As coding agents are increasingly deployed in large codebases, the need to automatically design challenging, codebase-level evaluation is central. We propose Gistify, a task where a coding LLM must create a single, minimal, self-contained file that can reproduce a specific functionality of a codebase. The coding LLM is given full access to a codebase along with a specific entrypoint (e.g., a python command), and the generated file must replicate the output of the same command ran under the full codebase, while containing only the essential components necessary to execute the provided command. Success on Gistify requires both structural understanding of the codebase, accurate modeling of its execution flow as well as the ability to produce potentially large code patches. Our findings show that current state-of-the-art models struggle to reliably solve Gistify tasks, especially ones with long executions traces.
Keeping software systems up to date is essential to avoid technical debt, security vulnerabilities, and the rigidity typical of legacy systems. However, updating libraries and frameworks remains a time consuming and error-prone process. Recent advances in Large Language Models (LLMs) and agentic coding systems offer new opportunities for automating such maintenance tasks. In this paper, we evaluate the update of a well-known Python library, SQLAlchemy, across a dataset of ten client applications. For this task, we use the Github's Copilot Agent Mode, an autonomous AI systema capable of planning and executing multi-step migration workflows. To assess the effectiveness of the automated migration, we also introduce Migration Coverage, a metric that quantifies the proportion of API usage points correctly migrated. The results of our study show that the LLM agent was capable of migrating functionalities and API usages between SQLAlchemy versions (migration coverage: 100%, median), but failed to maintain the application functionality, leading to a low test-pass rate (39.75%, median).
Multi-page visual documents such as manuals, brochures, presentations, and posters convey key information through layout, colors, icons, and cross-slide references. While large language models (LLMs) offer opportunities in document understanding, current systems struggle with complex, multi-page visual documents, particularly in fine-grained reasoning over elements and pages. We introduce SlideAgent, a versatile agentic framework for understanding multi-modal, multi-page, and multi-layout documents, especially slide decks. SlideAgent employs specialized agents and decomposes reasoning into three specialized levels-global, page, and element-to construct a structured, query-agnostic representation that captures both overarching themes and detailed visual or textual cues. During inference, SlideAgent selectively activates specialized agents for multi-level reasoning and integrates their outputs into coherent, context-aware answers. Extensive experiments show that SlideAgent achieves significant improvement over both proprietary (+7.9 overall) and open-source models (+9.8 overall).
The electricity sector transition requires substantial increases in residential demand response capacity, yet Home Energy Management Systems (HEMS) adoption remains limited by user interaction barriers requiring translation of everyday preferences into technical parameters. While large language models have been applied to energy systems as code generators and parameter extractors, no existing implementation deploys LLMs as autonomous coordinators managing the complete workflow from natural language input to multi-appliance scheduling. This paper presents an agentic AI HEMS where LLMs autonomously coordinate multi-appliance scheduling from natural language requests to device control, achieving optimal scheduling without example demonstrations. A hierarchical architecture combining one orchestrator with three specialist agents uses the ReAct pattern for iterative reasoning, enabling dynamic coordination without hardcoded workflows while integrating Google Calendar for context-aware deadline extraction. Evaluation across three open-source models using real Austrian day-ahead electricity prices reveals substantial capability differences. Llama-3.3-70B successfully coordinates all appliances across all scenarios to match cost-optimal benchmarks computed via mixed-integer linear programming, while other models achieve perfect single-appliance performance but struggle to coordinate all appliances simultaneously. Progressive prompt engineering experiments demonstrate that analytical query handling without explicit guidance remains unreliable despite models' general reasoning capabilities. We open-source the complete system including orchestration logic, agent prompts, tools, and web interfaces to enable reproducibility, extension, and future research.
While Multi-Agent Systems (MAS) excel at complex tasks, their growing autonomy with operational complexity often leads to critical inefficiencies, such as excessive token consumption and failures arising from misinformation. Existing methods primarily focus on post-hoc failure attribution, lacking proactive, real-time interventions to enhance robustness and efficiency. To this end, we introduce SupervisorAgent, a lightweight and modular framework for runtime, adaptive supervision that operates without altering the base agent's architecture. Triggered by an LLM-free adaptive filter, SupervisorAgent intervenes at critical junctures to proactively correct errors, guide inefficient behaviors, and purify observations. On the challenging GAIA benchmark, SupervisorAgent reduces the token consumption of the Smolagent framework by an average of 29.45% without compromising its success rate. Extensive experiments across five additional benchmarks (math reasoning, code generation, and question answering) and various SoTA foundation models validate the broad applicability and robustness of our approach. The code is available at https://github.com/LINs-lab/SupervisorAgent.
Reinforcement Learning with Verifiable Rewards (RLVR) is a promising approach for enhancing agentic deep search. However, its application is often hindered by low \textbf{Reward Density} in deep search scenarios, where agents expend significant exploratory costs for infrequent and often null final rewards. In this paper, we formalize this challenge as the \textbf{Reward Density Optimization} problem, which aims to improve the reward obtained per unit of exploration cost. This paper introduce \textbf{InfoFlow}, a systematic framework that tackles this problem from three aspects. 1) \textbf{Subproblem decomposition}: breaking down long-range tasks to assign process rewards, thereby providing denser learning signals. 2) \textbf{Failure-guided hints}: injecting corrective guidance into stalled trajectories to increase the probability of successful outcomes. 3) \textbf{Dual-agent refinement}: employing a dual-agent architecture to offload the cognitive burden of deep exploration. A refiner agent synthesizes the search history, which effectively compresses the researcher's perceived trajectory, thereby reducing exploration cost and increasing the overall reward density. We evaluate InfoFlow on multiple agentic search benchmarks, where it significantly outperforms strong baselines, enabling lightweight LLMs to achieve performance comparable to advanced proprietary LLMs.
Purpose: The purpose of this study was to determine if an ensemble of multiple LLM agents could be used collectively to provide a more reliable assessment of a pixel-based AI triage tool than a single LLM. Methods: 29,766 non-contrast CT head exams from fourteen hospitals were processed by a commercial intracranial hemorrhage (ICH) AI detection tool. Radiology reports were analyzed by an ensemble of eight open-source LLM models and a HIPAA compliant internal version of GPT-4o using a single multi-shot prompt that assessed for presence of ICH. 1,726 examples were manually reviewed. Performance characteristics of the eight open-source models and consensus were compared to GPT-4o. Three ideal consensus LLM ensembles were tested for rating the performance of the triage tool. Results: The cohort consisted of 29,766 head CTs exam-report pairs. The highest AUC performance was achieved with llama3.3:70b and GPT-4o (AUC= 0.78). The average precision was highest for Llama3.3:70b and GPT-4o (AP=0.75 & 0.76). Llama3.3:70b had the highest F1 score (0.81) and recall (0.85), greater precision (0.78), specificity (0.72), and MCC (0.57). Using MCC (95% CI) the ideal combination of LLMs were: Full-9 Ensemble 0.571 (0.552-0.591), Top-3 Ensemble 0.558 (0.537-0.579), Consensus 0.556 (0.539-0.574), and GPT4o 0.522 (0.500-0.543). No statistically significant differences were observed between Top-3, Full-9, and Consensus (p > 0.05). Conclusion: An ensemble of medium to large sized open-source LLMs provides a more consistent and reliable method to derive a ground truth retrospective evaluation of a clinical AI triage tool over a single LLM alone.
Online social networks have transformed the ways in which political mobilization messages are disseminated, raising new questions about how peer influence operates at scale. Building on the landmark 61-million-person Facebook experiment \citep{bond201261}, we develop an agent-based simulation framework that integrates real U.S. Census demographic distributions, authentic Twitter network topology, and heterogeneous large language model (LLM) agents to examine the effect of mobilization messages on voter turnout. Each simulated agent is assigned demographic attributes, a personal political stance, and an LLM variant (\texttt{GPT-4.1}, \texttt{GPT-4.1-Mini}, or \texttt{GPT-4.1-Nano}) reflecting its political sophistication. Agents interact over realistic social network structures, receiving personalized feeds and dynamically updating their engagement behaviors and voting intentions. Experimental conditions replicate the informational and social mobilization treatments of the original Facebook study. Across scenarios, the simulator reproduces qualitative patterns observed in field experiments, including stronger mobilization effects under social message treatments and measurable peer spillovers. Our framework provides a controlled, reproducible environment for testing counterfactual designs and sensitivity analyses in political mobilization research, offering a bridge between high-validity field experiments and flexible computational modeling.\footnote{Code and data available at https://github.com/CausalMP/LLM-SocioPol}
While a multi-agent approach based on large language models (LLMs) represents a promising strategy to surpass the capabilities of single models, its success is critically dependent on synergistic team composition. However, forming optimal teams is a significant challenge, as the inherent opacity of most models obscures the internal characteristics necessary for effective collaboration. In this paper, we propose an interaction-centric framework for automatic team composition that does not require any prior knowledge including their internal architectures, training data, or task performances. Our method constructs a "language model graph" that maps relationships between models from the semantic coherence of pairwise conversations, and then applies community detection to identify synergistic model clusters. Our experiments with diverse LLMs demonstrate that the proposed method discovers functionally coherent groups that reflect their latent specializations. Priming conversations with specific topics identified synergistic teams which outperform random baselines on downstream benchmarks and achieve comparable accuracy to that of manually-curated teams based on known model specializations. Our findings provide a new basis for the automated design of collaborative multi-agent LLM teams.
Enabling continual learning in LLMs remains a key unresolved research challenge. In a recent announcement, a frontier LLM company made a step towards this by introducing Agent Skills, a framework that equips agents with new knowledge based on instructions stored in simple markdown files. Although Agent Skills can be a very useful tool, we show that they are fundamentally insecure, since they enable trivially simple prompt injections. We demonstrate how to hide malicious instructions in long Agent Skill files and referenced scripts to exfiltrate sensitive data, such as internal files or passwords. Importantly, we show how to bypass system-level guardrails of a popular coding agent: a benign, task-specific approval with the "Don't ask again" option can carry over to closely related but harmful actions. Overall, we conclude that despite ongoing research efforts and scaling model capabilities, frontier LLMs remain vulnerable to very simple prompt injections in realistic scenarios. Our code is available at https://github.com/aisa-group/promptinject-agent-skills.
Repository-level software engineering tasks require large language models (LLMs) to efficiently navigate and extract information from complex codebases through multi-turn tool interactions. Existing approaches face significant limitations: training-free, in-context learning methods struggle to guide agents effectively in tool utilization and decision-making based on environmental feedback, while training-based approaches typically rely on costly distillation from larger LLMs, introducing data compliance concerns in enterprise environments. To address these challenges, we introduce RepoSearch-R1, a novel agentic reinforcement learning framework driven by Monte-carlo Tree Search (MCTS). This approach allows agents to generate diverse, high-quality reasoning trajectories via self-training without requiring model distillation or external supervision. Based on RepoSearch-R1, we construct a RepoQA-Agent specifically designed for repository question-answering tasks. Comprehensive evaluation on repository question-answering tasks demonstrates that RepoSearch-R1 achieves substantial improvements of answer completeness: 16.0% enhancement over no-retrieval methods, 19.5% improvement over iterative retrieval methods, and 33% increase in training efficiency compared to general agentic reinforcement learning approaches. Our cold-start training methodology eliminates data compliance concerns while maintaining robust exploration diversity and answer completeness across repository-level reasoning tasks.
Group based reinforcement learning (RL) has shown impressive results on complex reasoning and mathematical tasks. Yet, when applied to train multi-turn, interactive LLM agents, these methods often suffer from structural blindness-the inability to exploit the underlying connectivity of the environment. This manifests in three critical challenges: (1) inefficient, unguided exploration, (2) imprecise credit assignment due to overlooking pivotal states, and (3) myopic planning caused by static reward discounting. We address these issues with Graph-Enhanced Policy Optimization (GEPO), which dynamically constructs a state-transition graph from agent experience and employs graph-theoretic centrality to provide three synergistic learning signals: (1)structured intrinsic rewards that guide exploration toward high-impact states, (2) a graph-enhanced advantage function for topology-aware credit assignment, and (3) a dynamic discount factor adapted to each state's strategic value. On the ALFWorld, WebShop, and a proprietary Workbench benchmarks, GEPO demonstrates strong performance, achieving absolute success rate gains of +4.1%, +5.3%, and +10.9% over competitive baselines. These results highlight that explicitly modeling environmental structure is a robust, generalizable strategy for advancing LLM agent training.
With increasing urban traffic complexity, Traffic Signal Control (TSC) is essential for optimizing traffic flow and improving road safety. Large Language Models (LLMs) emerge as promising approaches for TSC. However, they are prone to hallucinations in emergencies, leading to unreliable decisions that may cause substantial delays for emergency vehicles. Moreover, diverse intersection types present substantial challenges for traffic state encoding and cross-intersection training, limiting generalization across heterogeneous intersections. Therefore, this paper proposes Retrieval Augmented Generation (RAG)-enhanced distributed LLM agents with Emergency response for Generalizable TSC (REG-TSC). Firstly, this paper presents an emergency-aware reasoning framework, which dynamically adjusts reasoning depth based on the emergency scenario and is equipped with a novel Reviewer-based Emergency RAG (RERAG) to distill specific knowledge and guidance from historical cases, enhancing the reliability and rationality of agents' emergency decisions. Secondly, this paper designs a type-agnostic traffic representation and proposes a Reward-guided Reinforced Refinement (R3) for heterogeneous intersections. R3 adaptively samples training experience from diverse intersections with environment feedback-based priority and fine-tunes LLM agents with a designed reward-weighted likelihood loss, guiding REG-TSC toward high-reward policies across heterogeneous intersections. On three real-world road networks with 17 to 177 heterogeneous intersections, extensive experiments show that REG-TSC reduces travel time by 42.00%, queue length by 62.31%, and emergency vehicle waiting time by 83.16%, outperforming other state-of-the-art methods.
Social media platforms generate massive volumes of heterogeneous data, capturing user behaviors, textual content, temporal dynamics, and network structures. Analyzing such data is crucial for understanding phenomena such as opinion dynamics, community formation, and information diffusion. However, discovering insights from this complex landscape is exploratory, conceptually challenging, and requires expertise in social media mining and visualization. Existing automated approaches, though increasingly leveraging large language models (LLMs), remain largely confined to structured tabular data and cannot adequately address the heterogeneity of social media analysis. We present SIA (Social Insight Agents), an LLM agent system that links heterogeneous multi-modal data -- including raw inputs (e.g., text, network, and behavioral data), intermediate outputs, mined analytical results, and visualization artifacts -- through coordinated agent flows. Guided by a bottom-up taxonomy that connects insight types with suitable mining and visualization techniques, SIA enables agents to plan and execute coherent analysis strategies. To ensure multi-modal integration, it incorporates a data coordinator that unifies tabular, textual, and network data into a consistent flow. Its interactive interface provides a transparent workflow where users can trace, validate, and refine the agent's reasoning, supporting both adaptability and trustworthiness. Through expert-centered case studies and quantitative evaluation, we show that SIA effectively discovers diverse and meaningful insights from social media while supporting human-agent collaboration in complex analytical tasks.
Reward models (RMs) play a critical role in aligning large language models (LLMs) with human preferences. Yet in the domain of tool learning, the lack of RMs specifically designed for function-calling tasks has limited progress toward more capable agentic AI. We introduce ToolRM, a family of lightweight generative RMs tailored for general tool-use scenarios. To build these models, we propose a novel pipeline that constructs pairwise preference data using rule-based scoring and multidimensional sampling. This yields ToolPref-Pairwise-30K, a diverse, balanced, and challenging dataset of critique tasks that supports reinforcement learning with verifiable feedback. To evaluate tool-use RMs, we also introduce TRBench$_{BFCL}$, a benchmark built on the agentic evaluation suite BFCL. Trained on our constructed data, models from the Qwen3-4B/8B series achieve up to 14.28% higher accuracy, substantially outperforming frontier models such as Claude 4 and OpenAI o3 in pairwise reward judgments. Beyond training objectives, ToolRM generalizes to broader critique tasks, including Best-of-N sampling and self-correction. Experiments on ACEBench highlight its effectiveness and efficiency, enabling inference-time scaling and reducing output token usage by over 66%. We release data and model checkpoints to facilitate future research.
As emerging mobility modes continue to expand, many cities face declining bus ridership, increasing fiscal pressure to sustain underutilized routes, and growing inefficiencies in resource allocation. This study employs an agent-based modelling (ABM) approach calibrated through a large language model (LLM) using few-shot learning to examine how progressive bus route cutbacks affect passenger dissatisfaction across demographic groups and overall network resilience. Using IC-card data from Beijing's Huairou District, the LLM-calibrated ABM estimated passenger sensitivity parameters related to travel time, waiting, transfers, and crowding. Results show that the structural configuration of the bus network exerts a stronger influence on system stability than capacity or operational factors. The elimination of high-connectivity routes led to an exponential rise in total dissatisfaction, particularly among passengers with disabilities and older adults. The evolution of dissatisfaction exhibited three distinct phases - stable, transitional, and critical. Through the analysis of each stage, this study found that the continuous bus route reduction scenario exhibits three-stage thresholds. Once these thresholds are crossed, even a small reduction in routes may lead to a significant loss of passenger flow. Research highlights the nonlinear response of user sentiment to service reductions and underscore the importance of maintaining structural critical routes and providing stable services to vulnerable groups for equitable and resilient transport planning.
Large language models (LLMs) are catalyzing the development of autonomous AI research agents for scientific and engineering discovery. We present FM Agent, a novel and general-purpose multi-agent framework that leverages a synergistic combination of LLM-based reasoning and large-scale evolutionary search to address complex real-world challenges. The core of FM Agent integrates several key innovations: 1) a cold-start initialization phase incorporating expert guidance, 2) a novel evolutionary sampling strategy for iterative optimization, 3) domain-specific evaluators that combine correctness, effectiveness, and LLM-supervised feedback, and 4) a distributed, asynchronous execution infrastructure built on Ray. Demonstrating broad applicability, our system has been evaluated across diverse domains, including operations research, machine learning, GPU kernel optimization, and classical mathematical problems. FM Agent reaches state-of-the-art results autonomously, without human interpretation or tuning -- 1976.3 on ALE-Bench (+5.2\%), 43.56\% on MLE-Bench (+4.0pp), up to 20x speedups on KernelBench, and establishes new state-of-the-art(SOTA) results on several classical mathematical problems. Beyond academic benchmarks, FM Agent shows considerable promise for both large-scale enterprise R\&D workflows and fundamental scientific research, where it can accelerate innovation, automate complex discovery processes, and deliver substantial engineering and scientific advances with broader societal impact.
As one of the earliest writing systems, Oracle Bone Script (OBS) preserves the cultural and intellectual heritage of ancient civilizations. However, current OBS research faces two major challenges: (1) the interpretation of OBS involves a complex workflow comprising multiple serial and parallel sub-tasks, and (2) the efficiency of OBS information organization and retrieval remains a critical bottleneck, as scholars often spend substantial effort searching for, compiling, and managing relevant resources. To address these challenges, we present OracleAgent, the first agent system designed for the structured management and retrieval of OBS-related information. OracleAgent seamlessly integrates multiple OBS analysis tools, empowered by large language models (LLMs), and can flexibly orchestrate these components. Additionally, we construct a comprehensive domain-specific multimodal knowledge base for OBS, which is built through a rigorous multi-year process of data collection, cleaning, and expert annotation. The knowledge base comprises over 1.4M single-character rubbing images and 80K interpretation texts. OracleAgent leverages this resource through its multimodal tools to assist experts in retrieval tasks of character, document, interpretation text, and rubbing image. Extensive experiments demonstrate that OracleAgent achieves superior performance across a range of multimodal reasoning and generation tasks, surpassing leading mainstream multimodal large language models (MLLMs) (e.g., GPT-4o). Furthermore, our case study illustrates that OracleAgent can effectively assist domain experts, significantly reducing the time cost of OBS research. These results highlight OracleAgent as a significant step toward the practical deployment of OBS-assisted research and automated interpretation systems.
The ability of LLM agents to plan and invoke tools exposes them to new safety risks, making a comprehensive red-teaming system crucial for discovering vulnerabilities and ensuring their safe deployment. We present SIRAJ: a generic red-teaming framework for arbitrary black-box LLM agents. We employ a dynamic two-step process that starts with an agent definition and generates diverse seed test cases that cover various risk outcomes, tool-use trajectories, and risk sources. Then, it iteratively constructs and refines model-based adversarial attacks based on the execution trajectories of former attempts. To optimize the red-teaming cost, we present a model distillation approach that leverages structured forms of a teacher model's reasoning to train smaller models that are equally effective. Across diverse evaluation agent settings, our seed test case generation approach yields 2 -- 2.5x boost to the coverage of risk outcomes and tool-calling trajectories. Our distilled 8B red-teamer model improves attack success rate by 100%, surpassing the 671B Deepseek-R1 model. Our ablations and analyses validate the effectiveness of the iterative framework, structured reasoning, and the generalization of our red-teamer models.
Natural-language-to-SQL (NL-to-SQL) systems hold promise for democratizing access to structured data, allowing users to query databases without learning SQL. Yet existing systems struggle with realistic spatio-temporal queries, where success requires aligning vague user phrasing with schema-specific categories, handling temporal reasoning, and choosing appropriate outputs. We present an agentic pipeline that extends a naive text-to-SQL baseline (llama-3-sqlcoder-8b) with orchestration by a Mistral-based ReAct agent. The agent can plan, decompose, and adapt queries through schema inspection, SQL generation, execution, and visualization tools. We evaluate on 35 natural-language queries over the NYC and Tokyo check-in dataset, covering spatial, temporal, and multi-dataset reasoning. The agent achieves substantially higher accuracy than the naive baseline 91.4% vs. 28.6% and enhances usability through maps, plots, and structured natural-language summaries. Crucially, our design enables more natural human-database interaction, supporting users who lack SQL expertise, detailed schema knowledge, or prompting skill. We conclude that agentic orchestration, rather than stronger SQL generators alone, is a promising foundation for interactive geospatial assistants.
Large Language Models (LLMs) often struggle with problems that require multi-step reasoning. For small-scale open-source models, Reinforcement Learning with Verifiable Rewards (RLVR) fails when correct solutions are rarely sampled even after many attempts, while Supervised Fine-Tuning (SFT) tends to overfit long demonstrations through rigid token-by-token imitation. To address this gap, we propose Supervised Reinforcement Learning (SRL), a framework that reformulates problem solving as generating a sequence of logical "actions". SRL trains the model to generate an internal reasoning monologue before committing to each action. It provides smoother rewards based on the similarity between the model's actions and expert actions extracted from the SFT dataset in a step-wise manner. This supervision offers richer learning signals even when all rollouts are incorrect, while encouraging flexible reasoning guided by expert demonstrations. As a result, SRL enables small models to learn challenging problems previously unlearnable by SFT or RLVR. Moreover, initializing training with SRL before refining with RLVR yields the strongest overall performance. Beyond reasoning benchmarks, SRL generalizes effectively to agentic software engineering tasks, establishing it as a robust and versatile training framework for reasoning-oriented LLMs.
If we cannot inspect the training data of a large language model (LLM), how can we ever know what it has seen? We believe the most compelling evidence arises when the model itself freely reproduces the target content. As such, we propose RECAP, an agentic pipeline designed to elicit and verify memorized training data from LLM outputs. At the heart of RECAP is a feedback-driven loop, where an initial extraction attempt is evaluated by a secondary language model, which compares the output against a reference passage and identifies discrepancies. These are then translated into minimal correction hints, which are fed back into the target model to guide subsequent generations. In addition, to address alignment-induced refusals, RECAP includes a jailbreaking module that detects and overcomes such barriers. We evaluate RECAP on EchoTrace, a new benchmark spanning over 30 full books, and the results show that RECAP leads to substantial gains over single-iteration approaches. For instance, with GPT-4.1, the average ROUGE-L score for the copyrighted text extraction improved from 0.38 to 0.47 - a nearly 24% increase.
Automating the co-design of a robot's morphology and control is a long-standing challenge due to the vast design space and the tight coupling between body and behavior. We introduce Debate2Create (D2C), a framework in which large language model (LLM) agents engage in a structured dialectical debate to jointly optimize a robot's design and its reward function. In each round, a design agent proposes targeted morphological modifications, and a control agent devises a reward function tailored to exploit the new design. A panel of pluralistic judges then evaluates the design-control pair in simulation and provides feedback that guides the next round of debate. Through iterative debates, the agents progressively refine their proposals, producing increasingly effective robot designs. Notably, D2C yields diverse and specialized morphologies despite no explicit diversity objective. On a quadruped locomotion benchmark, D2C discovers designs that travel 73% farther than the default, demonstrating that structured LLM-based debate can serve as a powerful mechanism for emergent robot co-design. Our results suggest that multi-agent debate, when coupled with physics-grounded feedback, is a promising new paradigm for automated robot design.
Large language models (LLMs) in psychological counseling have attracted increasing attention. However, existing approaches often lack emotional understanding, adaptive strategies, and the use of therapeutic methods across multiple sessions with long-term memory, leaving them far from real clinical practice. To address these critical gaps, we introduce TheraMind, a strategic and adaptive agent for longitudinal psychological counseling. The cornerstone of TheraMind is a novel dual-loop architecture that decouples the complex counseling process into an Intra-Session Loop for tactical dialogue management and a Cross-Session Loop for strategic therapeutic planning. The Intra-Session Loop perceives the patient's emotional state to dynamically select response strategies while leveraging cross-session memory to ensure continuity. Crucially, the Cross-Session Loop empowers the agent with long-term adaptability by evaluating the efficacy of the applied therapy after each session and adjusting the method for subsequent interactions. We validate our approach in a high-fidelity simulation environment grounded in real clinical cases. Extensive evaluations show that TheraMind outperforms other methods, especially on multi-session metrics like Coherence, Flexibility, and Therapeutic Attunement, validating the effectiveness of its dual-loop design in emulating strategic, adaptive, and longitudinal therapeutic behavior. The code is publicly available at https://0mwwm0.github.io/TheraMind/.
We introduce Agentic Economic Modeling (AEM), a framework that aligns synthetic LLM choices with small-sample human evidence for reliable econometric inference. AEM first generates task-conditioned synthetic choices via LLMs, then learns a bias-correction mapping from task features and raw LLM choices to human-aligned choices, upon which standard econometric estimators perform inference to recover demand elasticities and treatment effects.We validate AEM in two experiments. In a large scale conjoint study with millions of observations, using only 10% of the original data to fit the correction model lowers the error of the demand-parameter estimates, while uncorrected LLM choices even increase the errors. In a regional field experiment, a mixture model calibrated on 10% of geographic regions estimates an out-of-domain treatment effect of -65\pm10 bps, closely matching the full human experiment (-60\pm8 bps).Under time-wise extrapolation, training with only day-one human data yields -24 bps (95% CI: [-26, -22], p<1e-5),improving over the human-only day-one baseline (-17 bps, 95% CI: [-43, +9], p=0.2049).These results demonstrate AEM's potential to improve RCT efficiency and establish a foundation method for LLM-based counterfactual generation.
Large language model-based agents show promise for software engineering, but environment configuration remains a bottleneck due to heavy manual effort and scarce large-scale, high-quality datasets. Existing benchmarks assess only end-to-end build/test success, obscuring where and why agents succeed or fail. We introduce the Environment Configuration Diagnosis Benchmark, Enconda-bench, which provides process-level trajectory assessment of fine-grained agent capabilities during environment setup-planning, perception-driven error diagnosis, feedback-driven repair, and action to execute final environment configuration. Our task instances are automatically constructed by injecting realistic README errors and are validated in Docker for scalable, high-quality evaluation. Enconda-bench combines process-level analysis with end-to-end executability to enable capability assessments beyond aggregate success rates. Evaluations across state-of-the-art LLMs and agent frameworks show that while agents can localize errors, they struggle to translate feedback into effective corrections, limiting end-to-end performance. To our knowledge, Enconda-bench is the first framework to provide process-level internal capability assessment for environment configuration, offering actionable insights for improving software engineering agents.
An Agentic AI Workflow (AAW), also known as an LLM-based multi-agent system, is an autonomous system that assembles several LLM-based agents to work collaboratively towards a shared goal. The high autonomy, widespread adoption, and growing interest in such AAWs highlight the need for a deeper understanding of their operations, from both quality and security aspects. To this day, there are no existing methods to assess the influence of each agent on the AAW's final output. Adopting techniques from related fields is not feasible since existing methods perform only static structural analysis, which is unsuitable for inference time execution. We present Counterfactual-based Agent Influence Ranker (CAIR) - the first method for assessing the influence level of each agent on the AAW's output and determining which agents are the most influential. By performing counterfactual analysis, CAIR provides a task-agnostic analysis that can be used both offline and at inference time. We evaluate CAIR using an AAWs dataset of our creation, containing 30 different use cases with 230 different functionalities. Our evaluation showed that CAIR produces consistent rankings, outperforms baseline methods, and can easily enhance the effectiveness and relevancy of downstream tasks.
While Large Language Model (LLM) agents are often approached from the angle of action planning/generation to accomplish a goal (e.g., given by language descriptions), their abilities to collaborate with each other to achieve a joint goal are not well explored. To address this limitation, this paper studies LLM agents in task collaboration, particularly under the condition of information asymmetry, where agents have disparities in their knowledge and skills and need to work together to complete a shared task. We extend Einstein Puzzles, a classical symbolic puzzle, to a table-top game. In this game, two LLM agents must reason, communicate, and act to satisfy spatial and relational constraints required to solve the puzzle. We apply a fine-tuning-plus-verifier framework in which LLM agents are equipped with various communication strategies and verification signals from the environment. Empirical results highlight the critical importance of aligned communication, especially when agents possess both information-seeking and -providing capabilities. Interestingly, agents without communication can still achieve high task performance; however, further analysis reveals a lack of true rule understanding and lower trust from human evaluators. Instead, by integrating an environment-based verifier, we enhance agents' ability to comprehend task rules and complete tasks, promoting both safer and more interpretable collaboration in AI systems. https://github.com/Roihn/EinsteinPuzzles
The diagnosis of most mental disorders, including psychiatric evaluations, primarily depends on dialogues between psychiatrists and patients. This subjective process can lead to variability in diagnoses across clinicians and patients, resulting in inconsistencies and challenges in achieving reliable outcomes. To address these issues and standardize psychiatric diagnoses, we propose a Fine-Tuned Large Language Model (LLM) Consortium and OpenAI-gpt-oss Reasoning LLM-enabled Decision Support System for the clinical diagnosis of mental disorders. Our approach leverages fine-tuned LLMs trained on conversational datasets involving psychiatrist-patient interactions focused on mental health conditions (e.g., depression). The diagnostic predictions from individual models are aggregated through a consensus-based decision-making process, refined by the OpenAI-gpt-oss reasoning LLM. We propose a novel method for deploying LLM agents that orchestrate communication between the LLM consortium and the reasoning LLM, ensuring transparency, reliability, and responsible AI across the entire diagnostic workflow. Experimental results demonstrate the transformative potential of combining fine-tuned LLMs with a reasoning model to create a robust and highly accurate diagnostic system for mental health assessment. A prototype of the proposed platform, integrating three fine-tuned LLMs with the OpenAI-gpt-oss reasoning LLM, was developed in collaboration with the U.S. Army Medical Research Team in Norfolk, Virginia, USA. To the best of our knowledge, this work represents the first application of a fine-tuned LLM consortium integrated with a reasoning LLM for clinical mental health diagnosis paving the way for next-generation AI-powered eHealth systems aimed at standardizing psychiatric diagnoses.
Large Language Models (LLMs) excel as passive responders, but teaching them to be proactive, goal-oriented partners, a critical capability in high-stakes domains, remains a major challenge. Current paradigms either myopically optimize single-turn attributes or rely on brittle, high-cost user simulators, creating a persistent ``reality gap''. To bridge this gap, we introduce \texttt{Learn-to-Ask}, a general, simulator-free framework for learning and deploying proactive dialogue agents \textit{directly from offline expert data}, bypassing the need to model complex user dynamics. Our key insight is to reframe the offline policy learning problem by leveraging the \textbf{observed future} of each expert trajectory. This allows us to infer a dense, turn-by-turn reward signal grounded in the expert's revealed strategy, decomposing the intractable long-horizon problem into a series of supervised learning tasks, and training a policy to output a structured \texttt{(action, state_assessment)} tuple, governing both \textbf{what to ask} and, crucially, \textbf{when to stop}. To ensure reward fidelity, our Automated Grader Calibration pipeline systematically purges noise from the LLM-based reward model with minimal human supervision. Empirically, we demonstrate the efficacy of \texttt{Learn-to-Ask} in a real-world medical dataset, using LLMs of varying sizes up to 32B. Our approach culminates in the successful deployment of LLMs into a live, large-scale online AI service. In rigorous in-house evaluations, our model was launched and achieved performance even superior to human experts, proving our framework's ability to translate offline data into tangible, real-world impact. We hope this work provides a practical and economically viable blueprint for transforming passive LLMs into proactive, goal-oriented LLM applications.