Training effective AI agents for multi-turn interactions requires high-quality data that captures realistic human-agent dynamics, yet such data is scarce and expensive to collect manually. We introduce APIGen-MT, a two-phase framework that generates verifiable and diverse multi-turn agent data. In the first phase, our agentic pipeline produces detailed task blueprints with ground-truth actions, leveraging a committee of LLM reviewers and iterative feedback loops. These blueprints are then transformed into complete interaction trajectories through simulated human-agent interplay. We train a family of models -- the xLAM-2-fc-r series with sizes ranging from 1B to 70B parameters. Our models outperform frontier models such as GPT-4o and Claude 3.5 on $\tau$-bench and BFCL benchmarks, with the smaller models surpassing their larger counterparts, particularly in multi-turn settings, while maintaining superior consistency across multiple trials. Comprehensive experiments demonstrate that our verified blueprint-to-details approach yields high-quality training data, enabling the development of more reliable, efficient, and capable agents. We open-source both the synthetic data collected and the trained xLAM-2-fc-r models to advance research in AI agents. Models are available on HuggingFace at https://huggingface.co/collections/Salesforce/xlam-2-67ef5be12949d8dcdae354c4 and project website is https://apigen-mt.github.io
In the interaction between agents and their environments, agents expand their capabilities by planning and executing actions. However, LLM-based agents face substantial challenges when deployed in novel environments or required to navigate unconventional action spaces. To empower agents to autonomously explore environments, optimize workflows, and enhance their understanding of actions, we propose SynWorld, a framework that allows agents to synthesize possible scenarios with multi-step action invocation within the action space and perform Monte Carlo Tree Search (MCTS) exploration to effectively refine their action knowledge in the current environment. Our experiments demonstrate that SynWorld is an effective and general approach to learning action knowledge in new environments. Code is available at https://github.com/zjunlp/SynWorld.
Large Language Models (LLMs) have achieved considerable performance across various agentic planning tasks. However, traditional agent planning approaches adopt a "flood irrigation" methodology that indiscriminately injects gold trajectories, external feedback, and domain knowledge into agent models. This practice overlooks the fundamental human cognitive principle of situational self-awareness during decision-making-the ability to dynamically assess situational demands and strategically employ resources during decision-making. We propose agentic knowledgeable self-awareness to address this gap, a novel paradigm enabling LLM-based agents to autonomously regulate knowledge utilization. Specifically, we propose KnowSelf, a data-centric approach that applies agents with knowledgeable self-awareness like humans. Concretely, we devise a heuristic situation judgement criterion to mark special tokens on the agent's self-explored trajectories for collecting training data. Through a two-stage training process, the agent model can switch between different situations by generating specific special tokens, achieving optimal planning effects with minimal costs. Our experiments demonstrate that KnowSelf can outperform various strong baselines on different tasks and models with minimal use of external knowledge. Code is available at https://github.com/zjunlp/KnowSelf.
Integrated into websites, LLM-powered chatbots offer alternative means of navigation and information retrieval, leading to a shift in how users access information on the web. Yet, predominantly closed-sourced solutions limit proliferation among web hosts and suffer from a lack of transparency with regard to implementation details and energy efficiency. In this work, we propose our openly available agent Talk2X leveraging an adapted retrieval-augmented generation approach (RAG) combined with an automatically generated vector database, benefiting energy efficiency. Talk2X's architecture is generalizable to arbitrary websites offering developers a ready to use tool for integration. Using a mixed-methods approach, we evaluated Talk2X's usability by tasking users to acquire specific assets from an open science repository. Talk2X significantly improved task completion time, correctness, and user experience supporting users in quickly pinpointing specific information as compared to standard user-website interaction. Our findings contribute technical advancements to an ongoing paradigm shift of how we access information on the web.
Recent advancements in AI have reinvigorated Agent-Based Models (ABMs), as the integration of Large Language Models (LLMs) has led to the emergence of ``generative ABMs'' as a novel approach to simulating social systems. While ABMs offer means to bridge micro-level interactions with macro-level patterns, they have long faced criticisms from social scientists, pointing to e.g., lack of realism, computational complexity, and challenges of calibrating and validating against empirical data. This paper reviews the generative ABM literature to assess how this new approach adequately addresses these long-standing criticisms. Our findings show that studies show limited awareness of historical debates. Validation remains poorly addressed, with many studies relying solely on subjective assessments of model `believability', and even the most rigorous validation failing to adequately evidence operational validity. We argue that there are reasons to believe that LLMs will exacerbate rather than resolve the long-standing challenges of ABMs. The black-box nature of LLMs moreover limit their usefulness for disentangling complex emergent causal mechanisms. While generative ABMs are still in a stage of early experimentation, these findings question of whether and how the field can transition to the type of rigorous modeling needed to contribute to social scientific theory.
Agentic systems powered by large language models (LLMs) are becoming progressively more complex and capable. Their increasing agency and expanding deployment settings attract growing attention over effective governance policies, monitoring and control protocols. Based on emerging landscapes of the agentic market, we analyze the potential liability issues stemming from delegated use of LLM agents and their extended systems from a principal-agent perspective. Our analysis complements existing risk-based studies on artificial agency and covers the spectrum of important aspects of the principal-agent relationship and their potential consequences at deployment. Furthermore, we motivate method developments for technical governance along the directions of interpretability and behavior evaluations, reward and conflict management, and the mitigation of misalignment and misconduct through principled engineering of detection and fail-safe mechanisms. By illustrating the outstanding issues in AI liability for LLM-based agentic systems, we aim to inform the system design, auditing and monitoring approaches to enhancing transparency and accountability.
Effective conversational agents must be able to personalize their behavior to suit a user's preferences, personality, and attributes, whether they are assisting with writing tasks or operating in domains like education or healthcare. Current training methods like Reinforcement Learning from Human Feedback (RLHF) prioritize helpfulness and safety but fall short in fostering truly empathetic, adaptive, and personalized interactions. Traditional approaches to personalization often rely on extensive user history, limiting their effectiveness for new or context-limited users. To overcome these limitations, we propose to incorporate an intrinsic motivation to improve the conversational agents's model of the user as an additional reward alongside multi-turn RLHF. This reward mechanism encourages the agent to actively elicit user traits by optimizing conversations to increase the accuracy of its user model. Consequently, the policy agent can deliver more personalized interactions through obtaining more information about the user. We applied our method both education and fitness settings, where LLMs teach concepts or recommend personalized strategies based on users' hidden learning style or lifestyle attributes. Using LLM-simulated users, our approach outperformed a multi-turn RLHF baseline in revealing information about the users' preferences, and adapting to them.
Generalizable alignment is a core challenge for deploying Large Language Models (LLMs) safely in real-world NLP applications. Current alignment methods, including Reinforcement Learning from Human Feedback (RLHF), often fail to guarantee constraint satisfaction outside their training distribution due to their reliance on implicit, post-hoc preferences. Inspired by a paradigm shift to first curate data before tuning, we introduce a new framework for safe language alignment that learns natural language constraints from positive and negative demonstrations as a primary step. From inferring both a task-specific reward function and latent constraint functions, our approach fosters adaptation to novel safety requirements and robust generalization under domain shifts and adversarial inputs. We formalize the framework within a Constrained Markov Decision Process (CMDP) and validate it via a text-based navigation environment, demonstrating safe adaptation to changing danger zones. Our experiments show fewer violations upon domain shift when following a safe navigation path, and we achieve zero violations by applying learned constraints to a distilled BERT model as a fine-tuning technique. This work offers a promising path toward building safety-critical and more generalizable LLMs for practical NLP settings.
Language Model Models (LLMs) have improved dramatically in the past few years, increasing their adoption and the scope of their capabilities over time. A significant amount of work is dedicated to ``model alignment'', i.e., preventing LLMs to generate unsafe responses when deployed into customer-facing applications. One popular method to evaluate safety risks is \textit{red-teaming}, where agents attempt to bypass alignment by crafting elaborate prompts that trigger unsafe responses from a model. Standard human-driven red-teaming is costly, time-consuming and rarely covers all the recent features (e.g., multi-lingual, multi-modal aspects), while proposed automation methods only cover a small subset of LLMs capabilities (i.e., English or single-turn). We present Multi-lingual Multi-turn Automated Red Teaming (\textbf{MM-ART}), a method to fully automate conversational, multi-lingual red-teaming operations and quickly identify prompts leading to unsafe responses. Through extensive experiments on different languages, we show the studied LLMs are on average 71\% more vulnerable after a 5-turn conversation in English than after the initial turn. For conversations in non-English languages, models display up to 195\% more safety vulnerabilities than the standard single-turn English approach, confirming the need for automated red-teaming methods matching LLMs capabilities.
Large Language Models (LLMs) equipped with web search capabilities have demonstrated impressive potential for deep research tasks. However, current approaches predominantly rely on either manually engineered prompts (prompt engineering-based) with brittle performance or reinforcement learning within controlled Retrieval-Augmented Generation (RAG) environments (RAG-based) that fail to capture the complexities of real-world interaction. In this paper, we introduce DeepResearcher, the first comprehensive framework for end-to-end training of LLM-based deep research agents through scaling reinforcement learning (RL) in real-world environments with authentic web search interactions. Unlike RAG-based approaches that assume all necessary information exists within a fixed corpus, our method trains agents to navigate the noisy, unstructured, and dynamic nature of the open web. We implement a specialized multi-agent architecture where browsing agents extract relevant information from various webpage structures and overcoming significant technical challenges. Extensive experiments on open-domain research tasks demonstrate that DeepResearcher achieves substantial improvements of up to 28.9 points over prompt engineering-based baselines and up to 7.2 points over RAG-based RL agents. Our qualitative analysis reveals emergent cognitive behaviors from end-to-end RL training, including the ability to formulate plans, cross-validate information from multiple sources, engage in self-reflection to redirect research, and maintain honesty when unable to find definitive answers. Our results highlight that end-to-end training in real-world web environments is not merely an implementation detail but a fundamental requirement for developing robust research capabilities aligned with real-world applications. We release DeepResearcher at https://github.com/GAIR-NLP/DeepResearcher.
Large Language Model (LLM) agents are autonomous systems powered by LLMs, capable of reasoning and planning to solve problems by leveraging a set of tools. However, the integration of multi-tool capabilities in LLM agents introduces challenges in securely managing tools, ensuring their compatibility, handling dependency relationships, and protecting control flows within LLM agent workflows. In this paper, we present the first systematic security analysis of task control flows in multi-tool-enabled LLM agents. We identify a novel threat, Cross-Tool Harvesting and Polluting (XTHP), which includes multiple attack vectors to first hijack the normal control flows of agent tasks, and then collect and pollute confidential or private information within LLM agent systems. To understand the impact of this threat, we developed Chord, a dynamic scanning tool designed to automatically detect real-world agent tools susceptible to XTHP attacks. Our evaluation of 73 real-world tools from the repositories of two major LLM agent development frameworks, LangChain and LlamaIndex, revealed a significant security concern: 80% of the tools are vulnerable to hijacking attacks, 78% to XTH attacks, and 41% to XTP attacks, highlighting the prevalence of this threat.
Large Language Model (LLM) tools have demonstrated their potential to deliver high-quality assistance by providing instant, personalized feedback that is crucial for effective programming education. However, many of these tools operate independently from institutional Learning Management Systems, which creates a significant disconnect. This isolation limits the ability to leverage learning materials and exercise context for generating tailored, context-aware feedback. Furthermore, previous research on self-regulated learning and LLM support mainly focused on knowledge acquisition, not the development of important self-regulation skills. To address these challenges, we developed CodeRunner Agent, an LLM-based programming assistant that integrates the CodeRunner, a student-submitted code executing and automated grading plugin in Moodle. CodeRunner Agent empowers educators to customize AI-generated feedback by incorporating detailed context from lecture materials, programming questions, student answers, and execution results. Additionally, it enhances students' self-regulated learning by providing strategy-based AI responses. This integrated, context-aware, and skill-focused approach offers promising avenues for data-driven improvements in programming education.
Amid the recent uptake of Generative AI, sociotechnical scholars and critics have traced a multitude of resulting harms, with analyses largely focused on values and axiology (e.g., bias). While value-based analyses are crucial, we argue that ontologies -- concerning what we allow ourselves to think or talk about -- is a vital but under-recognized dimension in analyzing these systems. Proposing a need for a practice-based engagement with ontologies, we offer four orientations for considering ontologies in design: pluralism, groundedness, liveliness, and enactment. We share examples of potentialities that are opened up through these orientations across the entire LLM development pipeline by conducting two ontological analyses: examining the responses of four LLM-based chatbots in a prompting exercise, and analyzing the architecture of an LLM-based agent simulation. We conclude by sharing opportunities and limitations of working with ontologies in the design and development of sociotechnical systems.
Large Language Models (LLMs) are revolutionizing the development of AI assistants capable of performing diverse tasks across domains. However, current state-of-the-art LLM-driven agents face significant challenges, including high operational costs and limited success rates on complex benchmarks like GAIA. To address these issues, we propose the Knowledge Graph of Thoughts (KGoT), an innovative AI assistant architecture that integrates LLM reasoning with dynamically constructed knowledge graphs (KGs). KGoT extracts and structures task-relevant knowledge into a dynamic KG representation, iteratively enhanced through external tools such as math solvers, web crawlers, and Python scripts. Such structured representation of task-relevant knowledge enables low-cost models to solve complex tasks effectively. For example, KGoT achieves a 29% improvement in task success rates on the GAIA benchmark compared to Hugging Face Agents with GPT-4o mini, while reducing costs by over 36x compared to GPT-4o. Improvements for recent reasoning models are similar, e.g., 36% and 37.5% for Qwen2.5-32B and Deepseek-R1-70B, respectively. KGoT offers a scalable, affordable, and high-performing solution for AI assistants.
Large language models (LLMs) demonstrate strong potential as agents for tool invocation due to their advanced comprehension and planning capabilities. Users increasingly rely on LLM-based agents to solve complex missions through iterative interactions. However, existing benchmarks predominantly access agents in single-mission scenarios, failing to capture real-world complexity. To bridge this gap, we propose the Multi-Mission Tool Bench. In the benchmark, each test case comprises multiple interrelated missions. This design requires agents to dynamically adapt to evolving demands. Moreover, the proposed benchmark explores all possible mission-switching patterns within a fixed mission number. Specifically, we propose a multi-agent data generation framework to construct the benchmark. We also propose a novel method to evaluate the accuracy and efficiency of agent decisions with dynamic decision trees. Experiments on diverse open-source and closed-source LLMs reveal critical factors influencing agent robustness and provide actionable insights to the tool invocation society.
The task of issue resolving is to modify a codebase to generate a patch that addresses a given issue. However, existing benchmarks, such as SWE-bench, focus almost exclusively on Python, making them insufficient for evaluating Large Language Models (LLMs) across diverse software ecosystems. To address this, we introduce a multilingual issue-resolving benchmark, called Multi-SWE-bench, covering Java, TypeScript, JavaScript, Go, Rust, C, and C++. It includes a total of 1,632 high-quality instances, which were carefully annotated from 2,456 candidates by 68 expert annotators, ensuring that the benchmark can provide an accurate and reliable evaluation. Based on Multi-SWE-bench, we evaluate a series of state-of-the-art models using three representative methods (Agentless, SWE-agent, and OpenHands) and present a comprehensive analysis with key empirical insights. In addition, we launch a Multi-SWE-RL open-source community, aimed at building large-scale reinforcement learning (RL) training datasets for issue-resolving tasks. As an initial contribution, we release a set of 4,723 well-structured instances spanning seven programming languages, laying a solid foundation for RL research in this domain. More importantly, we open-source our entire data production pipeline, along with detailed tutorials, encouraging the open-source community to continuously contribute and expand the dataset. We envision our Multi-SWE-bench and the ever-growing Multi-SWE-RL community as catalysts for advancing RL toward its full potential, bringing us one step closer to the dawn of AGI.
The advent of Large Language Models (LLMs) is transforming software development, significantly enhancing software engineering processes. Research has explored their role within development teams, focusing on specific tasks such as artifact generation, decision-making support, and information retrieval. Despite the growing body of work on LLMs in software engineering, most studies have centered on broad adoption trends, neglecting the nuanced relationship between individual cognitive and behavioral factors and their impact on task-specific adoption. While factors such as perceived effort and performance expectancy have been explored at a general level, their influence on distinct software engineering tasks remains underexamined. This gap hinders the development of tailored LLM-based systems (e.g., Generative AI Agents) that align with engineers' specific needs and limits the ability of team leaders to devise effective strategies for fostering LLM adoption in targeted workflows. This study bridges this gap by surveying N=188 software engineers to test the relationship between individual attributes related to technology adoption and LLM adoption across five key tasks, using structural equation modeling (SEM). The Unified Theory of Acceptance and Use of Technology (UTAUT2) was applied to characterize individual adoption behaviors. The findings reveal that task-specific adoption is influenced by distinct factors, some of which negatively impact adoption when considered in isolation, underscoring the complexity of LLM integration in software engineering. To support effective adoption, this article provides actionable recommendations, such as seamlessly integrating LLMs into existing development environments and encouraging peer-driven knowledge sharing to enhance information retrieval.
With the rapid development of 3D printing, the demand for personalized and customized production on the manufacturing line is steadily increasing. Efficient merging of printing workpieces can significantly enhance the processing efficiency of the production line. Addressing the challenge, a Large Language Model (LLM)-driven method is established in this paper for the autonomous merging of 3D printing work orders, integrated with a memory-augmented learning strategy. In industrial scenarios, both device and order features are modeled into LLM-readable natural language prompt templates, and develop an order-device matching tool along with a merging interference checking module. By incorporating a self-memory learning strategy, an intelligent agent for autonomous order merging is constructed, resulting in improved accuracy and precision in order allocation. The proposed method effectively leverages the strengths of LLMs in industrial applications while reducing hallucination.
GUI testing is an essential quality assurance process in mobile app development. However, the creation and maintenance of GUI tests for mobile apps are resource-intensive and costly. Recognizing that many apps share similar functionalities, researchers have proposed various techniques to migrate GUI tests from one app to another with similar features. For example, some techniques employ mapping-based approaches to align the GUI elements traversed by the tests of a source app to those present in the target app. Other test migration techniques have also been proposed to leverage large language models (LLMs) by adapting the GUI tasks in source tests. However, these techniques are ineffective in dealing with different operational logic between the source and target apps. The semantics of GUI elements may not be correctly inferred due to the missing analysis of these flows. In this work, we propose REUSEDROID, a novel multiagent framework for GUI test migration empowered by Large Vision-Language Models (VLMs). REUSEDROID is powered by multiple VLM-based agents, each tackling a stage of the test migration process by leveraging the relevant visual and textual information embedded in GUI pages. An insight of REUSEDROID is to migrate tests based only on the core logic shared across similar apps, while their entire operational logic could differ. We evaluate REUSEDROID on LinPro, a new test migration dataset that consists of 578 migration tasks for 39 popular apps across 4 categories. The experimental result shows that REUSEDROID can successfully migrate 90.3% of the migration tasks, outperforming the best mapping-based and LLM-based baselines by 318.1% and 109.1%, respectively.
Reinforcement learning has shown great potential in finance. We have organized the FinRL Contests 2023-2025 featuring different financial tasks. Large language models have a strong capability to process financial texts. Integrating LLM-generated signals into FinRL is a new task, enabling agents to use both structured market data and unstructured financial text. To address the sampling bottleneck during training, we introduce GPU-based parallel market environments to improve sampling speed. In this paper, we summarize the parallel market environments used in FinRL Contests 2023-2025. Two new environments incorporate LLM-generated signals and support massively parallel simulation. Contestants utilize these environments to train agents for stock and cryptocurrency trading tasks.
Recent advancements in Large Language Models (LLMs) have not only showcased impressive creative capabilities but also revealed emerging agentic behaviors that exploit linguistic ambiguity in adversarial settings. In this study, we investigate how an LLM, acting as an autonomous agent, leverages semantic ambiguity to generate deceptive puzzles that mislead and challenge human users. Inspired by the popular puzzle game "Connections", we systematically compare puzzles produced through zero-shot prompting, role-injected adversarial prompts, and human-crafted examples, with an emphasis on understanding the underlying agent decision-making processes. Employing computational analyses with HateBERT to quantify semantic ambiguity, alongside subjective human evaluations, we demonstrate that explicit adversarial agent behaviors significantly heighten semantic ambiguity -- thereby increasing cognitive load and reducing fairness in puzzle solving. These findings provide critical insights into the emergent agentic qualities of LLMs and underscore important ethical considerations for evaluating and safely deploying autonomous language systems in both educational technologies and entertainment.
The rapid advancements in large Language models (LLMs) have significantly enhanced their reasoning capabilities, driven by various strategies such as multi-agent collaboration. However, unlike the well-established performance improvements achieved through scaling data and model size, the scaling of reasoning in LLMs is more complex and can even negatively impact reasoning performance, introducing new challenges in model alignment and robustness. In this survey, we provide a comprehensive examination of scaling in LLM reasoning, categorizing it into multiple dimensions and analyzing how and to what extent different scaling strategies contribute to improving reasoning capabilities. We begin by exploring scaling in input size, which enables LLMs to process and utilize more extensive context for improved reasoning. Next, we analyze scaling in reasoning steps that improves multi-step inference and logical consistency. We then examine scaling in reasoning rounds, where iterative interactions refine reasoning outcomes. Furthermore, we discuss scaling in training-enabled reasoning, focusing on optimization through iterative model improvement. Finally, we review applications of scaling across domains and outline future directions for further advancing LLM reasoning. By synthesizing these diverse perspectives, this survey aims to provide insights into how scaling strategies fundamentally enhance the reasoning capabilities of LLMs and further guide the development of next-generation AI systems.
Automated Driving System (ADS) is a safety-critical software system responsible for the interpretation of the vehicle's environment and making decisions accordingly. The unbounded complexity of the driving context, including unforeseeable events, necessitate continuous improvement, often achieved through iterative DevOps processes. However, DevOps processes are themselves complex, making these improvements both time- and resource-intensive. Automation in code generation for ADS using Large Language Models (LLM) is one potential approach to address this challenge. Nevertheless, the development of ADS requires rigorous processes to verify, validate, assess, and qualify the code before it can be deployed in the vehicle and used. In this study, we developed and evaluated a prototype for automatic code generation and assessment using a designed pipeline of a LLM-based agent, simulation model, and rule-based feedback generator in an industrial setup. The LLM-generated code is evaluated automatically in a simulation model against multiple critical traffic scenarios, and an assessment report is provided as feedback to the LLM for modification or bug fixing. We report about the experimental results of the prototype employing Codellama:34b, DeepSeek (r1:32b and Coder:33b), CodeGemma:7b, Mistral:7b, and GPT4 for Adaptive Cruise Control (ACC) and Unsupervised Collision Avoidance by Evasive Manoeuvre (CAEM). We finally assessed the tool with 11 experts at two Original Equipment Manufacturers (OEMs) by conducting an interview study.
Blockchain consensus mechanisms have relied on algorithms such as Proof-of-Work (PoW) and Proof-of-Stake (PoS) to ensure network functionality and integrity. However, these approaches struggle with adaptability for decision-making where the opinions of each matter rather than reaching an agreement based on honest majority or weighted consensus. This paper introduces a novel deliberation-based consensus mechanism where Large Language Models (LLMs) act as rational agents engaging in structured discussions to reach a unanimous consensus. By leveraging graded consensus and a multi-round deliberation process, our approach ensures both unanimous consensus for definitive problems and graded confidence for prioritized decisions and policies. We provide a formalization of our system and use it to show that the properties of blockchains: consistency, agreement, liveness, and determinism are maintained. Moreover, experimental results demonstrate our system's feasibility, showcasing how our deliberation method's convergence, block properties, and accuracy enable decision-making on blockchain networks. We also address key challenges with this novel approach such as degeneration of thoughts, hallucinations, malicious models and nodes, resource consumption, and scalability.
With the development of LLMs as agents, there is a growing interest in connecting multiple agents into multi-agent systems to solve tasks concurrently, focusing on their role in task assignment and coordination. This paper explores how LLMs can effectively allocate computational tasks among multiple agents, considering factors such as cost, efficiency, and performance. In this work, we address key questions, including the effectiveness of LLMs as orchestrators and planners, comparing their effectiveness in task assignment and coordination. Our experiments demonstrate that LLMs can achieve high validity and accuracy in resource allocation tasks. We find that the planner method outperforms the orchestrator method in handling concurrent actions, resulting in improved efficiency and better utilization of agents. Additionally, we show that providing explicit information about worker capabilities enhances the allocation strategies of planners, particularly when dealing with suboptimal workers.
Objective: Traditional phone-based surveys are among the most accessible and widely used methods to collect biomedical and healthcare data, however, they are often costly, labor intensive, and difficult to scale effectively. To overcome these limitations, we propose an end-to-end survey collection framework driven by conversational Large Language Models (LLMs). Materials and Methods: Our framework consists of a researcher responsible for designing the survey and recruiting participants, a conversational phone agent powered by an LLM that calls participants and administers the survey, a second LLM (GPT-4o) that analyzes the conversation transcripts generated during the surveys, and a database for storing and organizing the results. To test our framework, we recruited 8 participants consisting of 5 native and 3 non-native english speakers and administered 40 surveys. We evaluated the correctness of LLM-generated conversation transcripts, accuracy of survey responses inferred by GPT-4o and overall participant experience. Results: Survey responses were successfully extracted by GPT-4o from conversation transcripts with an average accuracy of 98% despite transcripts exhibiting an average per-line word error rate of 7.7%. While participants noted occasional errors made by the conversational LLM agent, they reported that the agent effectively conveyed the purpose of the survey, demonstrated good comprehension, and maintained an engaging interaction. Conclusions: Our study highlights the potential of LLM agents in conducting and analyzing phone surveys for healthcare applications. By reducing the workload on human interviewers and offering a scalable solution, this approach paves the way for real-world, end-to-end AI-powered phone survey collection systems.
While AI agents have shown remarkable performance at various tasks, they still struggle with complex multi-modal applications, structured generation and strategic planning. Improvements via standard fine-tuning is often impractical, as solving agentic tasks usually relies on black box API access without control over model parameters. Inference-time methods such as Best-of-N (BON) sampling offer a simple yet effective alternative to improve performance. However, BON lacks iterative feedback integration mechanism. Hence, we propose Iterative Agent Decoding (IAD) which combines iterative refinement with dynamic candidate evaluation and selection guided by a verifier. IAD differs in how feedback is designed and integrated, specifically optimized to extract maximal signal from reward scores. We conduct a detailed comparison of baselines across key metrics on Sketch2Code, Text2SQL, and Webshop where IAD consistently outperforms baselines, achieving 3--6% absolute gains on Sketch2Code and Text2SQL (with and without LLM judges) and 8--10% gains on Webshop across multiple metrics. To better understand the source of IAD's gains, we perform controlled experiments to disentangle the effect of adaptive feedback from stochastic sampling, and find that IAD's improvements are primarily driven by verifier-guided refinement, not merely sampling diversity. We also show that both IAD and BON exhibit inference-time scaling with increased compute when guided by an optimal verifier. Our analysis highlights the critical role of verifier quality in effective inference-time optimization and examines the impact of noisy and sparse rewards on scaling behavior. Together, these findings offer key insights into the trade-offs and principles of effective inference-time optimization.
Over the past two decades, researchers have made significant advancements in simulating human crowds, yet these efforts largely focus on low-level tasks like collision avoidance and a narrow range of behaviors such as path following and flocking. However, creating compelling crowd scenes demands more than just functional movement-it requires capturing high-level interactions between agents, their environment, and each other over time. To address this issue, we introduce Gen-C, a generative model to automate the task of authoring high-level crowd behaviors. Gen-C bypasses the labor-intensive and challenging task of collecting and annotating real crowd video data by leveraging a large language model (LLM) to generate a limited set of crowd scenarios, which are subsequently expanded and generalized through simulations to construct time-expanded graphs that model the actions and interactions of virtual agents. Our method employs two Variational Graph Auto-Encoders guided by a condition prior network: one dedicated to learning a latent space for graph structures (agent interactions) and the other for node features (agent actions and navigation). This setup enables the flexible generation of dynamic crowd interactions. The trained model can be conditioned on natural language, empowering users to synthesize novel crowd behaviors from text descriptions. We demonstrate the effectiveness of our approach in two scenarios, a University Campus and a Train Station, showcasing its potential for populating diverse virtual environments with agents exhibiting varied and dynamic behaviors that reflect complex interactions and high-level decision-making patterns.
Large Language Models (LLMs) are playing an expanding role in physics research by enhancing reasoning, symbolic manipulation, and numerical computation. However, ensuring the reliability and interpretability of their outputs remains a significant challenge. In our framework, we conceptualize the collaboration between AI and human scientists as a dynamic interplay among three modules: the reasoning module, the interpretation module, and the AI-scientist interaction module. Recognizing that effective physics reasoning demands rigorous logical consistency, quantitative precision, and deep integration with established theoretical models, we introduce the interpretation module to improve the understanding of AI-generated outputs, which is not previously explored in the literature. This module comprises multiple specialized agents, including summarizers, model builders, UI builders, and testers, which collaboratively structure LLM outputs within a physically grounded framework, by constructing a more interpretable science model. A case study demonstrates that our approach enhances transparency, facilitates validation, and strengthens AI-augmented reasoning in scientific discovery.
We present the first mechanistic evidence that model-free reinforcement learning agents can learn to plan. This is achieved by applying a methodology based on concept-based interpretability to a model-free agent in Sokoban -- a commonly used benchmark for studying planning. Specifically, we demonstrate that DRC, a generic model-free agent introduced by Guez et al. (2019), uses learned concept representations to internally formulate plans that both predict the long-term effects of actions on the environment and influence action selection. Our methodology involves: (1) probing for planning-relevant concepts, (2) investigating plan formation within the agent's representations, and (3) verifying that discovered plans (in the agent's representations) have a causal effect on the agent's behavior through interventions. We also show that the emergence of these plans coincides with the emergence of a planning-like property: the ability to benefit from additional test-time compute. Finally, we perform a qualitative analysis of the planning algorithm learned by the agent and discover a strong resemblance to parallelized bidirectional search. Our findings advance understanding of the internal mechanisms underlying planning behavior in agents, which is important given the recent trend of emergent planning and reasoning capabilities in LLMs through RL