As LLM agents grow more capable of causing harm autonomously, AI developers will rely on increasingly sophisticated control measures to prevent possibly misaligned agents from causing harm. AI developers could demonstrate that their control measures are sufficient by running control evaluations: testing exercises in which a red team produces agents that try to subvert control measures. To ensure control evaluations accurately capture misalignment risks, the affordances granted to this red team should be adapted to the capability profiles of the agents to be deployed under control measures. In this paper we propose a systematic framework for adapting affordances of red teams to advancing AI capabilities. Rather than assuming that agents will always execute the best attack strategies known to humans, we demonstrate how knowledge of an agents's actual capability profile can inform proportional control evaluations, resulting in more practical and cost-effective control measures. We illustrate our framework by considering a sequence of five fictional models (M1-M5) with progressively advanced capabilities, defining five distinct AI control levels (ACLs). For each ACL, we provide example rules for control evaluation, control measures, and safety cases that could be appropriate. Finally, we show why constructing a compelling AI control safety case for superintelligent LLM agents will require research breakthroughs, highlighting that we might eventually need alternative approaches to mitigating misalignment risk.
Document-level context is crucial for handling discourse challenges in text-to-text document-level machine translation (MT). Despite the increased discourse challenges introduced by noise from automatic speech recognition (ASR), the integration of document-level context in speech translation (ST) remains insufficiently explored. In this paper, we develop DoCIA, an online framework that enhances ST performance by incorporating document-level context. DoCIA decomposes the ST pipeline into four stages. Document-level context is integrated into the ASR refinement, MT, and MT refinement stages through auxiliary LLM (large language model)-based modules. Furthermore, DoCIA leverages document-level information in a multi-level manner while minimizing computational overhead. Additionally, a simple yet effective determination mechanism is introduced to prevent hallucinations from excessive refinement, ensuring the reliability of the final results. Experimental results show that DoCIA significantly outperforms traditional ST baselines in both sentence and discourse metrics across four LLMs, demonstrating its effectiveness in improving ST performance.
Tracking financial investments in climate adaptation is a complex and expertise-intensive task, particularly for Early Warning Systems (EWS), which lack standardized financial reporting across multilateral development banks (MDBs) and funds. To address this challenge, we introduce an LLM-based agentic AI system that integrates contextual retrieval, fine-tuning, and multi-step reasoning to extract relevant financial data, classify investments, and ensure compliance with funding guidelines. Our study focuses on a real-world application: tracking EWS investments in the Climate Risk and Early Warning Systems (CREWS) Fund. We analyze 25 MDB project documents and evaluate multiple AI-driven classification methods, including zero-shot and few-shot learning, fine-tuned transformer-based classifiers, chain-of-thought (CoT) prompting, and an agent-based retrieval-augmented generation (RAG) approach. Our results show that the agent-based RAG approach significantly outperforms other methods, achieving 87\% accuracy, 89\% precision, and 83\% recall. Additionally, we contribute a benchmark dataset and expert-annotated corpus, providing a valuable resource for future research in AI-driven financial tracking and climate finance transparency.
Multiagent collaboration has emerged as a promising framework for enhancing the reasoning capabilities of large language models (LLMs). While this approach improves reasoning capability, it incurs substantial computational overhead due to iterative agent interactions. Furthermore, engaging in debates for queries that do not necessitate collaboration amplifies the risk of error generation. To address these challenges, we propose Debate Only When Necessary (DOWN), an adaptive multiagent debate framework that selectively activates the debate process based on the confidence score of the agent's initial response. For queries where debate is triggered, agents refine their outputs using responses from participating agents and their confidence scores. Experimental results demonstrate that this mechanism significantly improves efficiency while maintaining or even surpassing the performance of existing multiagent debate systems. We also find that confidence-guided debate mitigates error propagation and enhances the selective incorporation of reliable responses. These results establish DOWN as an optimization strategy for efficient and effective multiagent reasoning, facilitating the practical deployment of LLM-based collaboration.
Advances in Large Language Models (LLMs) paved the way for their emerging applications in various domains, such as human behavior simulations, where LLMs could augment human-generated data in social science research and machine learning model training. However, pretrained LLMs often fail to capture the behavioral diversity of target populations due to the inherent variability across individuals and groups. To address this, we propose \textit{Mixture of Personas} (MoP), a \textit{probabilistic} prompting method that aligns the LLM responses with the target population. MoP is a contextual mixture model, where each component is an LM agent characterized by a persona and an exemplar representing subpopulation behaviors. The persona and exemplar are randomly chosen according to the learned mixing weights to elicit diverse LLM responses during simulation. MoP is flexible, requires no model finetuning, and is transferable across base models. Experiments for synthetic data generation show that MoP outperforms competing methods in alignment and diversity metrics.
This paper introduces the art project The Dream Within Huang Long Cave, an AI-driven interactive and immersive narrative experience. The project offers new insights into AI technology, artistic practice, and psychoanalysis. Inspired by actual geographical landscapes and familial archetypes, the work combines psychoanalytic theory and computational technology, providing an artistic response to the concept of the non-existence of the Big Other. The narrative is driven by a combination of a large language model (LLM) and a realistic digital character, forming a virtual agent named YELL. Through dialogue and exploration within a cave automatic virtual environment (CAVE), the audience is invited to unravel the language puzzles presented by YELL and help him overcome his life challenges. YELL is a fictional embodiment of the Big Other, modeled after the artist's real father. Through a cross-temporal interaction with this digital father, the project seeks to deconstruct complex familial relationships. By demonstrating the non-existence of the Big Other, we aim to underscore the authenticity of interpersonal emotions, positioning art as a bridge for emotional connection and understanding within family dynamics.
Meat reduction benefits human and planetary health, but social norms keep meat central in shared meals. To date, the development of communication strategies that promote meat reduction while minimizing social costs has required the costly involvement of human participants at each stage of the process. We present work in progress on simulating multi-round dialogues on meat reduction between Generative Agents based on large language models (LLMs). We measure our main outcome using established psychological questionnaires based on the Theory of Planned Behavior and additionally investigate Social Costs. We find evidence that our preliminary simulations produce outcomes that are (i) consistent with theoretical expectations; and (ii) valid when compared to data from previous studies with human participants. Generative agent-based models are a promising tool for identifying novel communication strategies on meat reduction-tailored to highly specific participant groups-to then be tested in subsequent studies with human participants.
Detecting biases in structured data is a complex and time-consuming task. Existing automated techniques are limited in diversity of data types and heavily reliant on human case-by-case handling, resulting in a lack of generalizability. Currently, large language model (LLM)-based agents have made significant progress in data science, but their ability to detect data biases is still insufficiently explored. To address this gap, we introduce the first end-to-end, multi-agent synergy framework, BIASINSPECTOR, designed for automatic bias detection in structured data based on specific user requirements. It first develops a multi-stage plan to analyze user-specified bias detection tasks and then implements it with a diverse and well-suited set of tools. It delivers detailed results that include explanations and visualizations. To address the lack of a standardized framework for evaluating the capability of LLM agents to detect biases in data, we further propose a comprehensive benchmark that includes multiple evaluation metrics and a large set of test cases. Extensive experiments demonstrate that our framework achieves exceptional overall performance in structured data bias detection, setting a new milestone for fairer data applications.
Practitioners are increasingly turning to Extract-Load-Transform (ELT) pipelines with the widespread adoption of cloud data warehouses. However, designing these pipelines often involves significant manual work to ensure correctness. Recent advances in AI-based methods, which have shown strong capabilities in data tasks, such as text-to-SQL, present an opportunity to alleviate manual efforts in developing ELT pipelines. Unfortunately, current benchmarks in data engineering only evaluate isolated tasks, such as using data tools and writing data transformation queries, leaving a significant gap in evaluating AI agents for generating end-to-end ELT pipelines. To fill this gap, we introduce ELT-Bench, an end-to-end benchmark designed to assess the capabilities of AI agents to build ELT pipelines. ELT-Bench consists of 100 pipelines, including 835 source tables and 203 data models across various domains. By simulating realistic scenarios involving the integration of diverse data sources and the use of popular data tools, ELT-Bench evaluates AI agents' abilities in handling complex data engineering workflows. AI agents must interact with databases and data tools, write code and SQL queries, and orchestrate every pipeline stage. We evaluate two representative code agent frameworks, Spider-Agent and SWE-Agent, using six popular Large Language Models (LLMs) on ELT-Bench. The highest-performing agent, Spider-Agent Claude-3.7-Sonnet with extended thinking, correctly generates only 3.9% of data models, with an average cost of $4.30 and 89.3 steps per pipeline. Our experimental results demonstrate the challenges of ELT-Bench and highlight the need for a more advanced AI agent to reduce manual effort in ELT workflows. Our code and data are available at https://github.com/uiuc-kang-lab/ETL.git.
Efficiently leveraging of the capabilities of contemporary large language models (LLMs) is increasingly challenging, particularly when direct fine-tuning is expensive and often impractical. Existing training-free methods, including manually or automated designed workflows, typically demand substantial human effort or yield suboptimal results. This paper proposes Weak-for-Strong Harnessing (W4S), a novel framework that customizes smaller, cost-efficient language models to design and optimize workflows for harnessing stronger models. W4S formulates workflow design as a multi-turn markov decision process and introduces reinforcement learning for agentic workflow optimization (RLAO) to train a weak meta-agent. Through iterative interaction with the environment, the meta-agent learns to design increasingly effective workflows without manual intervention. Empirical results demonstrate the superiority of W4S that our 7B meta-agent, trained with just one GPU hour, outperforms the strongest baseline by 2.9% ~ 24.6% across eleven benchmarks, successfully elevating the performance of state-of-the-art models such as GPT-3.5-Turbo and GPT-4o. Notably, W4S exhibits strong generalization capabilities across both seen and unseen tasks, offering an efficient, high-performing alternative to directly fine-tuning strong models.
Recent advancements in large language models (LLMs) have revolutionized their ability to handle single-turn tasks, yet real-world applications demand sophisticated multi-turn interactions. This survey provides a comprehensive review of recent advancements in evaluating and enhancing multi-turn interactions in LLMs. Focusing on task-specific scenarios, from instruction following in diverse domains such as math and coding to complex conversational engagements in roleplay, healthcare, education, and even adversarial jailbreak settings, we systematically examine the challenges of maintaining context, coherence, fairness, and responsiveness over prolonged dialogues. The paper organizes current benchmarks and datasets into coherent categories that reflect the evolving landscape of multi-turn dialogue evaluation. In addition, we review a range of enhancement methodologies under multi-turn settings, including model-centric strategies (contextual learning, supervised fine-tuning, reinforcement learning, and new architectures), external integration approaches (memory-augmented, retrieval-based methods, and knowledge graph), and agent-based techniques for collaborative interactions. Finally, we discuss open challenges and propose future directions for research to further advance the robustness and effectiveness of multi-turn interactions in LLMs. Related resources and papers are available at https://github.com/yubol-cmu/Awesome-Multi-Turn-LLMs.
Current large language models (LLMs) are constrained by human-derived training data and limited by a single level of abstraction that impedes definitive truth judgments. This paper introduces a novel framework in which AI models autonomously generate and validate new knowledge through direct interaction with their environment. Central to this approach is an unbounded, ungamable numeric reward - such as annexed disk space or follower count - that guides learning without requiring human benchmarks. AI agents iteratively generate strategies and executable code to maximize this metric, with successful outcomes forming the basis for self-retraining and incremental generalisation. To mitigate model collapse and the warm start problem, the framework emphasizes empirical validation over textual similarity and supports fine-tuning via GRPO. The system architecture employs modular agents for environment analysis, strategy generation, and code synthesis, enabling scalable experimentation. This work outlines a pathway toward self-improving AI systems capable of advancing beyond human-imposed constraints toward autonomous general intelligence.
Cell type annotation is critical for understanding cellular heterogeneity. Based on single-cell RNA-seq data and deep learning models, good progress has been made in annotating a fixed number of cell types within a specific tissue. However, universal cell annotation, which can generalize across tissues, discover novel cell types, and extend to novel cell types, remains less explored. To fill this gap, this paper proposes scAgent, a universal cell annotation framework based on Large Language Models (LLMs). scAgent can identify cell types and discover novel cell types in diverse tissues; furthermore, it is data efficient to learn novel cell types. Experimental studies in 160 cell types and 35 tissues demonstrate the superior performance of scAgent in general cell-type annotation, novel cell discovery, and extensibility to novel cell type.
This paper proposes a highly robust autonomous agent framework based on the ReAct paradigm, designed to solve complex tasks through adaptive decision making and multi-agent collaboration. Unlike traditional frameworks that rely on fixed workflows generated by LLM-based planners, this framework dynamically generates next actions during agent execution based on prior trajectories, thereby enhancing its robustness. To address potential termination issues caused by adaptive execution paths, I propose a timely abandonment strategy incorporating a probabilistic penalty mechanism. For multi-agent collaboration, I introduce a memory transfer mechanism that enables shared and dynamically updated memory among agents. The framework's innovative timely abandonment strategy dynamically adjusts the probability of task abandonment via probabilistic penalties, allowing developers to balance conservative and exploratory tendencies in agent execution strategies by tuning hyperparameters. This significantly improves adaptability and task execution efficiency in complex environments. Additionally, agents can be extended through external tool integration, supported by modular design and MCP protocol compatibility, which enables flexible action space expansion. Through explicit division of labor, the multi-agent collaboration mechanism enables agents to focus on specific task components, thereby significantly improving execution efficiency and quality.
LLM-driven autonomous agents have emerged as a promising direction in recent years. However, many of these LLM agents are designed empirically or based on intuition, often lacking systematic design principles, which results in diverse agent structures with limited generality and scalability. In this paper, we advocate for building LLM agents by incorporating insights from computer systems. Inspired by the von Neumann architecture, we propose a structured framework for LLM agentic systems, emphasizing modular design and universal principles. Specifically, this paper first provides a comprehensive review of LLM agents from the computer system perspective, then identifies key challenges and future directions inspired by computer system design, and finally explores the learning mechanisms for LLM agents beyond the computer system. The insights gained from this comparative analysis offer a foundation for systematic LLM agent design and advancement.
Long video understanding has emerged as an increasingly important yet challenging task in computer vision. Agent-based approaches are gaining popularity for processing long videos, as they can handle extended sequences and integrate various tools to capture fine-grained information. However, existing methods still face several challenges: (1) they often rely solely on the reasoning ability of large language models (LLMs) without dedicated mechanisms to enhance reasoning in long video scenarios; and (2) they remain vulnerable to errors or noise from external tools. To address these issues, we propose a specialized chain-of-thought (CoT) process tailored for long video analysis. Our proposed CoT with plan-adjust mode enables the LLM to incrementally plan and adapt its information-gathering strategy. We further incorporate heuristic uncertainty estimation of both the LLM and external tools to guide the CoT process. This allows the LLM to assess the reliability of newly collected information, refine its collection strategy, and make more robust decisions when synthesizing final answers. Empirical experiments show that our uncertainty-aware CoT effectively mitigates noise from external tools, leading to more reliable outputs. We implement our approach in a system called VideoAgent2, which also includes additional modules such as general context acquisition and specialized tool design. Evaluation on three dedicated long video benchmarks (and their subsets) demonstrates that VideoAgent2 outperforms the previous state-of-the-art agent-based method, VideoAgent, by an average of 13.1% and achieves leading performance among all zero-shot approaches
Competitive Pok\'emon Singles (CPS) is a popular strategy game where players learn to exploit their opponent based on imperfect information in battles that can last more than one hundred stochastic turns. AI research in CPS has been led by heuristic tree search and online self-play, but the game may also create a platform to study adaptive policies trained offline on large datasets. We develop a pipeline to reconstruct the first-person perspective of an agent from logs saved from the third-person perspective of a spectator, thereby unlocking a dataset of real human battles spanning more than a decade that grows larger every day. This dataset enables a black-box approach where we train large sequence models to adapt to their opponent based solely on their input trajectory while selecting moves without explicit search of any kind. We study a progression from imitation learning to offline RL and offline fine-tuning on self-play data in the hardcore competitive setting of Pok\'emon's four oldest (and most partially observed) game generations. The resulting agents outperform a recent LLM Agent approach and a strong heuristic search engine. While playing anonymously in online battles against humans, our best agents climb to rankings inside the top 10% of active players.
The performance of large language models (LLMs) depends on how they are prompted, with choices spanning both the high-level prompting pattern (e.g., Zero-Shot, CoT, ReAct, ReWOO) and the specific prompt content (instructions and few-shot demonstrations). Manually tuning this combination is tedious, error-prone, and non-transferable across LLMs or tasks. Therefore, this paper proposes AutoPDL, an automated approach to discover good LLM agent configurations. Our method frames this as a structured AutoML problem over a combinatorial space of agentic and non-agentic prompting patterns and demonstrations, using successive halving to efficiently navigate this space. We introduce a library implementing common prompting patterns using the PDL prompt programming language. AutoPDL solutions are human-readable, editable, and executable PDL programs that use this library. This approach also enables source-to-source optimization, allowing human-in-the-loop refinement and reuse. Evaluations across three tasks and six LLMs (ranging from 8B to 70B parameters) show consistent accuracy gains ($9.5\pm17.5$ percentage points), up to 68.9pp, and reveal that selected prompting strategies vary across models and tasks.
The advances in vision-language models (VLMs) have led to a growing interest in autonomous driving to leverage their strong reasoning capabilities. However, extending these capabilities from 2D to full 3D understanding is crucial for real-world applications. To address this challenge, we propose OmniDrive, a holistic vision-language dataset that aligns agent models with 3D driving tasks through counterfactual reasoning. This approach enhances decision-making by evaluating potential scenarios and their outcomes, similar to human drivers considering alternative actions. Our counterfactual-based synthetic data annotation process generates large-scale, high-quality datasets, providing denser supervision signals that bridge planning trajectories and language-based reasoning. Futher, we explore two advanced OmniDrive-Agent frameworks, namely Omni-L and Omni-Q, to assess the importance of vision-language alignment versus 3D perception, revealing critical insights into designing effective LLM-agents. Significant improvements on the DriveLM Q\&A benchmark and nuScenes open-loop planning demonstrate the effectiveness of our dataset and methods.
Geospatial Copilots hold immense potential for automating Earth observation (EO) and climate monitoring workflows, yet their reliance on large-scale models such as GPT-4o introduces a paradox: tools intended for sustainability studies often incur unsustainable costs. Using agentic AI frameworks in geospatial applications can amass thousands of dollars in API charges or requires expensive, power-intensive GPUs for deployment, creating barriers for researchers, policymakers, and NGOs. Unfortunately, when geospatial Copilots are deployed with open language models (OLMs), performance often degrades due to their dependence on GPT-optimized logic. In this paper, we present Geo-OLM, a tool-augmented geospatial agent that leverages the novel paradigm of state-driven LLM reasoning to decouple task progression from tool calling. By alleviating the workflow reasoning burden, our approach enables low-resource OLMs to complete geospatial tasks more effectively. When downsizing to small models below 7B parameters, Geo-OLM outperforms the strongest prior geospatial baselines by 32.8% in successful query completion rates. Our method performs comparably to proprietary models achieving results within 10% of GPT-4o, while reducing inference costs by two orders of magnitude from \$500-\$1000 to under \$10. We present an in-depth analysis with geospatial downstream benchmarks, providing key insights to help practitioners effectively deploy OLMs for EO applications.
Although LLM-based agents have attracted significant attention in domains such as software engineering and machine learning research, their role in advancing combinatorial optimization (CO) remains relatively underexplored. This gap underscores the need for a deeper understanding of their potential in tackling structured, constraint-intensive problems-a pursuit currently limited by the absence of comprehensive benchmarks for systematic investigation. To address this, we introduce CO-Bench, a benchmark suite featuring 36 real-world CO problems drawn from a broad range of domains and complexity levels. CO-Bench includes structured problem formulations and curated data to support rigorous investigation of LLM agents. We evaluate multiple agent frameworks against established human-designed algorithms, revealing key strengths and limitations of current approaches and identifying promising directions for future research. CO-Bench is publicly available at https://github.com/sunnweiwei/CO-Bench.
Recently, researchers have proposed many multi-agent frameworks for function-level code generation, which aim to improve software development productivity by automatically generating function-level source code based on task descriptions. A typical multi-agent framework consists of Large Language Model (LLM)-based agents that are responsible for task planning, code generation, testing, debugging, etc. Studies have shown that existing multi-agent code generation frameworks perform well on ChatGPT. However, their generalizability across other foundation LLMs remains unexplored systematically. In this paper, we report an empirical study on the generalizability of four state-of-the-art multi-agent code generation frameworks across six open-source LLMs with varying parameter sizes, architectures, and performance levels. Our study reveals the unstable generalizability of existing frameworks on diverse foundation LLMs. Based on the findings obtained from the empirical study, we propose AdaCoder, a novel adaptive planning, multi-agent framework for function-level code generation. AdaCoder has two phases. Phase-1 is an initial code generation step without planning, which uses an LLM-based coding agent and a script-based testing agent to unleash LLM's native power, identify cases beyond LLM's power, and determine the errors hindering execution. Phase-2 adds a rule-based debugging agent and an LLM-based planning agent for iterative code generation with planning. Our evaluation shows that AdaCoder achieves higher generalizability on diverse LLMs. Compared to the best baseline MapCoder, AdaCoder is on average 27.69% higher in Pass@1, 16 times faster in inference, and 12 times lower in token consumption.
Learning open-vocabulary physical skills for simulated agents presents a significant challenge in artificial intelligence. Current reinforcement learning approaches face critical limitations: manually designed rewards lack scalability across diverse tasks, while demonstration-based methods struggle to generalize beyond their training distribution. We introduce GROVE, a generalized reward framework that enables open-vocabulary physical skill learning without manual engineering or task-specific demonstrations. Our key insight is that Large Language Models(LLMs) and Vision Language Models(VLMs) provide complementary guidance -- LLMs generate precise physical constraints capturing task requirements, while VLMs evaluate motion semantics and naturalness. Through an iterative design process, VLM-based feedback continuously refines LLM-generated constraints, creating a self-improving reward system. To bridge the domain gap between simulation and natural images, we develop Pose2CLIP, a lightweight mapper that efficiently projects agent poses directly into semantic feature space without computationally expensive rendering. Extensive experiments across diverse embodiments and learning paradigms demonstrate GROVE's effectiveness, achieving 22.2% higher motion naturalness and 25.7% better task completion scores while training 8.4x faster than previous methods. These results establish a new foundation for scalable physical skill acquisition in simulated environments.
Malicious examples are crucial for evaluating the robustness of machine learning algorithms under attack, particularly in Industrial Control Systems (ICS). However, collecting normal and attack data in ICS environments is challenging due to the scarcity of testbeds and the high cost of human expertise. Existing datasets are often limited by the domain expertise of practitioners, making the process costly and inefficient. The lack of comprehensive attack pattern data poses a significant problem for developing robust anomaly detection methods. In this paper, we propose a novel approach that combines data-centric and design-centric methodologies to generate attack patterns using large language models (LLMs). Our results demonstrate that the attack patterns generated by LLMs not only surpass the quality and quantity of those created by human experts but also offer a scalable solution that does not rely on expensive testbeds or pre-existing attack examples. This multi-agent based approach presents a promising avenue for enhancing the security and resilience of ICS environments.
Studying deception in AI agents is important and difficult due to the lack of model organisms and sandboxes that elicit the behavior without asking the model to act under specific conditions or inserting intentional backdoors. Extending upon $\textit{AmongAgents}$, a text-based social-deduction game environment, we aim to fix this by introducing Among Us as a rich sandbox where LLM-agents exhibit human-style deception naturally while they think, speak, and act with other agents or humans. We introduce Deception ELO as an unbounded measure of deceptive capability, suggesting that frontier models win more because they're better at deception, not at detecting it. We evaluate the effectiveness of AI safety techniques (LLM-monitoring of outputs, linear probes on various datasets, and sparse autoencoders) for detecting lying and deception in Among Us, and find that they generalize very well out-of-distribution. We open-source our sandbox as a benchmark for future alignment research and hope that this is a good testbed to improve safety techniques to detect and remove agentically-motivated deception, and to anticipate deceptive abilities in LLMs.
Assistive agents should be able to perform under-specified long-horizon tasks while respecting user preferences. We introduce Actively Discovering and Adapting to Preferences for any Task (ADAPT) -- a benchmark designed to evaluate agents' ability to adhere to user preferences across various household tasks through active questioning. Next, we propose Reflection-DPO, a novel training approach for adapting large language models (LLMs) to the task of active questioning. Reflection-DPO finetunes a 'student' LLM to follow the actions of a privileged 'teacher' LLM, and optionally ask a question to gather necessary information to better predict the teacher action. We find that prior approaches that use state-of-the-art LLMs fail to sufficiently follow user preferences in ADAPT due to insufficient questioning and poor adherence to elicited preferences. In contrast, Reflection-DPO achieves a higher rate of satisfying user preferences, outperforming a zero-shot chain-of-thought baseline by 6.1% on unseen users.
Understanding how humans collaborate and communicate in teams is essential for improving human-agent teaming and AI-assisted decision-making. However, relying solely on data from large-scale user studies is impractical due to logistical, ethical, and practical constraints, necessitating synthetic models of multiple diverse human behaviors. Recently, agents powered by Large Language Models (LLMs) have been shown to emulate human-like behavior in social settings. But, obtaining a large set of diverse behaviors requires manual effort in the form of designing prompts. On the other hand, Quality Diversity (QD) optimization has been shown to be capable of generating diverse Reinforcement Learning (RL) agent behavior. In this work, we combine QD optimization with LLM-powered agents to iteratively search for prompts that generate diverse team behavior in a long-horizon, multi-step collaborative environment. We first show, through a human-subjects experiment (n=54 participants), that humans exhibit diverse coordination and communication behavior in this domain. We then show that our approach can effectively replicate trends from human teaming data and also capture behaviors that are not easily observed without collecting large amounts of data. Our findings highlight the combination of QD and LLM-powered agents as an effective tool for studying teaming and communication strategies in multi-agent collaboration.
OLAF (Open Life Science Analysis Framework) is an open-source platform that enables researchers to perform bioinformatics analyses using natural language. By combining large language models (LLMs) with a modular agent-pipe-router architecture, OLAF generates and executes bioinformatics code on real scientific data, including formats like .h5ad. The system includes an Angular front end and a Python/Firebase backend, allowing users to run analyses such as single-cell RNA-seq workflows, gene annotation, and data visualization through a simple web interface. Unlike general-purpose AI tools, OLAF integrates code execution, data handling, and scientific libraries in a reproducible, user-friendly environment. It is designed to lower the barrier to computational biology for non-programmers and support transparent, AI-powered life science research.
Automated summarization of healthcare community question-answering forums is challenging due to diverse perspectives presented across multiple user responses to each question. The PerAnsSumm Shared Task was therefore proposed to tackle this challenge by identifying perspectives from different answers and then generating a comprehensive answer to the question. In this study, we address the PerAnsSumm Shared Task using two complementary paradigms: (i) a training-based approach through QLoRA fine-tuning of LLaMA-3.3-70B-Instruct, and (ii) agentic approaches including zero- and few-shot prompting with frontier LLMs (LLaMA-3.3-70B-Instruct and GPT-4o) and a Mixture-of-Agents (MoA) framework that leverages a diverse set of LLMs by combining outputs from multi-layer feedback aggregation. For perspective span identification/classification, GPT-4o zero-shot achieves an overall score of 0.57, substantially outperforming the 0.40 score of the LLaMA baseline. With a 2-layer MoA configuration, we were able to improve LLaMA performance up by 28 percent to 0.51. For perspective-based summarization, GPT-4o zero-shot attains an overall score of 0.42 compared to 0.28 for the best LLaMA zero-shot, and our 2-layer MoA approach boosts LLaMA performance by 32 percent to 0.37. Furthermore, in few-shot setting, our results show that the sentence-transformer embedding-based exemplar selection provides more gain than manually selected exemplars on LLaMA models, although the few-shot prompting is not always helpful for GPT-4o. The YaleNLP team's approach ranked the overall second place in the shared task.
This tutorial on adaptation of LLMs is designed to address the growing demand for models that go beyond the static capabilities of generic LLMs by providing an overview of dynamic, domain-specific, and task-adaptive LLM adaptation techniques. While general LLMs have demonstrated strong generalization across a variety of tasks, they often struggle to perform well in specialized domains such as finance, healthcare, and code generation for underrepresented languages. Additionally, their static nature limits their ability to evolve with the changing world, and they are often extremely large in size, making them impractical and costly to deploy at scale. As a result, the adaptation of LLMs has drawn much attention since the birth of LLMs and is of core importance, both for industry, which focuses on serving its targeted users, and academia, which can greatly benefit from small but powerful LLMs. To address this gap, this tutorial aims to provide an overview of the LLM adaptation techniques. We start with an introduction to LLM adaptation, from both the data perspective and the model perspective. We then emphasize how the evaluation metrics and benchmarks are different from other techniques. After establishing the problems, we explore various adaptation techniques. We categorize adaptation techniques into two main families. The first is parametric knowledge adaptation, which focuses on updating the parametric knowledge within LLMs. Additionally, we will discuss real-time adaptation techniques, including model editing, which allows LLMs to be updated dynamically in production environments. The second kind of adaptation is semi-parametric knowledge adaptation, where the goal is to update LLM parameters to better leverage external knowledge or tools through techniques like retrieval-augmented generation (RAG) and agent-based systems.