1 model.

Copied to clipboard

Jiaxiang Chen, Zhuo Wang, Mingxi Zou, Zhucong Li, Zhijian Zhou, Song Wang, Zenglin Xu

Unlocking Smarter Device Control: Foresighted Planning with a World Model-Driven Code Execution Approach (2025.findings-emnlp)

Challenge:	Existing models rely on implicit exploration, which leads to unstable reasoning paths and lack of error correction.
Approach:	They propose a framework that shifts from implicit exploration to structured reasoning through guideline and refinement.
Outcome:	The proposed model outperforms strong baselines on the Big-Bench Hard benchmark.

Copied to clipboard

Xiaoran Yin, Xu Luo, Hao Wu, Lianli Gao, Jingkuan Song

Challenge:	Current approaches to automating complex tasks focus on reactive policies and focus on visual observations.
Approach:	They propose a framework that prioritizes natural language understanding and structured reasoning to enhance the agent’s global understanding of the environment by developing a task-oriented, refinable world model at the outset of the task.
Outcome:	The proposed framework outperforms existing approaches in simulated environments and on real mobile devices.

ReasoningLM: Enabling Structural Subgraph Reasoning in Pre-trained Language Models for Question Answering over Knowledge Graph (2023.emnlp-main)

Copied to clipboard

Jinhao Jiang, Kun Zhou, Xin Zhao, Yaliang Li, Ji-Rong Wen

Semantic Text Processing

Challenge:	Question Answering over Knowledge Graph (KGQA) aims to find answer entities for natural language questions based on knowledge graphs.
Approach:	They propose a subgraph-aware self-attention mechanism to imitate the graph neural network (GNN) based module to perform multi-hop reasoning on KG.
Outcome:	The proposed method surpasses state-of-the-art models by a large margin even with fewer updated parameters and less training data.

From "Aha Moments" to Controllable Thinking: Toward Meta-Cognitive Reasoning in LRMs via Decoupled Reasoning and Control (2026.acl-long)

Copied to clipboard

Rui Ha, Rui Pu, Chaozhuo Li, Li Sun, Sen Su

SEER: Facilitating Structured Reasoning and Explanation via Reinforcement Learning (2024.acl-long)

Challenge:	Large Reasoning Models exhibit step-by-step reasoning, reflection, and backtracking, but these behaviors are often unregulated, leading to overthinking.
Approach:	They propose a meta-cognitive reasoning framework that decouples reasoning from control to enable independent optimization of control strategies.
Outcome:	Experiments show that the proposed model improves efficiency and accuracy across reasoning benchmarks.

Copied to clipboard

Guoxin Chen, Kexin Tang, Chao Yang, Fuying Ye, Yu Qiao, Yiming Qian

GAMBIT: A Gamified Jailbreak Framework for Multimodal Large Language Models (2026.acl-long)

Challenge:	Existing methods focus on single-step reasoning, ignoring logical dependencies between steps.
Approach:	They propose a method that maximizes a structure-based return to facilitate structured reasoning and explanation.
Outcome:	The proposed method outperforms state-of-the-art methods on EntailmentBank and STREET benchmarks.

Copied to clipboard

Xiangdong Hu, Yangyang Jiang, Qin Hu, Xiaojun Jia

Enough Coin Flips Can Make LLMs Act Bayesian (2025.acl-long)

Challenge:	Existing attacks focus on increasing the complexity of the modified visual task and do not explicitly leverage the model’s own reasoning incentives.
Approach:	They propose a framework that decomposes and reassembles harmful visual semantics and constructs a gamified scene that drives the model to explore, reconstruct intent and answer as part of winning the game.
Outcome:	Experiments on reasoning and non-reasoning MLLMs show that the proposed framework outperforms baseline models on both vision and text.

Copied to clipboard

Ritwik Gupta, Rodolfo Corona, Jiaxin Ge, Eric Wang, Dan Klein, Trevor Darrell, David M. Chan

RLET: A Reinforcement Learning Based Approach for Explainable QA with Entailment Trees (2022.emnlp-main)

Challenge:	Large language models exhibit the ability to generalize given few-shot examples in their input prompt, an emergent capability known as in-context learning.
Approach:	They investigate whether large language models use in-context learning to generalize given few-shot examples in their input prompt.
Outcome:	The proposed model can generalize given few-shot examples in their input prompt, an emergent capability known as in-context learning.

Copied to clipboard

Tengxiao Liu, Qipeng Guo, Xiangkun Hu, Yue Zhang, Xipeng Qiu, Zheng Zhang

Enhancing Systematic Decompositional Natural Language Inference Using Informal Logic (2024.emnlp-main)

Challenge:	Existing structured reasoning frameworks lack internal decision probability and cannot model the tree as a whole.
Approach:	They propose a Reinforcement Learning based Entailment Tree generation framework that is trained using the cumulative signals across the whole tree.
Outcome:	The proposed framework offers explicit deductions with entailment steps in a tree structure.

Copied to clipboard

Nathaniel Weir, Kate Sanders, Orion Weller, Shreya Sharma, Dongwei Jiang, Zhengping Jiang, Bhavana Dalvi Mishra, Oyvind Tafjord, Peter Jansen, Peter Clark, Benjamin Van Durme

Textual Inference

Challenge:	Recent language models allow structured reasoning with text, but lack of a clear protocol for discerning entailment causes noisy datasets and limited performance gains.
Approach:	They propose a consistent approach to annotating decompositional entailment and evaluate its impact on LLM-based textual inference.
Outcome:	The proposed approach has higher internal consistency than prior decompositional entailment datasets and significantly improves proof quality and accuracy.

Exploring Layer Activation Dynamic of CoT via Knowledge Probe (2026.acl-long)

Copied to clipboard

Chuanxin Zhang, Jiajun Liu, Yao He, Wenjun Ke, Peng Wang, Yankun Le, Sirui Liu, Zhaoyu Yang

Information Extraction & Text Mining

Challenge:	Chain-of-thought reasoning has emerged as a crucial paradigm for multi-step reasoning tasks.
Approach:	They propose a multi-stage probing framework that enforces structured reasoning with three explicit stages: keyword extraction, theorem generation, and computation execution.
Outcome:	The proposed framework enforces structured reasoning with three explicit stages: keyword extraction, theorem generation, and computation execution.

Causal-Audit: Explicit and Auditable Graph-based Reasoning via Target-Aware Causal Chain Construction (2026.findings-acl)

Copied to clipboard

Su Lan, Xuefei Yin, Yanming Zhu, Alan Wee-Chung Liew

Multimodality

Challenge:	Existing LLM-based methods rely on implicit language-level reasoning, resulting in opaque causal assumptions and fragile predictions.
Approach:	They propose an explicit and auditable causal reasoning framework for context-free intervention-based question answering that uses four modular stages rather than implicit end-to-end prediction.
Outcome:	The proposed framework outperforms existing LLM-based methods while providing interpretable and auditable causal reasoning traces.

MT-Mol: Multi Agent System with Tool-based Reasoning for Molecular Optimization (2025.findings-emnlp)

Copied to clipboard

Hyomin Kim, Yunhui Jang, Sungsoo Ahn

Explainability & Interpretability in NLP

Challenge:	Structured reasoning and tool-grounded molecular optimization are still underexplored.
Approach:	They propose a framework for molecular optimization that leverages tool-guided reasoning and role-specialized LLM agents.
Outcome:	a new framework outperforms existing LLM frameworks on 15 of 23 tasks.

Closing the Spatial Execution Gap in Digital Whiteboards via Verifiable Reinforcement Learning (2026.acl-long)

Copied to clipboard

Chang Liu, Benjamin Wagley, Zibo Wang, Mehmet E. Belviranli, Bo Wu

Decompose-ToM: Enhancing Theory of Mind Reasoning in Large Language Models through Simulation and Task Decomposition (2025.coling-main)

Challenge:	Large language models suffer from a fundamental Spatial Execution Gap, failing to translate visual semantics into precise, schema-valid coordinate operations in interactive environments.
Approach:	They propose a pipeline that leverages Group Relative Policy Optimization to enforce a strict Identify-Reason-Verify protocol and train on execution-verifiable rewards.
Outcome:	The proposed pipeline outperforms a state-of-the-art frontier model by 16.75% in operation accuracy.

Copied to clipboard

Sneheel Sarangi, Maha Elgarf, Hanan Salam

From Query to Logic: Ontology-Driven Multi-Hop Reasoning in LLMs (2026.findings-acl)

Challenge:	Theory of Mind (ToM) is the ability to attribute and infer the mental states of others.
Approach:	They propose an LLM-based inference algorithm that improves model performance on complex ToM tasks by simulating user perspectives.
Outcome:	The proposed algorithm improves model performance on complex ToM tasks while requiring minimal prompt tuning across tasks and no additional model training.

Copied to clipboard

Haonan Bian, Yutao Qi, Rui Yang, Yuanxi Che, Jiaqian Wang, Heming Xia, Ranran Zhen

Semantic Text Processing

Challenge:	Large Language Models (LLMs) exhibit limitations in complex multi-hop question answering tasks that necessitate non-linear, structured reasoning.
Approach:	They propose an ontology-driven reasoning and chain framework that combines LLMs’ generative capabilities with the structural benefits of knowledge graphs.
Outcome:	Extensive experiments across a diverse set of models and standard MQA benchmarks demonstrate that the proposed framework achieves competitive performance while producing more interpretable reasoning chains.

Measuring What Matters!! Assessing Therapeutic Principles in Mental-Health Conversation (2026.acl-long)

Copied to clipboard

Abdullah Mazhar, Het Riteshkumar Shah, Aseem Srivastava, Smriti Joshi, Md Shad Akhtar

Natural Logic at the Core: Dynamic Rewards for Entailment Tree Generation (2025.findings-acl)

Challenge:	Recent systems exhibit conversational competence but lack structured mechanisms to evaluate adherence to core therapeutic principles.
Approach:	They propose a framework to evaluate therapist-like responses for clinically grounded appropriateness and effectiveness using an ordinal scale.
Outcome:	The proposed framework achieves an F-1 score of 63.34 versus the baseline Qwen3 score of 38.56 .

Copied to clipboard

Jihao Shi, Xiao Ding, Kai Xiong, Hengwei Zhao, Bing Qin, Ting Liu

Safety is Not Only About Refusal: Reasoning-Enhanced Fine-tuning for Interpretable LLM Safety (2025.findings-acl)

Challenge:	Existing approaches to generating entailment trees lack logical consistency . static reward structures or intricate dependencies within multi-step reasoning are often ignored .
Approach:	They propose a method that integrates natural logic principles into reinforcement learning to guide entailment tree generation.
Outcome:	Experiments on EntailmentBank show that the proposed method improves interpretability and generalization.

Copied to clipboard

Yuyou Zhang, Miao Li, William Han, Yihang Yao, Zhepeng Cen, Ding Zhao

LLMs as Planning Formalizers: A Survey for Leveraging Large Language Models to Construct Automated Planning Models (2025.findings-acl)

Challenge:	Large Language Models (LLMs) are vulnerable to jailbreak attacks that exploit weaknesses in traditional safety alignment.
Approach:	They propose a framework that trains models to engage in explicit safe reasoning before response . they propose RATIONAL, which allows models to reject harmful prompts while providing meaningful and context-aware responses.
Outcome:	The proposed framework fine-tunes models to reason about query intent, ethics, and potential harm.

Copied to clipboard

Marcus Tantakoun, Christian Muise, Xiaodan Zhu

Inventive Problem Solving with LLMs: A Benchmark for TRIZ Reasoning (2026.findings-acl)

Challenge:	Large Language Models excel in various natural language tasks but struggle with long-horizon planning problems requiring structured reasoning.
Approach:	They propose to integrate large language models into AP and NLP planning frameworks by reviewing current research and identifying critical challenges and future directions.
Outcome:	The proposed frameworks are used to support reliable off-the-shelf AP planners.

Copied to clipboard

Zhu Wang, Brian Uzzi

Chain-of-Thought as a Lens: Evaluating Structured Reasoning Alignment between Human Preferences and Large Language Models (2026.acl-long)

Challenge:	Large language models are increasingly used in inventive problem-solving but effective support requires more than open-ended idea generation.
Approach:	They propose a dataset and benchmark for TRIZ reasoning grounded in open technical sources and U.S. patents.
Outcome:	The proposed framework represents trade-offs and links them to standardized inventive principles.

Copied to clipboard

Boxuan Wang, Zhuoyun Li, Xinmiao Huang, Xiaowei Huang, Yi Dong