arXiv subjects

Zaiqiao Meng

Publications and source records attributed to Zaiqiao Meng.

At least 19 recordsLinked to original sources

arXiv2026

GraphMed-LT: Patient-Specific Graph Memory with Latent Clinical Thought Refinement for Multi-Turn Medical Conversations

Multi-turn medical question answering (QA) aims to model realistic clinical diagnosis, where a doctor gathers patient information across multiple turns of conversation. Existing multi-turn medical conversation systems have shown promising progress, but they often rely on accumulated conversation histories as memory, leaving clinical evidence fragmented across turns. We propose GraphMed-LT, a patient-specific graph memory approach with latent clinical thought refinement for multi-turn medical conversations. GraphMed-LT extracts patient-specific clinical triplets from patient responses, retrieves relevant knowledge triplets, and organises them into an incrementally updated graph memory. The graph memory is projected into graph-conditioned evidence tokens and refined inside a trainable doctor agent through hidden-state feedback, enabling the agent to update its internal clinical context before asking follow-up questions or producing the final answer. Experiments on three multi-turn medical QA benchmarks show that GraphMed-LT consistently outperforms existing multi-turn medical conversation baselines across multiple LLM backbones, achieving up to a 6.3 percentage-point absolute improvement over the strongest baseline. Further analyses show that GraphMed-LT asks more answerable follow-up questions and provides consistent gains across medical specialties.

cs.CL↗

arXiv2026

SSE-Bio: A Structured Self-Evolving Agent with Agentic Retrieval Policy for Multi-Hop Biomedical Reasoning

Biomedical multi-hop question answering (QA) requires models to connect evidence across intermediate entities such as diseases, drugs, proteins, and phenotypes. Existing agents typically rely on static retrieval workflows or coarse-grained prompt rewriting, which can lead to instruction drift when reasoning procedures need to be updated. We propose SSE-Bio, a structured self-evolving agent with an agentic retrieval policy for multi-hop biomedical reasoning. Instead of globally rewriting agent instructions, SSE-Bio maintains a structured state, selectively retrieves knowledge triplets and prior templates through a trainable proxy policy, and improves its reasoning memory through fine-grained template editing. To optimise retrieval decisions, we introduce a proxy-training strategy based on group relative policy optimization, where the proxy is improved through decision-contrastive groups over alternative retrieval choices. Experiments on three biomedical multi-hop QA benchmarks show that SSE-Bio consistently outperforms existing baselines, achieving an improvement of 6.56 absolute points over the strongest self-evolving baseline on BioHopR.

cs.CL↗

arXiv2026

CCS: Clinical Consensus Selection for Radiology Report Generation

Radiology report generation (RRG) is commonly formulated as a single-path generation task, where a multimodal large language model (MLLM) produces one decoded report as the final output. While recent progress has largely been driven by scaling training data, model capacity, and retrieval mechanisms, improving report quality at inference time remains underexplored. In this work, we observe that fixed radiology MLLMs often generate clinically stronger reports elsewhere in their candidate pool than the one selected by default decoding, suggesting that inference-time decision making remains an overlooked bottleneck. To address this, we propose Clinical Consensus Selection (CCS), a decoder-agnostic inference-time selection framework that samples multiple candidate reports and selects the one with the highest clinical consensus across the rollout pool. CCS unifies text-based utilities with a radiology-adapted utility computed by an image--report-trained multimodal embedder, which measures candidate agreement beyond surface-level textual similarity. Across three datasets and multiple radiology MLLMs, CCS consistently improves inference-time performance over single-path decoding and generic Best-of-N baselines, with particularly clear gains on clinical metrics. Further analysis shows that image-grounded utility forms a selection axis distinct from textual consensus and that substantial headroom remains for improving RRG at inference time.

cs.CL↗

arXiv2026

A Large-Scale Dataset and Benchmark: Do Protein-Ligand Models Learn Binding Sites or Just Binding Likelihood?

Protein-ligand modeling underpins computational drug discovery and molecular design. Existing protein-ligand benchmarks typically evaluate whether a protein and ligand interact and how strongly they bind, through tasks such as binary binding prediction and affinity regression. However, these evaluations provide limited evidence of whether models can localize binding sites or identify the non-covalent interactions underlying molecular recognition. To address this gap, we introduce InteractBind, a large-scale protein-ligand dataset comprising approximately 100k protein-ligand pairs, together with a benchmark for fine-grained evaluation. The core fine-grained task is that of binding-site localization, which uses protein-residue and ligand-atom interaction maps spanning six major types of non-covalent interactions to assess whether model-derived interaction maps localize binding sites. InteractBind further includes binding affinity and protein similarity-controlled splits to support realistic generalization assessment. Using InteractBind, we evaluate eight existing sequence-based and interaction-aware models, assessing binary binding prediction and binding-site localization. Results reveal limited binding-site localization despite strong binary binding prediction, with marked variation across non-covalent interaction types. Overall, InteractBind establishes a benchmark paradigm that encourages the development of more interpretable and physically grounded protein-ligand models.

cs.LG↗

arXiv2026

Failure Modes in Multi-Hop QA: The Weakest Link Effect and the Recognition Bottleneck

Despite scaling to massive context windows, Large Language Models (LLMs) struggle with multi-hop reasoning due to inherent position bias, which causes them to overlook information at certain positions. Whether these failures stem from an inability to locate evidence (recognition failure) or integrate it (synthesis failure) is unclear. We introduce Multi-Focus Attention Instruction (MFAI), a semantic probe to disentangle these mechanisms by explicitly steering attention towards selected positions. Across 5 LLMs on two multi-hop QA tasks (MuSiQue and NeoQA), we identify the "Weakest Link Effect": in our 18-document, 3-bucket setting, multi-hop reasoning performance collapses to the level of the least visible evidence, governed by absolute position rather than the linear distance between facts. While matched MFAI resolves recognition bottlenecks, improving accuracy by up to 11.49% in low-visibility positions, misleading MFAI yields divergent effects modulated by task topology: entity-centric tasks with vertical reasoning chains are vulnerable, whereas event-centric tasks with horizontal evidence structures are more resilient. Finally, we demonstrate that thinking models utilizing System-2 reasoning effectively locate and integrate the required information, matching gold-only baselines even in noisy, long-context settings. Supplementary experiments on 2WikiMultiHopQA, extended 3-4 hop counts, and a 32B model confirm these findings generalize across datasets, reasoning depths, and model scales.

cs.AI↗

arXiv2026

SEW: Self-Evolving Agentic Workflows for Automated Code Generation

Large Language Models (LLMs) have demonstrated effectiveness in code generation tasks. To enable LLMs to address more complex coding challenges, existing research has focused on crafting multi-agent systems with agentic workflows, where complex coding tasks are decomposed into sub-tasks, assigned to specialized agents. Despite their effectiveness, current approaches heavily rely on hand-crafted agentic workflows, with both agent topologies and prompts manually designed, which limits their ability to automatically adapt to different types of coding problems. To address these limitations and enable automated workflow design, we propose \textbf{S}elf-\textbf{E}volving \textbf{W}orkflow (\textbf{SEW}), a novel self-evolving framework that automatically generates and optimises multi-agent workflows. Extensive experiments on three coding benchmark datasets, including the challenging LiveCodeBench, demonstrate that our SEW can automatically design agentic workflows and optimise them through self-evolution, bringing up to 12\% improvement on LiveCodeBench compared to using the backbone LLM only. Furthermore, by investigating different representation schemes of workflow, we provide insights into the optimal way to encode workflow information with text.

cs.SE↗

arXiv2026

EvoIdeator: Evolving Scientific Ideas through Checklist-Grounded Reinforcement Learning

Scientific idea generation is a cornerstone of autonomous knowledge discovery, yet the iterative evolution required to transform initial concepts into high-quality research proposals remains a formidable challenge for Large Language Models (LLMs). Existing Reinforcement Learning (RL) paradigms often rely on rubric-based scalar rewards that provide global quality scores but lack actionable granularity. Conversely, language-based refinement methods are typically confined to inference-time prompting, targeting models that are not explicitly optimized to internalize such critiques. To bridge this gap, we propose \textbf{EvoIdeator}, a framework that facilitates the evolution of scientific ideas by aligning the RL training objective with \textbf{checklist-grounded feedback}. EvoIdeator leverages a structured judge model to generate two synergistic signals: (1) \emph{lexicographic rewards} for multi-dimensional optimization, and (2) \emph{fine-grained language feedback} that offers span-level critiques regarding grounding, feasibility, and methodological rigor. By integrating these signals into the RL loop, we condition the policy to systematically utilize precise feedback during both optimization and inference. Extensive experiments demonstrate that EvoIdeator, built on Qwen3-4B, significantly outperforms much larger frontier models across key scientific metrics. Crucially, the learned policy exhibits strong generalization to diverse external feedback sources without further fine-tuning, offering a scalable and rigorous path toward self-refining autonomous ideation.

cs.AI↗

arXiv2026

EvoScientist: Towards Multi-Agent Evolving AI Scientists for End-to-End Scientific Discovery

The increasing adoption of Large Language Models (LLMs) has enabled AI scientists to perform complex end-to-end scientific discovery tasks requiring coordination of specialized roles, including idea generation and experimental execution. However, most state-of-the-art AI scientist systems rely on static, hand-designed pipelines and fail to adapt based on accumulated interaction histories. As a result, these systems overlook promising research directions, repeat failed experiments, and pursue infeasible ideas. To address this, we introduce EvoScientist, an evolving multi-agent AI scientist framework that continuously improves research strategies through persistent memory and self-evolution. EvoScientist comprises three specialized agents: a Researcher Agent (RA) for scientific idea generation, an Engineer Agent (EA) for experiment implementation and execution, and an Evolution Manager Agent (EMA) that distills insights from prior interactions into reusable knowledge. EvoScientist contains two persistent memory modules: (i) an ideation memory, which summarizes feasible research directions from top-ranked ideas while recording previously unsuccessful directions; and (ii) an experimentation memory, which captures effective data processing and model training strategies derived from code search trajectories and best-performing implementations. These modules enable the RA and EA to retrieve relevant prior strategies, improving idea quality and code execution success rates over time. Experiments show that EvoScientist outperforms 7 open-source and commercial state-of-the-art systems in scientific idea generation, achieving higher novelty, feasibility, relevance, and clarity via automatic and human evaluation. EvoScientist also substantially improves code execution success rates through multi-agent evolution, demonstrating persistent memory's effectiveness for end-to-end scientific discovery.

cs.CL↗

arXiv2025

T-Retrievability: A Topic-Focused Approach to Measure Fair Document Exposure in Information Retrieval

Retrievability of a document is a collection-based statistic that measures its expected (reciprocal) rank of being retrieved within a specific rank cut-off. A collection with uniformly distributed retrievability scores across documents is an indicator of fair document exposure. While retrievability scores have been used to quantify the fairness of exposure for a collection, in our work, we use the distribution of retrievability scores to measure the exposure bias of retrieval models. We hypothesise that an uneven distribution of retrievability scores across the entire collection may not accurately reflect exposure bias but rather indicate variations in topical relevance. As a solution, we propose a topic-focused localised retrievability measure, which we call \textit{T-Retrievability} (topic-retrievability), which first computes retrievability scores over multiple groups of topically-related documents, and then aggregates these localised values to obtain the collection-level statistics. Our analysis using this proposed T-Retrievability measure uncovers new insights into the exposure characteristics of various neural ranking models. The findings suggest that this localised measure provides a more nuanced understanding of exposure fairness, offering a more reliable approach for assessing document accessibility in IR systems.

cs.IR↗

arXiv2025

CCD: Mitigating Hallucinations in Radiology MLLMs via Clinical Contrastive Decoding

Multimodal large language models (MLLMs) have recently achieved remarkable progress in radiology by integrating visual perception with natural language understanding. However, they often generate clinically unsupported descriptions, known as medical hallucinations, which pose serious risks in medical applications that demand accuracy and image-grounded outputs. Through empirical analysis, we find that prompt-induced hallucinations remain prevalent in radiology MLLMs, largely due to over-sensitivity to clinical sections. To address this, we introduce Clinical Contrastive Decoding (CCD), a training-free and retrieval-free inference framework that integrates structured clinical signals from task-specific radiology expert models. CCD introduces a dual-stage contrastive mechanism to refine token-level logits during generation, thereby enhancing clinical fidelity without modifying the base MLLM. Experiments on three datasets and multiple models demonstrate that CCD consistently improves overall performance on radiology report generation (RRG). On the MIMIC-CXR dataset, it yields up to a 17% improvement in RadGraph-F1 when applied to state-of-the-art RRG models. Our approach provides a lightweight and generalisable solution for mitigating medical hallucinations, effectively bridging expert models and MLLMs in radiology.

cs.CL↗

arXiv2025

FusionDTI: Fine-grained Binding Discovery with Token-level Fusion for Drug-Target Interaction

Predicting drug-target interaction (DTI) is critical in the drug discovery process. Despite remarkable advances in recent DTI models through the integration of representations from diverse drug and target encoders, such models often struggle to capture the fine-grained interactions between drugs and protein, i.e. the binding of specific drug atoms (or substructures) and key amino acids of proteins, which is crucial for understanding the binding mechanisms and optimising drug design. To address this issue, this paper introduces a novel model, called FusionDTI, which uses a token-level Fusion module to effectively learn fine-grained information for Drug-Target Interaction. In particular, our FusionDTI model uses the SELFIES representation of drugs to mitigate sequence fragment invalidation and incorporates the structure-aware (SA) vocabulary of target proteins to address the limitation of amino acid sequences in structural information, additionally leveraging pre-trained language models extensively trained on large-scale biomedical datasets as encoders to capture the complex information of drugs and targets. Experiments on three well-known benchmark datasets show that our proposed FusionDTI model achieves the best performance in DTI prediction compared with seven existing state-of-the-art baselines. Furthermore, our case study indicates that FusionDTI could highlight the potential binding sites, enhancing the explainability of the DTI prediction.

q-bio.QM↗

arXiv2025

EvoAgentX: An Automated Framework for Evolving Agentic Workflows

Multi-agent systems (MAS) have emerged as a powerful paradigm for orchestrating large language models (LLMs) and specialized tools to collaboratively address complex tasks. However, existing MAS frameworks often require manual workflow configuration and lack native support for dynamic evolution and performance optimization. In addition, many MAS optimization algorithms are not integrated into a unified framework. In this paper, we present EvoAgentX, an open-source platform that automates the generation, execution, and evolutionary optimization of multi-agent workflows. EvoAgentX employs a modular architecture consisting of five core layers: the basic components, agent, workflow, evolving, and evaluation layers. Specifically, within the evolving layer, EvoAgentX integrates three MAS optimization algorithms, TextGrad, AFlow, and MIPRO, to iteratively refine agent prompts, tool configurations, and workflow topologies. We evaluate EvoAgentX on HotPotQA, MBPP, and MATH for multi-hop reasoning, code generation, and mathematical problem solving, respectively, and further assess it on real-world tasks using GAIA. Experimental results show that EvoAgentX consistently achieves significant performance improvements, including a 7.44% increase in HotPotQA F1, a 10.00% improvement in MBPP pass@1, a 10.00% gain in MATH solve accuracy, and an overall accuracy improvement of up to 20.00% on GAIA. The source code is available at: https://github.com/EvoAgentX/EvoAgentX

cs.AI↗

arXiv2025

RadEval: A framework for radiology text evaluation

We introduce RadEval, a unified, open-source framework for evaluating radiology texts. RadEval consolidates a diverse range of metrics, from classic n-gram overlap (BLEU, ROUGE) and contextual measures (BERTScore) to clinical concept-based scores (F1CheXbert, F1RadGraph, RaTEScore, SRR-BERT, TemporalEntityF1) and advanced LLM-based evaluators (GREEN). We refine and standardize implementations, extend GREEN to support multiple imaging modalities with a more lightweight model, and pretrain a domain-specific radiology encoder, demonstrating strong zero-shot retrieval performance. We also release a richly annotated expert dataset with over 450 clinically significant error labels and show how different metrics correlate with radiologist judgment. Finally, RadEval provides statistical testing tools and baseline model evaluations across multiple publicly available datasets, facilitating reproducibility and robust benchmarking in radiology report generation.

cs.CL↗

arXiv2025

Time to Revist Exact Match

Temporal question answering is an established method for evaluating temporal reasoning in large language models. Expected answers are often numeric (e.g., dates or durations), yet model responses are evaluated like regular text with exact match (EM), unable to distinguish small from large errors. In this investigative work, we frame temporal question answering as a numerical estimation task to assess the shortcomings of EM. We introduce TempAnswerQA, a benchmark distilled from Test of Time and TempTabQA, where all questions require a numerical, temporal answer, allowing us to evaluate models beyond EM. We use the forecasting metrics symmetric mean absolute percentage error (sMAPE) and mean absolute scaled error (MASE). With sMAPE, we find that error size and EM are decoupled. Models with low EM still have low sMAPE (both ~20%), and some models have high sMAPE despite high EM. Scaling errors by the deviation of the ground truth data with MASE reshuffles model rankings compared to EM, revealing gaps in models' understanding of temporal domain knowledge, especially when trained with synthetic data. Lastly, the models' most frequent error is to deviate by only $\pm1$ from the ground truth. sMAPE and MASE, unlike EM, adequately weight these errors. Our findings underscore the need for specialised metrics for temporal QA tasks. Code and data are available on https://github.com/aauss/temporal-answer-qa.

cs.CL↗

arXiv2025

A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems

Recent advances in large language models have sparked growing interest in AI agents capable of solving complex, real-world tasks. However, most existing agent systems rely on manually crafted configurations that remain static after deployment, limiting their ability to adapt to dynamic and evolving environments. To this end, recent research has explored agent evolution techniques that aim to automatically enhance agent systems based on interaction data and environmental feedback. This emerging direction lays the foundation for self-evolving AI agents, which bridge the static capabilities of foundation models with the continuous adaptability required by lifelong agentic systems. In this survey, we provide a comprehensive review of existing techniques for self-evolving agentic systems. Specifically, we first introduce a unified conceptual framework that abstracts the feedback loop underlying the design of self-evolving agentic systems. The framework highlights four key components: System Inputs, Agent System, Environment, and Optimisers, serving as a foundation for understanding and comparing different strategies. Based on this framework, we systematically review a wide range of self-evolving techniques that target different components of the agent system. We also investigate domain-specific evolution strategies developed for specialised fields such as biomedicine, programming, and finance, where optimisation objectives are tightly coupled with domain constraints. In addition, we provide a dedicated discussion on the evaluation, safety, and ethical considerations for self-evolving agentic systems, which are critical to ensuring their effectiveness and reliability. This survey aims to provide researchers and practitioners with a systematic understanding of self-evolving AI agents, laying the foundation for the development of more adaptive, autonomous, and lifelong agentic systems.

cs.AI↗

arXiv2025

Am I on the Right Track? What Can Predicted Query Performance Tell Us about the Search Behaviour of Agentic RAG

Agentic Retrieval-Augmented Generation (RAG) is a new paradigm where the reasoning model decides when to invoke a retriever (as a "tool") when answering a question. This paradigm, exemplified by recent research works such as Search-R1, enables the model to decide when to search and obtain external information. However, the queries generated by such Agentic RAG models and the role of the retriever in obtaining high-quality answers remain understudied. To this end, this initial study examines the applicability of query performance prediction (QPP) within the recent Agentic RAG models Search-R1 and R1-Searcher. We find that applying effective retrievers can achieve higher answer quality within a shorter reasoning process. Moreover, the QPP estimates of the generated queries, used as an approximation of their retrieval quality, are positively correlated with the quality of the final answer. Ultimately, our work is a step towards adaptive retrieval within Agentic RAG, where QPP is used to inform the model if the retrieved results are likely to be useful.

cs.IR↗

arXiv2025

Constructing and Evaluating Declarative RAG Pipelines in PyTerrier

Search engines often follow a pipeline architecture, where complex but effective reranking components are used to refine the results of an initial retrieval. Retrieval augmented generation (RAG) is an exciting application of the pipeline architecture, where the final component generates a coherent answer for the users from the retrieved documents. In this demo paper, we describe how such RAG pipelines can be formulated in the declarative PyTerrier architecture, and the advantages of doing so. Our PyTerrier-RAG extension for PyTerrier provides easy access to standard RAG datasets and evaluation measures, state-of-the-art LLM readers, and using PyTerrier's unique operator notation, easy-to-build pipelines. We demonstrate the succinctness of indexing and RAG pipelines on standard datasets (including Natural Questions) and how to build on the larger PyTerrier ecosystem with state-of-the-art sparse, learned-sparse, and dense retrievers, and other neural rankers.

cs.IR↗

arXiv2025

Grounding Chest X-Ray Visual Question Answering with Generated Radiology Reports

We present a novel approach to Chest X-ray (CXR) Visual Question Answering (VQA), addressing both single-image image-difference questions. Single-image questions focus on abnormalities within a specific CXR ("What abnormalities are seen in image X?"), while image-difference questions compare two longitudinal CXRs acquired at different time points ("What are the differences between image X and Y?"). We further explore how the integration of radiology reports can enhance the performance of VQA models. While previous approaches have demonstrated the utility of radiology reports during the pre-training phase, we extend this idea by showing that the reports can also be leveraged as additional input to improve the VQA model's predicted answers. First, we propose a unified method that handles both types of questions and auto-regressively generates the answers. For single-image questions, the model is provided with a single CXR. For image-difference questions, the model is provided with two CXRs from the same patient, captured at different time points, enabling the model to detect and describe temporal changes. Taking inspiration from 'Chain-of-Thought reasoning', we demonstrate that performance on the CXR VQA task can be improved by grounding the answer generator module with a radiology report predicted for the same CXR. In our approach, the VQA model is divided into two steps: i) Report Generation (RG) and ii) Answer Generation (AG). Our results demonstrate that incorporating predicted radiology reports as evidence to the AG model enhances performance on both single-image and image-difference questions, achieving state-of-the-art results on the Medical-Diff-VQA dataset.

cs.CV↗