MULTI-HOP QUESTION ANSWERING

MINTQA: A Multi-Hop Question Answering Benchmark for Evaluating LLMs on New and Long-tail Knowledge (2026.acl-long)

Challenge:	Recent approaches to multi-hop question answering rely on in-context learning . however, these models contain billions of parameters making them inefficient at inference time.
Approach:	They propose a framework that allows for improving smaller language models with less than 10 human-annotated QA pairs by synthesizing millions of multi-hop questions and claims to fine tune language models.
Outcome:	The proposed framework improves model performance on multi-hop question answering and fact verification benchmarks while being almost one-third the size in parameter count.

Copied to clipboard

Jie He, Nan Hu, Wanqiu Long, Jiaoyan Chen, Jeff Z. Pan

Hybrid Graphs for Table-and-Text based Question Answering using LLMs (2025.naacl-long)

Challenge:	Existing studies have shown that large language models can handle knowledge with varying familiarity.
Approach:	They propose a benchmark to evaluate multi-hop question answering on new and tail knowledge . they use RAG to integrate external knowledge into large language models .
Outcome:	The proposed benchmark evaluates the multi-hop reasoning ability of large language models . it primarily evaluates their ability to handle knowledge with different levels of familiarity .

Copied to clipboard

Ankush Agarwal, Chaitanya Devaguptapu, Ganesh S

Analyzing the Effectiveness of the Underlying Reasoning Tasks in Multi-hop Question Answering (2023.findings-eacl)

Challenge:	Current methods for QA rely on fine-tuning and high-quality data, which is difficult to obtain.
Approach:	They propose a Hybrid Graph-based approach for Table-Text QA that leverages Large Language Models without fine-tuning.
Outcome:	The proposed approach improves Exact Match scores by 10% on Hybrid-QA and 5.4% on OTT-QA.

Copied to clipboard

Xanh Ho, Anh-Khoa Duong Nguyen, Saku Sugawara, Akiko Aizawa

Dynamic Semantic Graph Construction and Reasoning for Explainable Multi-hop Science Question Answering (2021.findings-acl)

Challenge:	Existing studies have utilized underlying reasoning (UR) tasks in multi-hop question answering datasets to explain the predicted answers and evaluate models' reasoning abilities.
Approach:	They analyze UR tasks in QA datasets to determine their effectiveness . they find that UR task is helpful in preventing reasoning shortcuts .
Outcome:	The proposed model improves QA performance, reasoning shortcuts, and robustness on adversarial questions.

Copied to clipboard

Weiwen Xu, Huihui Zhang, Deng Cai, Wai Lam

Multimodality

Challenge:	Existing approaches suffer from low confidence when retrieving evidence facts to fill the knowledge gap and lack transparent reasoning process.
Approach:	They propose a framework to exploit more valid facts while obtaining explainability for multi-hop question answering at web scale by dynamically constructing a semantic graph and reasoning over it.
Outcome:	The proposed framework surpasses existing approaches while maintaining high explainability on OpenBookQA and ARC-Challenge.

COMPKE: Complex Question Answering under Knowledge Editing (2025.findings-acl)

Copied to clipboard

Keyuan Cheng, Zijian Kan, Zhuoran Zhang, Muhammad Asif Ali, Lijie Hu, Di Wang

Direct Evaluation of Chain-of-Thought in Multi-hop Reasoning with Knowledge Graphs (2024.findings-acl)

Challenge:	Existing benchmarks for knowledge editing do not accurately evaluate how well models apply knowledge in real-life situations.
Approach:	They propose a benchmark to evaluate how well updated models apply new knowledge in real-life situations.
Outcome:	The proposed method achieves 39.47 accuracy on GPT-4o-mini but drops significantly to 3.83 on Qwen2.5-3B.

Copied to clipboard

Thi Nguyen, Linhao Luo, Fatemeh Shiri, Dinh Phung, Yuan-Fang Li, Thuy-Trang Vu, Gholamreza Haffari

DocAssistant: Integrating Key-region Reading and Step-wise Reasoning for Robust Document Visual Question Answering (2025.findings-emnlp)

Challenge:	Prior research on evaluating large language models focused on answer accuracy, neglecting the correctness of the generated CoT.
Approach:	They propose a discriminative and generative CoT evaluation paradigm to assess LLMs’ knowledge of reasoning and the accuracy of the generated CoT.
Outcome:	The proposed evaluation paradigm assesses LLMs’ knowledge of reasoning and the accuracy of the generated CoT.

Copied to clipboard

Jinxu Zhang, Qiyuan Fan, Yu Zhang

Robustness in NLP

Challenge:	Existing document understanding models focus on key information and generate answers straightforwardly . existing models ignore evidence from source documents and lack interpretability .
Approach:	They propose a visual encoder that fuses text into visual encoded visual encodes . they use multimodal large language models as data generators and checkers to generate step-wise question-and-answer pairs for document images.
Outcome:	The proposed model can answer step-wise questions without compromising the performance of the original model.

EfficientRAG: Efficient Retriever for Multi-Hop Question Answering (2024.emnlp-main)

Copied to clipboard

Ziyuan Zhuang, Zhiyang Zhang, Sitao Cheng, Fangkai Yang, Jia Liu, Shujian Huang, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, Qi Zhang

FinePrompt: Unveiling the Role of Finetuned Inductive Bias on Compositional Reasoning in GPT-4 (2023.findings-emnlp)

Challenge:	Existing retrieval-augmented generation methods rely on multiple calls of large language models (LLMs) Large-language models lack knowledge underrepresented in training data and still face hallucinations.
Approach:	They propose an efficient retriever for multi-hop question answering that generates new queries iteratively without the need for LLM calls.
Outcome:	The proposed method surpasses existing methods on three open-domain multi-hop question-answering datasets.

Copied to clipboard

Jeonghwan Kim, Giwon Hong, Sung-Hyon Myaeng, Joyce Whang

Quick and (not so) Dirty: Unsupervised Selection of Justification Sentences for Multi-hop Question Answering (D19-1)

Challenge:	Large language models such as GPT-4 have demonstrated impressive capability to solve textual understanding problems at a level parallel to or surpassing state-of-the-art taskspecific models.
Approach:	They propose to transfer task-specific inductive biases from finetuned models to prompts to improve GPT-4's compositional reasoning capabilities.
Outcome:	The proposed prompt scheme shows competitive zero-shot and few-shot performances compared to existing prompts on complicated reasoning tasks.

Copied to clipboard

Vikas Yadav, Steven Bethard, Mihai Surdeanu

Uncertainty Guided Global Memory Improves Multi-Hop Question Answering (2023.emnlp-main)

Challenge:	Arras et al., 2017) suggest an unsupervised strategy for the selection of justification sentences for multi-hop question answering (QA) .
Approach:	They propose an unsupervised strategy for the selection of justification sentences for multi-hop question answering that maximizes the relevance of the selected sentences, minimizes overlap between selected facts, and maximizes coverage of both question and answer.
Outcome:	The proposed strategy improves state-of-the-art supervised QA model on two multi-hop QA datasets: AI2’s Reasoning Challenge (ARC) and Multi-Sentence Reading Comprehension (MultiRC).

Copied to clipboard

Alsu Sagirova, Mikhail Burtsev

Latent Reasoning for Low-Resource Question Generation (2021.findings-acl)

Challenge:	Transformers are used to solve multi-hop question answering tasks that require reasoning over multiple parts of a long document.
Approach:	They propose a method that collects relevant information over the entire document and then combines it with local context to solve a multi-hop question answering task.
Outcome:	The proposed method improves on three MHQA datasets compared to the baseline model.

Copied to clipboard

Xinting Huang, Jianzhong Qi, Yu Sun, Rui Zhang

Tackling Distractor Documents in Multi-Hop QA with Reinforcement and Curriculum Learning (2026.findings-eacl)

Challenge:	Existing approaches to multihop question generation require extensive data collection and decomposition.
Approach:	They propose a generative approach that optimizes the two-phase model without question decomposition data.
Outcome:	The proposed approach outperforms baselines on HOTPOTQA, a benchmark multi-hop question answering dataset.

Copied to clipboard

Jerry Huang, Siddarth Madala, Risham Sidhu, Cheng Niu, Hao Peng, Julia Hockenmaier, Tong Zhang

Dynamic Strategy Planning for Efficient Question Answering with Large Language Models (2025.findings-naacl)

Challenge:	Existing work on retrieval-augmented generation systems has shown that retrievers exhibit imperfect recall and precision, limiting downstream performance.
Approach:	They propose a retrieval-augmented generation model that generates answers from larger sets of retrieved contexts.
Outcome:	The proposed model generates answers and cites relevant information from larger sets of retrieved contexts.

Copied to clipboard

Tanmay Parekh, Pradyot Prakash, Alexander Radovic, Akshay Shekher, Denis Savenkov

If You Want to Go Far Go Together: Unsupervised Joint Candidate Evidence Retrieval for Multi-hop Question Answering (2021.naacl-main)

Challenge:	Existing studies have shown that using a single fixed strategy for answering all different kinds of questions is sub-optimal in performance and inefficient in terms of generated tokens and retrievals.
Approach:	They propose a technique to induce a dynamic strategy selection process in Large Language Models (LLMs) by incorporating an initial decision step to select the most suitable strategy conditioned on the input question and guides the LLM’s response generation accordingly.
Outcome:	The proposed technique improves model performance by 7-13% while reducing the cost by 11-32% relative to the best baseline model.

Copied to clipboard

Vikas Yadav, Steven Bethard, Mihai Surdeanu

Answering Questions by Meta-Reasoning over Multiple Chains of Thought (2023.emnlp-main)

Challenge:	et al. : evidence retrieval is highly dependent on partial, incorrect or no supporting knowledge.
Approach:	They propose a method that retrieves and reranks evidence facts jointly . they propose to account for links between sentences and coverage with the given query .
Outcome:	The proposed approach achieves state-of-the-art evidence retrieval performance on two multi-hop question answering datasets.

Copied to clipboard

Ori Yoran, Tomer Wolfson, Ben Bogin, Uri Katz, Daniel Deutch, Jonathan Berant

Question Answering

Challenge:	Modern systems for multi-hop question answering (QA) break questions into a sequence of reasoning steps, termed chain-of-thought (CoT) Often, multiple chains are sampled and aggregated, but the intermediate steps themselves are discarded.
Approach:	They propose a method which prompts large language models to meta-reason over multiple chains of thought rather than aggregate their answers.
Outcome:	The proposed approach outperforms baselines on 7 multi-hop QA datasets.

Multi-Step Reasoning Over Unstructured Text with Beam Dense Retrieval (2021.naacl-main)

Copied to clipboard

Chen Zhao, Chenyan Xiong, Jordan Boyd-Graber, Hal Daumé III

Leveraging Structured Information for Explainable Multi-hop Question Answering and Reasoning (2023.findings-emnlp)

Challenge:	Current methods for complex question answering use structured knowledge and unstructured text.
Approach:	They propose a multi-step retrieval approach that iteratively forms an evidence chain through beam search in dense representations.
Outcome:	The proposed method is competitive to state-of-the-art systems without using semi-structured information.

Copied to clipboard

Ruosen Li, Xinya Du

Unsupervised Multi-hop Question Answering by Question Generation (2021.naacl-main)

Challenge:	Neural models, including large language models (LLMs), achieve superior performance on multi-hop question-answering tasks.
Approach:	They propose to use the chain-of-thought mechanism to generate both the reasoning chain and the answer.
Outcome:	Empirical results show that the proposed framework generates more faithful reasoning chains and significantly improves the QA performance on two benchmark datasets.

Copied to clipboard

Liangming Pan, Wenhu Chen, Wenhan Xiong, Min-Yen Kan, William Yang Wang

A STEP towards Interpretable Multi-Hop Reasoning:Bridge Phrase Identification and Query Expansion (2022.lrec-1)

Challenge:	Existing training data for multi-hop question answering (QA) is time-consuming and resource-intensive.
Approach:	They propose an unsupervised framework that generates human-like multi-hop training data from homogeneous and heterogeneously data sources.
Outcome:	The proposed framework achieves 61% and 83% of the supervised learning performance for the HybridQA and HotpotQA datasets.

Copied to clipboard

Fan Luo, Mihai Surdeanu

Question Answering

Challenge:	Identifying bridge phrases remains one of the challenges for multi-hop question answering .
Approach:	They propose an unsupervised method for the identification of bridge phrases in multi-hop question answering . they construct a graph of noun phrases from the question and available context .
Outcome:	The proposed method improves all downstream components in a multi-hop QA system.

Generative Context Pair Selection for Multi-hop Question Answering (2021.emnlp-main)

Copied to clipboard

Dheeru Dua, Cicero Nogueira dos Santos, Patrick Ng, Ben Athiwaratkun, Bing Xiang, Matt Gardner, Sameer Singh

Reasoning

Challenge:	Recent studies have shown that discriminative training results in models that exploit these underlying biases to achieve a better held-out performance, without learning the right way to reason.
Approach:	They propose a generative context selection model for multi-hop QA that reasons about how the given question could have been generated given a context pair and not just independent contexts.
Outcome:	The proposed model outperforms the state-of-the-art model on hotpotQA while being comparable to the state of the art answering performance on adversarial held-out set.

Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps (2020.coling-main)

Copied to clipboard

Xanh Ho, Anh-Khoa Duong Nguyen, Saku Sugawara, Akiko Aizawa

Question Answering

Challenge:	Existing multi-hop question answering datasets do not provide a complete explanation for the reasoning process from the question to the answer.
Approach:	They propose a multi-hop question answering dataset that uses structured and unstructured data to test reasoning skills.
Outcome:	The proposed dataset ensures multi-hop reasoning while being challenging for multi-models.

RASPberry: Retrieval-Augmented Monte Carlo Tree Self-Play with Reasoning Consistency for Multi-Hop Question Answering (2025.findings-acl)

Copied to clipboard

Baixuan Li, Yunlong Fan, Tianyi Ma, Miao Gao, Chuanqi Shi, Zhiqiang Gao

Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy (2023.findings-emnlp)

Challenge:	Existing methods for generating and analyzing multiple document knowledge are not effective for multi-hop question answering.
Approach:	They propose a Monte Carlo tree-based approach to inference-time scaling using RASPberry.
Outcome:	Experimental results show that the proposed method achieves better inference-time scaling on smaller LLMs.

Copied to clipboard

Zhihong Shao, Yeyun Gong, Yelong Shen, Minlie Huang, Nan Duan, Weizhu Chen

Single Sequence Prediction over Reasoning Graphs for Multi-hop QA (2023.acl-long)

Challenge:	Recent work has proposed to improve relevance modeling by having large language models actively involved in retrieval, i.e., to guide retrieval with generation.
Approach:	They propose to have large language models actively involved in retrieval to guide retrieval with generation.
Outcome:	The proposed method synergizes retrieval and generation in an iterative manner, and can generate better results in subsequent iterations.

Copied to clipboard

Gowtham Ramesh, Makesh Narsimhan Sreedhar, Junjie Hu

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

Challenge:	Recent generative approaches for multi-hop question answering (QA) use fusion-in-decoder to generate a single sequence output . but, they often have difficulty accurately identifying passages corresponding to key entities in the context .
Approach:	They propose a single-sequence prediction method that integrates a graph structure linking key entities in each context passage to relevant subsequent passages for each question.
Outcome:	The proposed method improves answer exact-match/F1 scores and faithfulness of grounding on the hotpotQA dataset and achieves state-of-the-art numbers on the Musique dataset.

Copied to clipboard

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

Graph-Induced Transformers for Efficient Multi-Hop Question Answering (2022.emnlp-main)

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.

Copied to clipboard

Giwon Hong, Jeonghwan Kim, Junmo Kang, Sung-Hyon Myaeng

Hierarchical Graph Network for Multi-hop Question Answering (2020.emnlp-main)

Challenge:	Recent MHQA tasks that require inter-paragraph/sentence linkages use graphs to model internal structural information within text.
Approach:	They propose a graph-induced transformer that applies graph-derived attention patterns directly into a PLM without external graph modules.
Outcome:	The proposed model can replace external graph modules while preserving model performance.

Copied to clipboard

Yuwei Fang, Siqi Sun, Zhe Gan, Rohit Pillai, Shuohang Wang, Jingjing Liu

A Simple Yet Strong Pipeline for HotpotQA (2020.emnlp-main)

Challenge:	Existing multi-hop question answering models focus on multi-level reasoning across multiple documents or paragraphs.
Approach:	They propose a hierarchical graph network that aggregates clues from scattered texts . they use a set of contextual encoders to initialize nodes on different levels of granularity .
Outcome:	The proposed model outperforms existing multi-hop QA approaches on the HotpotQA benchmark.

Copied to clipboard

Dirk Groeneveld, Tushar Khot, null Mausam, Ashish Sabharwal

SRLGRN: Semantic Role Labeling Graph Reasoning Network (2020.emnlp-main)

Challenge:	Existing models for multi-hop question answering have been proposed with varying complexities.
Approach:	They propose to use BERT to identify potentially relevant sentences independently of each other . they feed selected sentences into a standard BERT span prediction model to choose an answer .
Outcome:	The proposed pipeline outperforms existing models on hotpotQA and support identification.

Copied to clipboard

Chen Zheng, Parisa Kordjamshidi

KG-CQR: Leveraging Structured Relation Representations in Knowledge Graphs for Contextual Query Retrieval (2025.emnlp-main)

Challenge:	Existing models that use context and type-matching heuristics do not provide realistic evaluation of reasoning capabilities.
Approach:	They propose a graph reasoning network based on the semantic structure of the sentences to learn cross paragraph reasoning paths and find supporting facts and the answer jointly.
Outcome:	The proposed network shows competitive performance on the HotpotQA distractor setting benchmark compared to the state-of-the-art models.

Copied to clipboard

Chi Minh Bui, Ngoc Mai Thieu, Vinh Van Nguyen, Jason J. Jung, Khac-Hoai Nam Bui

Shifting from Ranking to Set Selection for Retrieval Augmented Generation (2025.acl-long)

Challenge:	Existing methods that address corpus-level context loss focus on query enrichment through structured relation representations.
Approach:	They propose a framework for Contextual Query Retrieval that enriches queries with contextual representations derived from a corpus-centric KG.
Outcome:	The proposed framework outperforms strong baselines on RAGBench and MultiHop-RAG datasets in terms of retrieval effectiveness.

Copied to clipboard

Dahyun Lee, Yongrae Jo, Haeju Park, Moontae Lee

Re-ReST: Reflection-Reinforced Self-Training for Language Agents (2024.emnlp-main)

Challenge:	Existing approaches primarily rerank top-k passages based on individual relevance, often failing to meet the information needs of complex queries in multi-hop question answering.
Approach:	They propose a set-wise passage selection approach and introduce SetR which explicitly identifies the information requirements of a query through Chain-of-Thought reasoning.
Outcome:	The proposed approach outperforms both proprietary LLM-based rerankers and open-source baselines in terms of answer correctness and retrieval quality.

Copied to clipboard

Zi-Yi Dou, Cheng-Fu Yang, Xueqing Wu, Kai-Wei Chang, Nanyun Peng

Optimizing Question Semantic Space for Dynamic Retrieval-Augmented Multi-hop Question Answering (2025.acl-long)

Challenge:	Existing methods to fine tune language agents with reasoning-action trajectories require high-quality model-generated samples, which are hard to obtain for challenging language agent tasks.
Approach:	They propose a method to employ reflection during inference without ground-truth feedback to improve agents more autonomously.
Outcome:	The proposed method improves self-training performance on open-source language agents by 7.6% and 14.1% respectively.

Copied to clipboard

Linhao Ye, Lang Yu, Zhikai Lei, Qin Chen, Jie Zhou, Liang He

Avoiding Knowledge Edit Skipping in Multi-hop Question Answering with Guided Decomposition (2025.findings-emnlp)

Challenge:	Existing retrieval-augmented generation methods are insufficient for multi-hop question answering . however, they tend to generate hallucinations due to semantic mismatching .
Approach:	They propose to optimize question semantic space for dynamic retrieval-augmented multi-hop question answering by optimizing the semantic embeddings.
Outcome:	The proposed method outperforms existing RAG methods in both in- and out-of-domain settings.

Copied to clipboard

Yi Liu, Xiangrong Zhu, Xiangyu Liu, Wei Wei, Wei Hu

DAVIS: Planning Agent with Knowledge Graph-Powered Inner Monologue (2025.findings-emnlp)

Challenge:	Existing methods for knowledge editing fail to work in multi-hop question answering due to 'edit skipping' edit skipping occurs due to the mismatch between the granularity of LLMs in problem-solving and the facts in the edited memory.
Approach:	They propose a retrieval-augmented generation-based method that edits knowledge without modifying parameters without retraining LLMs.
Outcome:	The proposed method outperforms state-of-the-art methods for KE in multi-hop question answering.

Copied to clipboard

Minh Pham Dinh, Michael G Yankoski, Munira Syed, Trenton W. Ford

Knowledge Representation

Challenge:	Existing approaches to designing a generalist scientific agent fail to address multifaceted requirements of scientific tasks.
Approach:	DAVIS is a generalist scientific agent capable of performing tasks in laboratory settings to assist researchers.
Outcome:	DAVIS performs better on ScienceWorld benchmarks compared to previous approaches on 8 out of 9 elementary science subjects.

Drilling Down into the Discourse Structure with LLMs for Long Document Question Answering (2023.findings-emnlp)

Copied to clipboard

Inderjeet Nair, Shwetha Somasundaram, Apoorv Saxena, Koustava Goswami

Beyond the Answer: Advancing Multi-Hop QA with Fine-Grained Graph Reasoning and Evaluation (2025.acl-long)

Challenge:	Long document question answering requires locating relevant paragraphs within a document to answer a question.
Approach:	They propose to exploit the discourse structure commonly found in documents to create a condensed representation of the document, enabling a more comprehensive understanding and analysis of relationships between different parts.
Outcome:	The proposed approach retains 99.6% of the best zero-shot approach's performance while processing only 26% of tokens used by the best approach in the information seeking evidence retrieval setup.

Copied to clipboard

Qichuan Liu, Chentao Zhang, Chenfeng Zheng, Guosheng Hu, Xiaodong Li, Zhihong Zhang

Progressive Planning and Reinforced Reasoning: Large Language Model-Guided Multi-hop Question Answering over Knowledge Graph (2026.findings-acl)

Challenge:	Existing evaluations of multi-hop question answering systems focus on comparing final answers of reasoning method and given ground-truths.
Approach:	They propose a "Planner-Executor-Reasoner" architecture that evaluates reasoning . they propose PER-DP and PER QA architectures that provide ground-truths .
Outcome:	The proposed model improves the performance of multi-hop question answering systems.

Copied to clipboard

Xiang Li, Runhai Jiao, Ruifan Li, Dongnan Wu, Ruojiao Qiao, Lei Liu

CIRAG: Construction–Integration Retrieval and Adaptive Generation for Multi-hop Question Answering (2026.acl-long)

Challenge:	Existing approaches to multi-hop question answering lack effective intermediate guidance and policy networks focus on local neighborhood information, making it difficult to anticipate the long-term consequences of decisions.
Approach:	They propose a framework that converts decomposed sub-question sequences into stepwise decision guidance and a structure-aware lookahead policy network to enhance the agent's global state awareness and decision foresight in complex environments.
Outcome:	The proposed framework surpasses state-of-the-art methods while showing strong generalization.

Copied to clipboard

Zili Wei, Yilin Wang, Xiaocui Yang, Shi Feng, Weidong Bao, Daling Wang, Zihan Wang, Yifei Zhang

Reflection on Knowledge Graph for Large Language Models Reasoning (2025.findings-acl)

Challenge:	Existing methods for iterative retrieval-augmented generation (iRAG) suffer from greedy single-path expansion and granularity–demand mismatch .
Approach:	They propose a model that constructs candidate triples and history-conditionally integrates them to distill core triples to generate the next-hop query.
Outcome:	The proposed model mitigates the greedy single-path expansion and granularity–demand mismatch by preserving multiple plausible evidence chains.

Copied to clipboard

Yigeng Zhou, Wu Li, Yifan Lu, Jing Li, Fangming Liu, Meishan Zhang, Yequan Wang, Daojing He, Honghai Liu, Min Zhang

Rethinking the Role of Entropy in Optimizing Tool-Use Behaviors for Large Language Model Agents (2026.acl-long)

Challenge:	Existing methods for supplementing Large Language Models (LLMs) with knowledge graphs often introduce noise in the retrieval and reasoning pipeline, hindering their ability to integrate external knowledge for complex multi-hop question answering.
Approach:	They propose a framework to enhance LLMs' reasoning capabilities through reflective engagement with knowledge graphs by Query Decoupling, LLM-Driven Knowledge Graph Exploration, and Inference with Knowledge Reconstruction.
Outcome:	The proposed framework integrates external knowledge into LLMs and trains them to leverage this knowledge for answering questions.

Copied to clipboard

Zeping Li, Hongru Wang, Yiwen Zhao, Guanhua Chen, Yixia Li, Keyang Chen, Yixin Cao, Guangnan Ye, Hongfeng Chai, Zhenfei Yin

Reasoning with Graphs: Structuring Implicit Knowledge to Enhance LLMs Reasoning (2025.findings-acl)

Challenge:	Large language models excel in mathematical reasoning and multi-hop question answering tasks, but in long trajectories, agents often invoke tools excessively or inappropriately, increasing computation cost and derailing the reasoning process.
Approach:	They propose to use entropy reduction as a supervisory signal to reduce tool calls . they propose to design two reward strategies to address the needs of optimizing tool-use behavior.
Outcome:	The proposed reward strategies reduce tool calls by 72.07% and improve performance by 22.27%.

Copied to clipboard

Haoyu Han, Yaochen Xie, Hui Liu, Xianfeng Tang, Sreyashi Nag, William Headden, Yang Li, Chen Luo, Shuiwang Ji, Qi He, Jiliang Tang

Multimodality

Challenge:	Large language models (LLMs) have demonstrated remarkable success across a wide range of tasks, however, they still face challenges in reasoning tasks that require understanding and inferring relationships between distinct pieces of information within text sequences.
Approach:	They propose to construct explicit graphs from context and leverage them to enhance LLM reasoning performance on reasoning tasks.
Outcome:	Extensive experiments show that the proposed method improves both logical reasoning and multi-hop question answering tasks.

Search-in-Context: Efficient Multi-Hop QA over Long Contexts via Monte Carlo Tree Search with Dynamic KV Retrieval (2025.findings-acl)

Copied to clipboard

Jiabei Chen, Guang Liu, Shizhu He, Kun Luo, Yao Xu, Jun Zhao, Kang Liu