AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

ACL 2026

RiT: Rubrics-in-Thinking Reinforcement Learning for Improved Reasoning in Large Language Models

Xiaobin Tian, Shuai Yuan, Muyun Ding, Haonan Chen, Xiaoxi Jiang

Large Reasoning Models (LRMs) benefit from generating intermediate reasoning steps, enabling more reliable and interpretable decision-making. While outcome-based supervision has proven effective for LRMs across diverse tasks, it focuses solely on final answers and cannot guarantee high-quality intermediate reasoning. In contrast, existing process supervision is largely limited to verifiable domains such as mathematics or code, where intermediate steps can be explicitly checked, restricting its applicability to open-ended reasoning tasks. To address these limitations, we propose Rubrics-in-Thinking Reinforcement Learning (RiT), the first framework to introduce thinking-rubric supervision into intermediate reasoning. RiT automatically generates fine-grained rubrics and integrates them into a reward function via gated fusion with outcome-based rewards, guiding models to reason in a coherent and task-aligned manner, improving both intermediate steps and the final response. Experiments on reasoning-intensive and open-ended benchmarks demonstrate that RiT consistently outperforms outcome-only RL baselines.

ACL 2026

Travel on the ICD Tree: Benchmarking Agentic Reasoning for ICD Coding from Chinese Electronic Medical Records

Xinjie Xu, Yongqi Fan, Shuang-shuang Chen, Qi Ye, Weibin Guo, Xinxuan Hu

Accurate International Classification of Diseases (ICD) coding is crucial for hospital management and healthcare data governance. In clinical practice, straightforward cases can often be matched directly to ICD codes via diagnostic text, establishing retrieval-based methods as the baseline. More advanced approaches leverage large language models to rerank these results. However, real-world coding scenarios are typically more complex, demanding reasoning that goes beyond superficial descriptions. For instance, it involves synthesizing key information such as disease subtype, anatomical location, and complications from complex progress notes to accurately identify the primary diagnosis. However, a comprehensive evaluation framework for ICD coding based on complete EMRs is still lacking. To address these challenges, we constructed the Code4Detail dataset, which comprises 560 real clinical records covering 434 common diseases across 19 core chapters of ICD-10. To systematically explore the capability boundaries of large language models under different paradigms, we further propose the Travel on the ICD Tree (ToT-ICD) evaluation framework. Unlike the conventional retrieval-recall approach, ToT-ICD treats ICD coding as a structured exploration process across a hierarchical taxonomy. We design an agentic workflow that integrates similarity retrieval, path-guided navigation, and dynamic backtracking, enabling logical reasoning and decision-making under coding rules.

ACL 2026

LUMINA: Long-horizon Understanding for Multi-turn Interactive Agents

Amin Rakhsha, Thomas Hehn, Pietro Mazzaglia, Fabio Valerio Massoli, Arash Behboodi, Tribhuvanesh Orekondy

Large language models can perform well on many isolated tasks, yet they continue to struggle on multi-turn, long-horizon agentic problems that require skills such as planning, state tracking, and long context processing. In this work, we aim to better understand the relative importance of advancing these underlying capabilities for success on such tasks. We develop an oracle counterfactual framework for multi-turn problems that asks: how would an agent perform if it could leverage an oracle to perfectly execute a specific skill? The change in the agent’s performance due to this oracle assistance allows us to measure the criticality of that skill in the future advancement of AI agents. We introduce a suite of procedurally generated, game-like tasks with tunable complexity. These controlled environments allow us to provide precise oracle interventions, such as perfect planning or flawless state tracking, and make it possible to isolate the contribution of each oracle without confounding effects present in real-world benchmarks. Our results show that while some interventions (e.g., planning) consistently improve performance across settings, the usefulness of other skills is dependent on the properties of the environment and language model. Our work sheds light on the challenges of multi-turn agentic environments to guide the future efforts in the development of AI agents and language models.

ACL 2026

Eval-RAR: Evaluation-Driven Retrieval-Augmented Reasoning via Reinforcement Learning

Heng Yu, Rui Li, Qi Liu, Wenjun Feng, Junfeng Kang, Yi Zhan

Retrieval-augmented generation (RAG) effectively extends the knowledge boundaries of large language models (LLMs) for complex tasks, yet current paradigms typically optimize for an interleaving of reasoning and retrieval, where models fail to critically evaluate retrieved information against the target question. Most existing methods rely on sparse outcome-based rewards, failing to provide explicit supervision for the internal reasoning process or to diagnose information inadequacy. To address this, we propose Eval-RAR, an Evaluation-driven Retrieval-Augmented Reasoning framework. Eval-RAR introduces a “Search-then-Evaluate” paradigm where the model performs explicit self-evaluation after each search step, generating a rationale to either identify sufficient evidence or specify missing information to guide subsequent queries. To optimize this process, we employ reinforcement learning with a fine-grained evaluation reward, providing intermediate feedback that encourages the model to track core entities and maintain logical consistency. Experiments on seven single-hop and multi-hop QA benchmarks demonstrate that Eval-RAR outperforms existing methods.

ACL 2026

Apeiron: A Scalable LLM-agentic Framework for Autonomous Full-lifecycle Demand-optimized Application Synthesis

Junyan Cheng, Ankit Srivastava, Jessie Zeng, Milenko Drinic, Jack W Stokes

We introduce Apeiron, a scalable and extensible framework for addressing amorphous user demands through autonomous, full-lifecycle application synthesis. Apeiron models the unstructured app development process as a heuristic optimization problem combining (i) a Computer-Use Agent (CUA) evaluator that simulates personas and demands, (ii) an Activity Tracer that grounds feedback in code-level interaction traces, and (iii) a Locality Controller that constrains changes during continuous integration and delivery (CI/CD). Furthermore, we introduce an innovative data generation approach using CUA-as-a-Judge to tackle data scarcity. Across 300 app scenarios, 2,400 personas, and 46,338 demands, Apeiron outperformed baselines by 10.7% in CUA ratings and 27.8% in user-demand task scores. The optimization process enhances task scores by 64.7%, and the tracer contributes a 25.1% gain. In CI/CD, Apeiron effectively restores 96.9% of the pre-shift mean CUA rating in one optimization step with <30% code changes in response to 30% demand shifts. Finally, a user study (N=18) shows that our CUA ratings strongly correlate with human judgment (Spearman’s \rho=0.685) and that users prefer Apeiron-synthesized apps over baselines.

ACL 2026

FinMRAGBench: A Realistic and Complex Benchmark for Multi-Modal RAG in Financial Document Analysis

Shouqing Yang, Qi Zhang, Yuhang Yang, Ruikang Xu, Yuwei Hou, Zhulin Jia, Lirong Gao, Haobo Wang, Jinglei Chen, Jiexiang Wang, Sheng Guo, Bo Zheng, Gang Chen

Retrieval-augmented generation (RAG) has become a widely adopted paradigm for realistic financial analysis over financial documents. However, existing benchmarks fail to capture realistic financial analysis settings that involve cross-document retrieval, multi-page evidence integration, and diverse analytical tasks. To address this gap, we introduce \textbf{FinMRAGBench}, a comprehensive multi-modal financial RAG benchmark in which most questions require retrieving evidence scattered across multiple pages and documents, constructed from large-scale real-world annual reports and comprising 887 expert-verified QA pairs spanning five representative financial analysis tasks. Moreover, we introduce \textbf{FinMRAGAgent}, an agent trained on high-quality agentic trajectories following the reasoning-and-acting (ReAct) paradigm, capable of dynamic tool invocation and multi-step financial analysis. Our extensive experiments show that current multi-modal RAG systems still struggle with incomplete retrieval and complex financial reasoning. In contrast, FinMRAGAgent achieves the strongest overall performance across all models, demonstrating that our structured reasoning approach significantly enhances multi-modal RAG in realistic financial scenarios. The code and data are available at https://github.com/sqyangit/FinMRAGBench.

ACL 2026

EVGeoQA: Benchmarking LLMs on Dynamic, Multi-Objective Geo-Spatial Exploration

Jianfei Wu, Zhichun Wang, Zhensheng Wang, Zhiyu He

While Large Language Models (LLMs) demonstrate remarkable reasoning capabilities, their potential for purpose-driven exploration in dynamic geo-spatial environments remains under-investigated. Existing Geo-Spatial Question Answering (GSQA) benchmarks predominantly focus on static retrieval, failing to capture the complexity of real-world planning that involves dynamic user locations and compound constraints. To bridge this gap, we introduce EVGeoQA, a novel benchmark built upon Electric Vehicle (EV) charging scenarios that features a distinct location-anchored and dual-objective design. Specifically, each query in EVGeoQA is explicitly bound to a user’s real-time coordinate and integrates the dual objectives of a charging necessity and a co-located activity preference. To systematically assess models in such complex settings, we further propose GeoRover, a general evaluation framework based on a tool-augmented agent architecture to evaluate the LLMs’ capacity for dynamic, multi-objective exploration. Our experiments reveal that while LLMs successfully utilize tools to address sub-tasks, they struggle with long-range spatial exploration. Notably, we observe an emergent capability: LLMs can summarize historical exploration trajectories to enhance exploration efficiency. These findings establish EVGeoQA as a challenging testbed for future geo-spatial intelligence. The dataset and prompts are available at https://github.com/Hapluckyy/EVGeoQA/.

ACL 2026

Intrinsic Mutual Information as a Modulator for Preference Optimization

Peng Liao, Peijia Zheng, Lingbo Li, Shangsong Liang, Lin Chen

Offline preference optimization methods, such as Direct Preference Optimization (DPO), offer significant advantages in aligning Large Language Models (LLMs) with human values. However, achieving optimal performance with these methods typically involves additional hyperparameter tuning, resulting in substantial time overhead. Although prior work has proposed a range of improvements, these methods remain limited in effectiveness and have not fully eliminated reliance on hyperparameter tuning. In this work, we introduce RMiPO, a lightweight and efficient framework for offline preference optimization. RMiPO leverages intrinsic Response-level Mutual information for Preference Optimization with hyperparameter modulation, dynamically decoupling preference contributions at negligible additional computational cost. Extensive experimental results demonstrate that RMiPO achieves consistently superior performance over existing methods while reducing training overhead by more than 15%. Our code is available at https://github.com/liavonpenn/rmipo.

ACL 2026

A3: Android Agent Arena for Mobile GUI Agents with Essential-State Procedural Evaluation

Yuxiang Chai, Shunye Tang, Han Xiao, Weifeng Lin, Hanhao Li, Jiayu Zhang, Liang Liu, Pengxiang Zhao, Guangyi Liu, Guozhi Wang, Shuai Ren, Rongduo Han, Haining Zhang, Siyuan Huang, Hongsheng Li

The advancement of Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) has catalyzed the development of mobile graphic user interface (GUI) AI agents, which is designed to autonomously perform tasks on mobile devices. However, a significant gap persists in mobile GUI agent evaluation, where existing benchmarks predominantly rely on either static frame assessments such as AndroidControl or offline static apps such as AndroidWorld and thus fail to capture agent performance in dynamic, real-world online mobile apps. To address this gap, we present Android Agent Arena (A3), a novel “essential-state” based procedural evaluation system for mobile GUI agents. A3 introduces a benchmark of 100 tasks derived from 20 widely-used, dynamic online apps across 20 categories from the Google Play Store, ensuring evaluation comprehension. A3 also presents a novel “essential-state” based procedural evaluation method that leverages MLLMs as reward models to progressively verify task completion and process achievement. This evaluation approach address the limitations of traditional function based evaluation methods on online dynamic apps. Furthermore, A3 includes a toolkit to streamline Android device interaction, reset online environment and apps and facilitate data collection from both human and agent demonstrations. The complete A3 system, including the benchmark and tools, will be publicly released to provide a robust foundation for future research and development in mobile GUI agents.

ACL 2026

Momoka-RAG: MCTS-Organized Mapping of Knowledge Associations for Long-Document Retrieval Augmented Generation

Wenyu Tao, Xiaofen Xing, Zeliang Li, Xiangmin Xu

Existing frameworks remain trapped in a passive and mechanical approach in constructing knowledge structure, which only allows them to uncover superficial associations between chunks while lacking proactive exploration of deeper semantic relationships among them. To address the aforementioned issues, we propose Momoka-RAG (MCTS-Organized Mapping of Knowledge Associations for Long-Document Retrieval Augmented Generation). It employs the Momoka-Map to utilize Monte Carlo Tree Search (MCTS) to proactively uncover connections among chunks and construct optimal semantic information paths with the objective of completing semantic relationships. On this basis, the Momoka-Trail Retriever further expands and filters the chunk candidate pool to retrieve the chunks most relevant to the query. Experiments on datasets including Dragonball, SQUAD, NFCORPUS, SCI-DOCS, HotpotQA, and TriviaQA demonstrate that for long-document retrieval tasks, our framework achieves higher precision while maintaining competitive recall compared to other RAG frameworks.

ACL 2026

PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoning

Wenfeng Feng, Penghong Zhao, Guochao Jiang, Chuzhan Hao, Guohua Liu, Yuewei Zhang

Grouping-based methods have emerged as a significant frontier in Reinforcement Learning (RL), yet agentic reasoning poses a fundamental challenge for grouping-based methods: frequent environmental interactions and multi-step tool invocation generate highly variable trajectories, rendering intra-group advantage estimation unstable. In response, practitioners resort to excessive rollouts to stabilize training, which in turn incurs prohibitive computational costs. This negative feedback loop between advantage estimation instability and sampling inefficiency severely limits learning performance. We present PVPO, a stable and efficient critic-free RL framework that breaks this cycle through a pre-estimated value baseline and pre-sampled data filtering. Specifically, before training begins, PVPO performs a single round of rollouts to compute two signals: (1) Static V, a Monte Carlo estimate of the expected return that serves as a fixed baseline to stabilize advantage estimation; and (2) sample-level accuracy, as a difficulty metric to filter out trivial samples and inject ground-truth trajectories into hard ones, thereby enhancing training efficiency. As shown in Figure 1, experiments demonstrate that PVPO outperforms other grouping-based methods in both multi-step retrieval tasks and advanced mathematical reasoning benchmarks. Notably, our 7B model trained with PVPO matches or exceeds the performance of large language models (LLMs). Moreover, PVPO achieves a 2.5x speedup in training time compared to prior methods while maintaining comparable final performance.

ACL 2026

DataSciBench: An LLM Agent Benchmark for Data Science

Dan Zhang, Sining Zhoubian, Min Cai, Fengzu Li, Lekang Yang, Wei Wang, Tianjiao Dong, Ziniu Hu, Jie Tang, Yisong Yue

This paper presents DataSciBench, a comprehensive benchmark for evaluating Large Language Models (LLMs) in data science. Unlike existing benchmarks limited to single task, simple evaluation metrics, and readily available ground truth (GT), DataSciBench is built on curated, natural, and challenging prompts with complex evaluation criteria and uncertain GT. To bridge the gap, we develop a semi-automated GT generation pipeline, integrating LLM-based self-consistency and human verification to ensure accuracy, predefined task types, and aggregate functions (metrics). Furthermore, we introduce an innovative Intention-Function-Code (IFC) framework, assessing code execution outcomes through metrics and programmatic rules. Evaluating 26 models (8 API-based, 8 open-source general, 9 code generation, and 1 agentic models), our approach offers rigorous insights into LLM strengths and weaknesses. Experimental results show API-based models outperform open-source counterparts across all metrics, with DeepAnalyze-8B leading among open-sourced models. We release all code and data at https://github.com/THUDM/DataSciBench.

ACL 2026

SEAD: Self-Evolving Agent for Multi-Turn Service Dialogue

Yuqin Dai, Ning Gao, Wei Zhang, Jie Wang, Luozichen, Ruiyuan Wu, Jinpeng Wang, Chaozheng Wang

Large Language Models (LLMs) have demonstrated remarkable capabilities in open-domain dialogues. However, their performance in service dialogues remains suboptimal, as these require agents to guide users toward specific business objectives while dynamically tracking states and adapting strategies. This gap stems from the scarcity of high-quality training data and the difficulty in simulating authentic, goal-oriented user behaviors. We propose SEAD (Self-Evolving Agent for Service Dialogue), a framework that enables agents to learn effective strategies without large-scale human annotations. SEAD decouples user modeling into two components: a Profile Controller that generates diverse user states to manage training curriculum, and a User Simulator that focuses on realistic role-playing. This design ensures the environment provides adaptive training scenarios rather than acting as an unfair adversary.

ACL 2026

Memory Dial: A Training Framework for Controllable Memorization in Language Models

Xiangbo Zhang, Ali Emami

Memorization in language models is widely studied but remains difficult to isolate and control. Understanding when and what models memorize is essential for explaining their predictions, yet existing approaches are post-hoc: they can detect memorization in trained models, but cannot disentangle its effects from architecture, data, or optimization. We introduce Memory Dial, a training framework that makes memorization an explicit, controllable variable. Memory Dial interpolates between standard cross-entropy and a temperature-sharpened objective via a single parameter, producing a family of models identical in architecture, data, and optimization, but varying in memorization pressure. Experiments across six architectures and five benchmarks demonstrate that: (1) reliably controls memorization, with seen-example accuracy increasing monotonically while unseen accuracy remains stable; (2) larger models are more responsive to memorization pressure; and (3) frequent sequences are easier to memorize than rare ones. Memory Dial provides a controlled experimental framework for studying how memorization behavior emerges and interacts with generalization in language models.

ACL 2026

Towards Reliable Paper Contributions Annotation in the ACL Rolling Review

Julien Aubert-Béduchaud, Florian Boudin, Akiko Aizawa, Béatrice Daille, Richard Dufour

With the rapid growth of scientific publications, researchers struggle to efficiently assess the relevance of numerous papers. Identifying the types of contributions an article makes can help readers quickly grasp its significance. The ACL Rolling Review (ARR) introduced a typology requiring authors to specify their contributions to improve review quality and fairness. However, the current typology lacks clear definitions and guidance, leading to inconsistent labeling and raising concerns about its reliability.Our re-annotation campaign reveals substantial disagreement between authors and domain experts. Moreover, the predictions of large language models (LLMs), when compared with expert annotations, tend to be close to those provided by the authors. These findings suggest a potential path toward better annotation reliability within the ARR process.

ACL 2026

Subgraph-Guided Executable Logical Form Generation for Knowledge Base Question Answering

Yuhang Tian, Dandan Song, Zhijing Wu, Changzhi Zhou, Jun Yang, Huipeng Ma, Chenhao Li, Luan Zhang, Yading Li, Xudong Li, Shenxi Liu, Jing Jiang

Large Language Models (LLMs) have shown great potential in Knowledge Base Question Answering (KBQA) via semantic parsing. However, existing retrieval-augmented approaches typically retrieve entities and relations in isolation based solely on semantic similarity, ignoring the structural information of the Knowledge Base (KB) and the question. To address this limitation, we propose SELF-KBQA (Subgraph-Guided Executable Logical Form Generation), a novel framework that empowers LLMs to generate logical forms conditioned on structurally aligned and semantically relevant subgraphs. Specifically, we introduce a structure-aware subgraph retrieval stage that ranks candidate subgraphs by aligning them with the question’s structure, along with semantic relevance. Subsequently, we employ a token-budgeted evidence condensation strategy to distill the top-ranked subgraphs into compact contexts for the generation stage. Extensive experiments on GrailQA, WebQSP, and GraphQuestions demonstrate that SELF-KBQA achieves state-of-the-art performance.

ACL 2026

HeteroRAG: A Heterogeneous Retrieval-Augmented Generation Framework for Medical Vision Language Tasks

Zhe Chen, Yusheng Liao, Zhiyuan Zhu, Haolin Li, Hongcheng Liu, Yanfeng Wang, Yu Wang

Medical large vision-language Models (Med-LVLMs) have shown promise in clinical applications but suffer from factual inaccuracies and unreliable outputs, posing risks in real-world diagnostics. While RAG has emerged as a potential solution, current medical multimodal RAG systems are unable to perform effective retrieval across heterogeneous sources. The irrelevance of retrieved reports undermines the factuality of analysis, while insufficient knowledge affects the credibility of clinical decision-making. To bridge the research gap, we construct MedAtlas, which includes extensive multimodal report repositories and diverse text corpora. Based on it, we present HeteroRAG, a novel framework that enhances Med-LVLMs through heterogeneous knowledge sources. The framework introduces Modality-specific CLIPs for effective report retrieval and a Multi-corpora Query Generator for tailoring queries to diverse corpora. Incorporating knowledge from such multifaceted sources, Heterogeneous Knowledge Preference Tuning is performed to achieve cross-modality and multi-source knowledge alignment. Extensive experiments across 11 datasets and 3 modalities demonstrate that HeteroRAG achieves state-of-the-art performance in most medical vision language benchmarks, significantly improving factual accuracy and reliability of Med-LVLMs.

ACL 2026

UCGRec: User-Centric Graph Learning for LLM-based Sequential Recommendation

HanBeul Kim, CheolWon Na, Suyoung Bae, YunSeok Choi, Jee-Hyong Lee

Recently, Large Language Models (LLM) have emerged as a promising paradigm for sequential recommendation. In sequential recommendation, effectively integrating diverse user preferences is essential for improving LLM performance, as users often exhibit multiple interests across different contexts. However, most existing LLM-based methods rely primarily on item descriptions or utilize user preferences independently. As a result, they overlook the relationships among preferences and fail to filter out less-relevant items that introduce noise. This makes it difficult to accurately capture the user’s interests, leading to suboptimal recommendations. To overcome these limitations, we propose UCGRec (User-Centric Graph Learning for LLM-based Sequential Recommendation), a novel method that effectively integrates diverse user-relevant preference signals into a unified user-centric graph. Then, we inject the graph-based knowledge into the LLM through end-to-end training with graph neural networks. We conduct extensive experiments on four widely used sequential real-world recommendation datasets. Our experimental results demonstrate that UCGRec significantly outperforms conventional and state-of-the-art LLM-based methods.

ACL 2026

ModularMoE: Fast LLM Customization with Parameter-Sharing Mixture-of-Experts for Low-Resource Settings

Jiaxing Liu, Qi Qi, Haifeng Sun, Dunjun Li, Zirui Zhuang, Bo He, Xiang Yang, Cong Liu, Jianxin Liao, Jingyu Wang

The massive size of Large Language Models (LLMs) imposes substantial computational and storage burdens, particularly on devices with limited hardware resources. Compared to foundation models, smaller and more specialized models are often more suitable for practical deployment. Existing customization approaches, such as the conventional “prune-then-finetune” paradigm or task-agnostic deployment strategies, either incur excessive computational costs or lead to suboptimal task performance. The recently popular Mixture-of-Experts (MoE) architecture exhibits a strong ability to mitigate inter-task interference, offering a new perspective on model deployment. In this paper, we introduce ModularMoE, a training framework that converts pre-trained LLMs into parameter-sharing MoE models for lightweight deployment. Exploiting the emergent modularity within LLMs, we split the feed-forward layers into multiple disjoint modules. Each expert is then constructed as a combination of such modules, enabling knowledge sharing across experts and thereby improving parameter efficiency within MoEs. Extensive experiments across multiple downstream tasks demonstrate that ModularMoE outperforms other state-of-the-art baselines at the same sparsity level, achieving an average performance improvement of 4.10% to 28.75% while delivering up to 2.71× inference speedup.

ACL 2026

Know Thy Enemy: Securing LLMs Against Prompt Injection via Diverse Data Synthesis and Instruction-Level Chain-of-Thought Learning

Zhiyuan Chang, Mingyang Li, Yuekai Huang, Ziyou Jiang, Xiaojun Jia, Qian Xiong, Junjie Wang, Zhaoyang Li, Qing Wang

Large language model (LLM)-integrated applications have become increasingly prevalent, yet face critical security vulnerabilities from prompt injection (PI) attacks. Defending against PI attacks faces two major issues: malicious instructions can be injected through diverse vectors, and injected instructions often lack clear semantic boundaries from the surrounding context, making them difficult to identify. To address these issues, we propose InstruCoT, a model enhancement method for PI defense that synthesizes diverse training data and employs instruction-level chain-of-thought fine-tuning, enabling LLMs to effectively identify and reject malicious instructions regardless of their source or position in the context. We evaluate InstruCoT across three critical dimensions: Behavior Deviation, Privacy Leakage, and Harmful Output. Experimental results across four LLMs demonstrate that InstruCoT significantly outperforms baselines in all dimensions while maintaining utility performance without degradation.

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.