ACL · 2026 · main-long
Kai Wei; Yuwen Cui; Kehan Shen; Hua Wei; Guangjing Wang
borderline
Terminal simulation, framed as a terminal command-level Turing test, is a long-standing problem of symbolic language generation in dialogue and interactive systems. Prior scripted simulators lack the flexibility needed for complex, multi-turn interactions, while LLM-based approaches often misinterpret commands, break output formats, drift from system state, and remain vulnerable to prompt injection. In this work, we propose MANTIS, a terminal simulation framework that improves realism, consistency, and robustness in command-language generation. MANTIS integrates a multi-agent architecture with a filter-based routing model that safely dispatches commands to external tools or an LLM-based agent, enabling support for interactive commands while defending against prompt injection attacks. In addition, we design an agentic file system with history pruning to preserve long-term state consistency. We release three datasets: 28,045 real terminal input-output pairs, a 1,000-session multi-turn interaction dataset, and a 25,849-instance labeled classification dataset. MANTIS outperforms state-of-the-art baselines by more than 9%, achieving over 95% accuracy on multi-turn terminal simulation. The dataset and source code are available at https://github.com/kaiwei666a/MANTIS_Terminal_Simulation
Screening rationale: MANTIS is an interactive multi-turn terminal simulation framework with agentic routing and state, but it is mainly simulator infrastructure rather than human-agent collaboration for analytical workflows.
ACL · 2026 · main-long
Keyu Li; Junhao Shi; Yang Xiao; Mohan Jiang; Jie Sun; Yunze Wu; Dayuan Fu; Shijie Xia; Xiaojie Cai; Tianze Xu; Weiye Si; Wenjie Li; Dequan Wang; Pengfei Liu
borderline
Large Language Models (LLMs) based autonomous agents demonstrate multifaceted capabilities to contribute substantially to economic production. However, existing benchmarks remain focused on single agentic capability, failing to capture long-horizon real-world scenarios. Moreover, the reliance on human-in-the-loop feedback for realistic tasks creates a scalability bottleneck, hindering automated rollout collection and evaluation. To bridge this gap, we introduce AgencyBench, a comprehensive benchmark derived from daily AI usage, evaluating 6 core agentic capabilities across 32 real-world scenarios, comprising 138 tasks with specific queries, deliverables, and rubrics. These scenarios require an average of 90 tool calls, 1 million tokens, and hours of execution time to resolve. To enable automated evaluation, we employ a user simulation agent to provide iterative feedback, and a Docker sandbox to conduct visual and functional rubric-based assessment. Experiments reveal that closed-source models significantly outperform open-source models (48.4% vs 32.1%). Further analysis reveals significant disparities across models in resource efficiency, feedback-driven self-correction, and specific tool-use preferences.
Screening rationale: Benchmark covers long-horizon real-world autonomous agent tasks with iterative feedback from a user simulation, but it is not data/graph focused and has limited real human collaboration.
ACL · 2026 · findings
Florian Baud; Feda Almuhisen; Dorian Midou
keep
Numerical data from sensors and time series are widely used in scientific research fields such as nuclear fusion experiments, which generate vast amounts of complex, high-dimensional data. Therefore, efficient numerical data analysis tools are crucial to accelerate experimental research. Large language models (LLMs) have emerged as promising solutions to analyze numerical data with natural language queries. However, LLMs have difficulties treating this type of data as they have been designed for text in the first place. To overcome these limitations, we propose a model-agnostic and data-agnostic agent that processes numerical data by code generation and multimodal reasoning. Our agent demonstrates competitive performance against baselines on benchmark data on numerical data tasks such as sensor data classification and time series understanding. While outperforming them on information retrieval benchmarks, also we have successfully applied our agent in the context of nuclear fusion research, where physicists and Tokamak operators interact with it to plan and analyze fusion experiments.
Screening rationale: Directly describes an agent for numerical data analysis used by physicists and operators through natural-language interaction in a real scientific workflow.
ACL · 2026 · main-long
Yuanfu Sun; Kang Li; Dongzhe Fan; Jiajin Liu; Qiaoyu Tan
keepRule kept (not LLM-scored)
Large Language Models (LLMs) increasingly rely on agentic capabilities—iterative retrieval, tool use, and decision-making—to overcome the limits of static, parametric knowledge. Yet existing agentic frameworks treat external information as unstructured text and fail to leverage the topological dependencies inherent in real-world data. To bridge this gap, we introduce Agentic Graph Learning (AGL), a paradigm that reframes graph learning as an interleaved process of topology-aware navigation and LLM-based inference. Specifically, we propose AgentGL, the first reinforcement learning (RL)–driven framework for AGL. AgentGL equips an LLM agent with graph-native tools for multi-scale exploration, regulates tool usage via search-constrained thinking to balance accuracy and efficiency, and employs a graph-conditioned curriculum RL strategy to stabilize long-horizon policy learning without step-wise supervision. Across diverse Text-Attributed Graph (TAG) benchmarks and multiple LLM backbones, AgentGL substantially outperforms strong GraphLLMs and GraphRAG baselines, achieving absolute improvements of up to 17.5% in node classification and 28.4% in link prediction. These results demonstrate that AGL is a promising frontier for enabling LLMs to autonomously navigate and reason over complex relational environments. The code is publicly available at https://github.com/sunyuanfu/AgentGL .
Screening rationale: Auto-kept due to high prefilter tier.
ACL · 2026 · findings
Fengran Mo; Yifan Gao; Sha Li; Hansi Zeng; Xin Liu; Zhaoxuan Tan; Xian Li; Jianshu Chen; Dakuo Wang; Meng Jiang
borderline
Large Language Models (LLMs) have become a popular interface for human–AI interaction, supporting information seeking and task assistance through natural, multi-turn dialogue. To respond to users within multi-turn dialogues, the context-dependent user intent evolves across interactions, requiring contextual interpretation, query reformulation, and dynamic coordination between retrieval and generation. Existing studies usually follow static “rewrite, retrieve, and generate” pipelines, which optimize different procedures separately and overlook the mixed-initiative action optimization simultaneously. Although the recent developments in deep search agents demonstrate the effectiveness in jointly optimizing retrieval and generation via reasoning, these approaches focus on single-turn scenarios, which might lack the ability to handle multi-turn interactions. We introduce a conversational agent that interleaves search and reasoning across turns, enabling exploratory and adaptive behaviors learned through reinforcement learning (RL) training with tailored rewards towards evolving user goals. The experimental results across four widely used conversational benchmarks demonstrate the effectiveness of our methods by surpassing several existing strong baselines.
Screening rationale: The paper focuses on multi-turn human-AI conversational search with mixed-initiative retrieval and reasoning, making it relevant to interaction paradigms despite weak data/graph workflow alignment.
ACL · 2026 · main-long
Zheyuan Zhang; Kaiwen Shi; Zhengqing Yuan; Zehong Wang; Tianyi Ma; Keerthiram Murugesan; Vincent Galassi; Chuxu Zhang; Yanfang Ye
borderline
Large language models (LLMs) and agent-based frameworks have advanced rapidly, enabling diverse applications. Yet, with the proliferation of models and agentic strategies, practitioners face substantial uncertainty in selecting the best configuration for a downstream task. Prior studies show that different agents and backbones exhibit complementary strengths, and that larger models are not always superior, underscoring the need for adaptive routing mechanisms. Existing approaches to agent routing, however, often emphasize cost efficiency while overlooking the fine-grained contextual and relational structure inherent in QA tasks. In this paper, we propose AgentRouter, a framework that formulates multi-agent QA as a knowledge-graph–guided routing problem supervised by empirical performance signals. Specifically, we convert QA instance into a heterogeneous knowledge graph that jointly encodes queries, contextual entities, and agents, and then train a heterogeneous graph neural network (GNN) to propagate information across node types and produce task-aware routing distributions over agents. By leveraging soft supervision and weighted aggregation of agent outputs, AgentRouter learns principled collaboration schemes that capture the complementary strengths of diverse agents. Extensive experiments demonstrate that our framework consistently outperforms single-agent and ensemble baselines, while generalizing across benchmarks and LLM backbones. These results highlight the effectiveness and robustness of graph-supervised multi-agent routing for question answering. Our code repo is available at https://anonymous.4open.science/r/AgentRouter.
Screening rationale: It combines knowledge graphs with multi-agent routing and collaboration for QA, but involves no human/user role or analytical workflow.
ACL · 2026 · findings
Yixuan Liu; Yicheng Zhang
borderline
The Science of Science (SciSci) examines how scientific knowledge is generated, evaluated, and transformed by utilizing large-scale scholarly and bibliometric data. As these data grow in scale and complexity, analysis has increasingly relied on statistical, network-based, machine learning methods, and is now seeing growing involvement of AI agents. This emerging class of such agents, ranging from multi-agent simulations of scientific behavior to tool-augmented systems for empirical analysis, is beginning to reshape how SciSci research is conducted. In this survey, we propose a task-centered taxonomy, distinguishing agents as simulations , which model citation, collaboration, and community dynamics, from agents as tools , which assist empirical analysis and scientific workflows. We review agent architectures, learning mechanisms, evaluation, and SciSci benchmarks, and examine open challenges related to reliability, data quality, and bias. Our survey aims to clarify the landscape of AI agents in SciSci and to support the development of reliable and scientifically useful AI systems for studying science and scientific communities.
Screening rationale: Survey covers AI agents as tools for empirical analysis and scientific workflows over scholarly, bibliometric, and network data, but human-agent collaboration is not central.
ACL · 2026 · findings
Chau Minh Pham; Zichao Wang; Puneet Mathur; Alexa Siu; Akriti Jain; Aparna Garimella; Ananya B. Sai; Nedim Lipka; Mohit Iyyer; Varun Manjunatha
borderline
Large language models are increasingly used to draft long-form multimodal documents, but their end-to-end performance on professional report generation remains systematically understudied. We introduce AnalystBench, a continually extensible benchmark of 20 real-world report generation tasks grounded in multimodal document collections, where models must process millions of input tokens to produce long-form professional reports. Using expert-validated quality checklists and groundedness evaluation, we evaluate LLMs and coding agents and find that the best model, GPT-5.1, scores highly on executive summarization tasks (exceeding 90% on quality checklists) but degrades substantially on tasks requiring long-horizon synthesis over large inputs (dropping to 25-40%). Agent-based generation substantially benefits strong closed-source models such as GPT-5.1, with checklist scores improving by 20.24 percentage points and visual coverage by 37.41 points over vanilla generation, but offers little or negative gains for open-source models like DeepSeek-R1 (-3.02 points). Expert reviewers note that while generated reports are grounded and clearly separate factual description from interpretation, they often fall short in actionability, clarity, and quantitative precision, which highlights the gap between system performance and real-world professional needs.
Screening rationale: AnalystBench addresses realistic professional report-generation workflows over large multimodal inputs with expert evaluation, but has limited human-agent interaction beyond benchmarking agents against professional needs.
ACL · 2026 · findings
Junyan Cheng; Ankit Srivastava; Jessie Zeng; Milenko Drinic; Jack W. Stokes
borderline
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 𝜌=0.685 ) and that users prefer Apeiron-synthesized apps over baselines.
Screening rationale: Addresses user-demand-driven app synthesis with persona simulation, interaction traces, CI/CD feedback, and a user study, making it relevant to agent workflow optimization though outside data/graph analysis.
ACL · 2026 · findings
Jiabin Tang; Tianyu Fan; Chao Huang
borderline
Large Language Model (LLM) Agents have demonstrated remarkable capabilities in task automation and intelligent decision-making, driving the widespread adoption of agent development frameworks such as LangChain and AutoGen. However, these frameworks predominantly serve developers with extensive technical expertise—a significant limitation considering that only 0.03% of the global population possesses the necessary programming skills. This stark accessibility gap raises a fundamental question: Can we enable everyone, regardless of technical background, to build their own LLM agents using natural language alone? To address this challenge, we introduce AutoAgent - a Fully-Automated and highly Self-Developing framework that enables users to create and deploy LLM agents through Natural Language Alone. Operating as an autonomous Agent Operating System, AutoAgent comprises four key components: i) Agentic System Utilities, ii) LLM-powered Actionable Engine, iii) Self-Managing File System, and iv) Self-Play Agent Customization module. This lightweight yet powerful system enables efficient and dynamic creation and modification of tools, agents, and workflows without coding requirements or manual intervention. Beyond its code-free agent development capabilities, AutoAgent also serves as a versatile multi-agent system for General AI Assistants. Comprehensive evaluations on the GAIA benchmark demonstrate AutoAgent’s effectiveness in generalist multi-agent tasks, surpassing existing state-of-the-art methods. Furthermore, AutoAgent’s Retrieval-Augmented Generation (RAG)-related capabilities have shown consistently superior performance compared to many alternative LLM-based solutions.
Screening rationale: Enables non-programmers to create and modify agents and workflows through natural language, making it relevant to user-agent interaction despite weak data/graph specificity.
ACL · 2026 · main-long
Joaquin Polonuer; Lucas Vittor; Iñaki Arango; Ayush Noori; David A. Clifton; Luciano Del Corro; Marinka Zitnik
borderline
Retrieving evidence for language model queries from knowledge graphs requires balancing broad search across the graph with multi-hop traversal to follow relational links. Similarity-based retrievers provide coverage but remain shallow, whereas traversal-based methods rely on selecting seed nodes to start exploration, which can fail when queries span multiple entities and relations. We introduce ARK: Adaptive Retriever of Knowledge, a tool-using KG retriever that gives a language model control over this breadth-depth tradeoff using a two-operation toolset: global lexical search over node descriptors and one-hop neighborhood exploration that composes into multi-hop traversal. ARK alternates between breadth-oriented discovery and depth-oriented expansion without depending on a fragile seed selection, a pre-set hop depth, or requiring retrieval training. ARK adapts tool use to queries, using global search for language-heavy queries and neighborhood exploration for relation-heavy queries.On STaRK, ARK reaches 59.1% average Hit@1 and 67.4 average MRR, improving average Hit@1 by up to 31.4% and average MRR by up to 28.0% over retrieval-based and agent-based training-free methods.Finally, we distill ARK’s tool-use trajectories from a large teacher into an 8B model via label-free imitation, improving Hit@1 by +7.0, +26.6, and +13.5 absolute points over the base 8B model on AMAZON, MAG, and PRIME datasets, respectively, while retaining up to 98.5% of the teacher’s Hit@1 rate.
Screening rationale: This is centrally about autonomous knowledge graph retrieval and exploration, but it has no meaningful human/user collaboration component.
ACL · 2026 · findings
Pollawat Hongwimol; Haoning Shang; Chutong Wang; Zhichao Wan; Yi Gao; Yuanming Li; Lin Gui; Wenhao Sun; Cheng Yu
borderline
Product attribute extraction in e-commerce is bottlenecked by ontologies that are inconsistent, incomplete, and costly to maintain. We present AutoPKG, a multi-agent Large Language Model (LLM) framework that automatically constructs a Product-attribute Knowledge Graph (PKG) from multimodal product content. AutoPKG induces product types and type-specific attribute keys on demand, extracts attribute values from text and images, and consolidates updates through a centralized decision agent that maintains a globally consistent canonical graph. We also propose an evaluation protocol for dynamic PKGs that measures type/key validity and consolidation quality, as well as edge-level accuracy for value assertions after canonicalization. On a large real-world marketplace catalog dataset from Lazada (Alibaba), AutoPKG achieves up to 0.953 Weighted Knowledge Efficiency (WKE) for product types, 0.724 WKE for attribute keys, and 0.531 edge-level F1 for multimodal value extraction. Across three public benchmarks, we improve edge-level exact-match F1 by 0.152 and yield a 0.208 precision gain on the attribute extraction application. Online A/B tests show that AutoPKG-derived attributes increase Gross Merchandise Value (GMV) in Badge (+3.81%), Search (+5.32%), and Recommendation (+7.89%), supporting AutoPKG’s practical value in production.
Screening rationale: Strong production knowledge-graph construction setting, but it is an automated multi-agent extraction framework with no user-facing collaboration or oversight layer.
ACL · 2026 · findings
Yen-Che Chien; Kuang-Da Wang; Wei-Yao Wang; Wen-Chih Peng
borderline
Recent advances in autonomous digital agents from industry (e.g., Manus AI and Gemini’s research mode) highlight their potential for structured tasks through autonomous decision-making and task decomposition, but it remains unclear how well such systems support real-world information-intensive workflows. We study this question in journalism, where newswriting requires iterative planning, contextual reasoning, and active discovery of missing background to produce a coherent article. We introduce NEWSAGENT, a benchmark for evaluating how agents search raw materials, select relevant information, and iteratively revise drafts through core journalistic functions. Given a writing instruction and partial firsthand materials, agents must identify narrative perspectives, issue keyword-based queries, retrieve historical context, and generate complete news articles. Unlike typical summarization or retrieval tasks, essential context is not directly available and must be actively discovered, reflecting real-world reporting constraints. NEWSAGENT consists of 6k human-verified examples derived from real news. We evaluate open- and closed-sourced LLMs with commonly-used agentic frameworks on NEWSAGENT, which shows that agents are capable of retrieving relevant facts but struggling with planning and narrative integration. We believe that NEWSAGENT serves a realistic testbed for iterating and evaluating agent capabilities in terms of web data manipulation to real-world productivity. The benchmark resources are publicly available at https://github.com/wywyWang/CoachAI-Projects .
Screening rationale: Realistic information-intensive journalistic workflow benchmark for agents, but it focuses on autonomous agent capability without human-agent collaboration.
ACL · 2026 · findings
Huangwei Chen; Wu Li; Junhao Jia; Yining Chen; Xiaotao Pang; Ya-Long Chen; Li Gonghui; Haishuai Wang; Jiajun Bu; Lei Wu
borderline
The initial outpatient consultation is critical for clinical decision-making, yet it is often conducted by a single physician under time pressure, making it prone to cognitive biases and incomplete evidence capture. Although the Multi-Disciplinary Team (MDT) reduces these risks, they are costly and difficult to scale to real-time intake. We propose Aegle, a synchronous virtual MDT framework that brings MDT-level reasoning to outpatient consultations via a graph-based multi-agent architecture. Aegle formalizes the consultation state using a structured SOAP representation, separating evidence collection from diagnostic reasoning to improve traceability and bias control. An orchestrator dynamically activates specialist agents, which perform decoupled parallel reasoning and are subsequently integrated by an aggregator into a coherent clinical note. Experiments on ClinicalBench and a real-world RAPID-IPN dataset across 24 departments and 53 metrics show that Aegle consistently outperforms state-of-the-art proprietary and open-source models in documentation quality and consultation capability.
Screening rationale: Describes collaborative agents for a realistic clinical consultation workflow, but the collaboration is agent-agent rather than human-agent and data/graph relevance is secondary.
ACL · 2026 · main-long
Jingsheng Zheng; Jintian Zhang; Yujie Luo; Yuren Mao; Yunjun Gao; Lun Du; Huajun Chen; Ningyu Zhang
borderline
Autonomous machine learning agents have revolutionized scientific discovery, yet they remain constrained by a Generate-Execute-Feedback paradigm. Previous approaches suffers from a severe Execution Bottleneck, as hypothesis evaluation relies strictly on expensive physical execution. To bypass these physical constraints, we internalize execution priors to substitute costly runtime checks with instantaneous predictive reasoning, drawing inspiration from World Models. In this work, we formalize the task of Data-centric Solution Preference and construct a comprehensive corpus of 18,438 pairwise comparisons. We demonstrate that LLMs exhibit significant predictive capabilities when primed with a Verified Data Analysis Report, achieving 61.5% accuracy and robust confidence calibration. Finally, we instantiate this framework in ForeAgent, an agent that employs a Predict-then-Verify loop, achieving a 6x acceleration in convergence while surpassing execution-based baselines by +6%.
Screening rationale: It concerns autonomous machine learning/data-analysis agents and a workflow-level predict-then-verify loop, but has no clear human/user interaction component.
ACL · 2026 · findings
Kuo Tian; Pengfei Sun; Zhen Wu; Junran Ding; Xinyu Dai
borderline
The autonomous synthesis of deep research reports represents a critical frontier for Large Language Models (LLMs), demanding sophisticated information orchestration and non-linear narrative logic. Current approaches rely on rigid predefined linear workflows, which cause error accumulation, preclude global restructuring from subsequent insights, and ultimately limit in-depth multimodal fusion and report quality. We propose CogGen, a Cognitively inspired recursive framework for deep research report Generation. Leveraging a Hierarchical Recursive Architecture to simulate cognitive writing, CogGen enables flexible planning and global restructuring. To extend this recursivity to multimodal content, we introduce Abstract Visual Representation (AVR): a concise intent-driven language that iteratively refines visual-text layouts without pixel-level regeneration overhead. We further present CLEF, a Cognitive Load Evaluation Framework, and curate a new benchmark from Our World in Data (OWID). Extensive experiments show CogGen achieves state-of-the-art results among open-source systems, generating reports comparable to professional analysts’ outputs and surpassing Gemini Deep Research. Our code and dataset will be publicly available upon publication.
Screening rationale: Automated research report generation from OWID data is adjacent to analytical workflows, but the metadata describes autonomous generation rather than human-agent interaction or division of labor.
ACL · 2026 · main-long
Qiuyuan Ai; Zenghuang Fu; Zhaoyang Li; Ping Jiang; Haoyu Wu; Jie Song; Guannan He
borderline
Scaling LLM-based agents to long-horizon deep research is constrained by the context-noise trade-off, where linear history accumulation degrades reasoning and dilutes fine-grained evidence. To address this, we introduce the Cognitive Scaffold, a factorized memory architecture that decouples the cognitive state into a Fluid Working Context for immediate reasoning and a persistent Knowledge Graph for long-term retention. Unlike unstructured summarization, our framework employs a Rejection Sampling Fine-Tuning (RFT) pipeline to crystallize saturated context into structured event snapshots, strictly enforcing atomic constraints to preserve numerical values and entities. During reasoning, a thought-driven dual-path retrieval mechanism enables the agent to proactively recover precise evidence. Empirical evaluations on Xbench-DeepSearch, BrowseComp-ZH, and GAIA demonstrate that Cognitive Scaffold consistently outperforms baselines, achieving 74.7% Avg@3 and 87.0% Pass@3 on Xbench-DeepSearch, 48.5% Avg@3 and 65.9% Pass@3 on BrowseComp-ZH, and 72.8% Avg@3 and 88.3% Pass@3 on GAIA, while reducing compression hallucinations to 5.3%. We open-source our codebase to facilitate future research.
Screening rationale: Relevant to agentic deep research and uses a persistent knowledge graph, but the paper appears centered on autonomous memory architecture rather than human-agent interaction.
ACL · 2026 · findings
Shukai Liu; Bo Jiang; Jian Yang; Yizhi LI; Jinyang Guo; Xianglong Liu; Bryan Dai
borderline
Agents based on large language models have recently shown strong potential on real-world software engineering (SWE) tasks that require long-horizon interaction with repository-scale codebases. However, most existing agents rely on append-only context maintenance or passively triggered compression heuristics, which often lead to context explosion, semantic drift, and degraded reasoning in long-running interactions. We propose Cat, a new context management paradigm that elevates context maintenance to a callable tool integrated into the decision-making process of agents. Cat formalizes a structured context workspace consisting of stable task semantics, condensed long-term memory, and high-fidelity short-term interactions, and enables agents to proactively compress historical trajectories into actionable summaries at appropriate milestones. To support context management for SWE-agents, we propose a trajectory-level supervision framework, CaT-Generator, based on an offline data construction pipeline that injects context-management actions into complete interaction trajectories. Using this framework, we train a context-aware model, SWE-Compressor. Experiments on SWE-Bench-Verified demonstrate that SWE-Compressor reaches a 57.6% solved rate and significantly outperforms ReAct-based agents and static compression baselines, while maintaining stable and scalable long-horizon reasoning under a bounded context budget.
Screening rationale: Addresses long-horizon software-agent context management in repository workflows, but lacks a meaningful human collaboration role and is not data/graph focused.
ACL · 2026 · main-long
Zisu Huang; Muzhao Tian; Xiaohua Wang; Jingwen Xu; Zhengkang Guo; Qi Qian; Kaitao Song; Jiakang Yuan; Changze Lv; Xiaoqing Zheng
keep
As LLM-based agents are increasingly used in long-term interactions, cumulative memory is critical for enabling personalization and maintaining stylistic consistency. However, most existing systems adopt an "all-or-nothing" approach to memory usage: incorporating all relevant past information can lead to Memory Anchoring, where the agent is trapped by past interactions, while excluding memory entirely results in under-utilization and the loss of important interaction history. We show that an agent’s reliance on memory can be modeled as an explicit and user-controllable dimension. We first introduce a behavioral metric of memory dependence to quantify the influence of past interactions on current outputs. We then propose Steerable Memory Agent, SteeM, a framework that allows users to dynamically regulate memory reliance, ranging from a fresh-start mode that promotes innovation to a high-fidelity mode that closely follows interaction history. Experiments across different scenarios demonstrate that our approach consistently outperforms conventional prompting and rigid memory masking strategies, yielding a more nuanced and effective control for personalized human-agent collaboration.
Screening rationale: The paper centrally studies user-controllable memory reliance in long-term human-agent interaction, making it useful for interaction paradigms despite lacking data/graph workflow focus.
ACL · 2026 · main-long
Yuhan Chen; Zizhuo Shen; Miaomiao Cheng; Xu Han; Jiefu Gong; Shijin Wang; Wei Song
borderline
Simulating student writing behavior offers a promising pathway to scalable feedback evaluation and teacher training. However, existing LLM-based approaches tend to model overly capable learners who readily understand and over-apply feedback, resulting in pedagogically implausible behavior. In this work, we introduce pedagogical realism as a guiding principle for student writing simulation, emphasizing bounded cognition, selective feedback comprehension, and developmentally plausible learning processes. To operationalize this idea, we propose CPT-Agent, a cognitively grounded framework that decouples cognitive ability from writing proficiency and models their interaction during writing and revision. CPT-Agent combines probabilistic modeling of cognitive development, proficiency-controlled text generation, and structured memory for skill accumulation. Experiments show that it (1) produces clearly distinguishable proficiency levels, (2) generates cognitively plausible revisions consistent with instructional theories, and (3) achieves strong agreement with expert judgments in evaluating feedback quality. These results highlight the importance of modeling cognitive constraints in LLM-based student simulation and demonstrate the potential of pedagogically realistic agents for automated feedback assessment and teacher development.
Screening rationale: CPT-Agent simulates student writing and feedback comprehension for teacher development, offering some relevance to agent-based educational workflows but little direct human-agent collaboration or data/graph analysis.
ACL · 2026 · findings
Hongze Mi; Yibo Feng; WenJie Lu; Yuqi Wang; Jinyuan Li; Song Cao; He Cui; Tengfei Tian; Xuelin Zhang; Haotian Luo; Di Sun; Jun Fang; Hua Chai; Naiqiang Tan; Gang Pan
borderline
Graphical User Interface (GUI) agents aim to automate a wide spectrum of human tasks by emulating user interaction. Despite rapid advancements, current approaches are hindered by several critical challenges: data bottleneck in end-to-end training, high cost of delayed error detection, and risk of contradictory guidance. Inspired by the human cognitive loop of Thinking, Alignment, and Reflection, we present D-Artemis—a novel deliberative framework in this paper. D-Artemis leverages a fine-grained, app-specific tip retrieval mechanism to inform its decision-making process. It also employs a proactive Pre-execution Alignment stage, where Thought-Action Consistency (TAC) Check module and Action Correction Agent (ACA) work in concert to mitigate the risk of execution failures. A post-execution Status Reflection Agent (SRA) completes the cognitive loop, enabling strategic learning from experience. Crucially, D-Artemis enhances the capabilities of general-purpose Multimodal large language models (MLLMs) for GUI tasks without the need for training on complex trajectory datasets, demonstrating strong generalization. D-Artemis achieves SOTA among open-source general models on AndroidWorld (75.8%) and ScreenSpot-V2 (96.8%). Extensive ablation studies further demonstrate the significant contribution of each proposed component.
Screening rationale: GUI agents emulate user interaction and include pre/post-execution alignment mechanisms, but the system is primarily autonomous task automation and not data or graph analysis.
ACL · 2026 · main-long
Yuqing Zhang; Honghui Sheng; Xueyu Hu; Shengyu Zhang; Fei Wu
borderline
Mobile GUI agents powered by LMMs can perceive screens and follow instructions, yet existing benchmarks largely target short, linear workflows and step-level accuracy, offering limited insight into long-horizon planning and decision-making under branching structures. We present DAC-Bench, a decision-aware benchmark with compositional tasks comprising 830 episodes and 11,345 action steps across 35 applications on Android and iOS. Tasks are organized into Sequential, Conjunctive, Conditional, and Hierarchical structures, reflecting real-world multi-step and branching interaction patterns. To complement standard step-level evaluation, we introduce weighted longest common subsequence to capture length-sensitive progress and decision accuracy for branch correctness. Evaluations across 7 diverse agents show substantial performance degradation compared to prior benchmarks, with success rates dropping below 5% on 6–8 step tasks and branch accuracy averaging 38%, highlighting challenges in conditional decision-making. By exposing these failure modes, DAC-Bench provides a challenging and diagnostic benchmark for advancing decision-aware mobile GUI agents. Our code and dataset are available at: https://github.com/YuqingZhangMirror12/DAC-Bench.
Screening rationale: DAC-Bench concerns mobile GUI agents in realistic multi-step branching app workflows, but lacks a meaningful human-agent collaboration framing and is not data/graph oriented.
ACL · 2026 · findings
Xiaochuan Liu; Yuanfeng Song; Xiaoming Yin; Xing Chen
borderline
In today’s data-driven era, fully automated end-to-end data analytics, particularly insight discovery, is critical for discovering actionable insights that assist organizations in making effective decisions. With the rapid advancement of large language models (LLMs), LLM-driven agents have emerged as a promising paradigm for automating insight discovery. However, existing data insight agents remain limited in several key aspects, often failing to deliver satisfactory results due to: (1) insufficient utilization of domain knowledge, (2) shallow analytical depth, and (3) error-prone code generation. To address these issues, we propose DataSage, a novel multi-agent framework that incorporates three innovative features including external knowledge retrieval to enrich the analytical context, a multi-role debating mechanism to simulate diverse analytical perspectives and deepen analytical depth, and multi-path reasoning to improve the accuracy of the generated code and insights. Extensive experiments on InsightBench demonstrate that DataSage consistently outperforms existing data insight agents across all difficulty levels, improving by 7.5% and 13.9% respectively in the insight-level and summary-level metrics. It offers an effective solution for automated data insight discovery.
Screening rationale: DataSage is directly about automated data analytics and insight discovery with multi-agent mechanisms, but it lacks a human/user collaboration component.
ACL · 2026 · findings
Dan Zhang; Sining Zhoubian; Min Cai; Fengzu Li; Lekang Yang; Wei Wang; Tianjiao Dong; Ziniu Hu; Jie Tang; Yisong Yue
borderline
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 .
Screening rationale: A data science LLM benchmark with human verification in ground-truth construction, but no clear user-agent interaction or collaborative workflow layer.