As large language models (LLMs) become more capable and agentic, the requirement for trust in their outputs grows significantly, yet at the same time concerns have been mounting that models may learn to lie in pursuit of their goals. To address these concerns, a body of work has emerged around the notion of "honesty" in LLMs, along with interventions aimed at mitigating deceptive behaviors. However, evaluations of honesty are currently highly limited, with no benchmark combining large scale and applicability to all models. Moreover, many benchmarks claiming to measure honesty in fact simply measure accuracy--the correctness of a model's beliefs--in disguise. In this work, we introduce a large-scale human-collected dataset for measuring honesty directly, allowing us to disentangle accuracy from honesty for the first time. Across a diverse set of LLMs, we find that while larger models obtain higher accuracy on our benchmark, they do not become more honest. Surprisingly, while most frontier LLMs obtain high scores on truthfulness benchmarks, we find a substantial propensity in frontier LLMs to lie when pressured to do so, resulting in low honesty scores on our benchmark. We find that simple methods, such as representation engineering interventions, can improve honesty. These results underscore the growing need for robust evaluations and effective interventions to ensure LLMs remain trustworthy.
Agents based on large language models (LLMs) have demonstrated strong capabilities in a wide range of complex, real-world applications. However, LLM agents with a compromised memory bank may easily produce harmful outputs when the past records retrieved for demonstration are malicious. In this paper, we propose a novel Memory INJection Attack, MINJA, that enables the injection of malicious records into the memory bank by only interacting with the agent via queries and output observations. These malicious records are designed to elicit a sequence of malicious reasoning steps leading to undesirable agent actions when executing the victim user's query. Specifically, we introduce a sequence of bridging steps to link the victim query to the malicious reasoning steps. During the injection of the malicious record, we propose an indication prompt to guide the agent to autonomously generate our designed bridging steps. We also propose a progressive shortening strategy that gradually removes the indication prompt, such that the malicious record will be easily retrieved when processing the victim query comes after. Our extensive experiments across diverse agents demonstrate the effectiveness of MINJA in compromising agent memory. With minimal requirements for execution, MINJA enables any user to influence agent memory, highlighting practical risks of LLM agents.
LLM-based multi-agent systems (MAS) have shown significant potential in tackling diverse tasks. However, to design effective MAS, existing approaches heavily rely on manual configurations or multiple calls of advanced LLMs, resulting in inadaptability and high inference costs. In this paper, we simplify the process of building an MAS by reframing it as a generative language task, where the input is a user query and the output is a corresponding MAS. To address this novel task, we unify the representation of MAS as executable code and propose a consistency-oriented data construction pipeline to create a high-quality dataset comprising coherent and consistent query-MAS pairs. Using this dataset, we train MAS-GPT, an open-source medium-sized LLM that is capable of generating query-adaptive MAS within a single LLM inference. The generated MAS can be seamlessly applied to process user queries and deliver high-quality responses. Extensive experiments on 9 benchmarks and 5 LLMs show that the proposed MAS-GPT consistently outperforms 10+ baseline MAS methods on diverse settings, indicating MAS-GPT's high effectiveness, efficiency and strong generalization ability. Code will be available at https://github.com/rui-ye/MAS-GPT.
We present Attentive Reasoning Queries (ARQs), a novel structured reasoning approach that significantly improves instruction-following in Large Language Models through domain-specialized reasoning blueprints. While LLMs demonstrate remarkable capabilities across diverse tasks, they often fail to maintain adherence to complex, use-case-specific instructions during multi-turn conversations, presenting challenges for business-critical applications. ARQs address this limitation by guiding LLMs through systematic reasoning steps with targeted queries that reinstate critical instructions and facilitate intermediate reasoning throughout the completion process. In extensive testing within Parlant, our framework for reliable customer-facing agents in which ARQs were born out of necessity, they achieved a 90.2% success rate across 87 test scenarios, outperforming both Chain-of-Thought reasoning (86.1%) and direct response generation (81.5%). ARQs showed particular strength in addressing persistent failure modes like guideline re-application and hallucination prevention. Our analysis also revealed that ARQs can potentially be more computationally efficient than free-form reasoning when carefully designed. These findings demonstrate that structured reasoning approaches provide effective mechanisms for controlling how LLMs process information and make decisions in complex scenarios.
Large Language Models (LLMs) have shown promise in software vulnerability detection, particularly on function-level benchmarks like Devign and BigVul. However, real-world detection requires interprocedural analysis, as vulnerabilities often emerge through multi-hop function calls rather than isolated functions. While repository-level benchmarks like ReposVul and VulEval introduce interprocedural context, they remain computationally expensive, lack pairwise evaluation of vulnerability fixes, and explore limited context retrieval, limiting their practicality. We introduce JitVul, a JIT vulnerability detection benchmark linking each function to its vulnerability-introducing and fixing commits. Built from 879 CVEs spanning 91 vulnerability types, JitVul enables comprehensive evaluation of detection capabilities. Our results show that ReAct Agents, leveraging thought-action-observation and interprocedural context, perform better than LLMs in distinguishing vulnerable from benign code. While prompting strategies like Chain-of-Thought help LLMs, ReAct Agents require further refinement. Both methods show inconsistencies, either misidentifying vulnerabilities or over-analyzing security guards, indicating significant room for improvement.
Recent advancements in Large Language Model(LLM)-based Multi-Agent Systems(MAS) have demonstrated remarkable potential for tackling complex decision-making tasks. However, existing frameworks inevitably rely on serialized execution paradigms, where agents must complete sequential LLM planning before taking action. This fundamental constraint severely limits real-time responsiveness and adaptation, which is crucial in dynamic environments with ever-changing scenarios. In this paper, we propose a novel parallelized planning-acting framework for LLM-based MAS, featuring a dual-thread architecture with interruptible execution to enable concurrent planning and acting. Specifically, our framework comprises two core threads:(1) a planning thread driven by a centralized memory system, maintaining synchronization of environmental states and agent communication to support dynamic decision-making; and (2) an acting thread equipped with a comprehensive skill library, enabling automated task execution through recursive decomposition. Extensive experiments on challenging Minecraft demonstrate the effectiveness of the proposed framework.
Molecular optimization is a crucial yet complex and time-intensive process that often acts as a bottleneck for drug development. Traditional methods rely heavily on trial and error, making multi-objective optimization both time-consuming and resource-intensive. Current AI-based methods have shown limited success in handling multi-objective optimization tasks, hampering their practical utilization. To address this challenge, we present MultiMol, a collaborative large language model (LLM) system designed to guide multi-objective molecular optimization. MultiMol comprises two agents, including a data-driven worker agent and a literature-guided research agent. The data-driven worker agent is a large language model being fine-tuned to learn how to generate optimized molecules considering multiple objectives, while the literature-guided research agent is responsible for searching task-related literature to find useful prior knowledge that facilitates identifying the most promising optimized candidates. In evaluations across six multi-objective optimization tasks, MultiMol significantly outperforms existing methods, achieving a 82.30% success rate, in sharp contrast to the 27.50% success rate of current strongest methods. To further validate its practical impact, we tested MultiMol on two real-world challenges. First, we enhanced the selectivity of Xanthine Amine Congener (XAC), a promiscuous ligand that binds both A1R and A2AR, successfully biasing it towards A1R. Second, we improved the bioavailability of Saquinavir, an HIV-1 protease inhibitor with known bioavailability limitations. Overall, these results indicate that MultiMol represents a highly promising approach for multi-objective molecular optimization, holding great potential to accelerate the drug development process and contribute to the advancement of pharmaceutical research.
The prevailing paradigm in the domain of Open-Domain Dialogue agents predominantly focuses on the English language, encompassing both models and datasets. Furthermore, the financial and temporal investments required for crowdsourcing such datasets for finetuning are substantial, particularly when multiple languages are involved. Fortunately, advancements in Large Language Models (LLMs) have unveiled a plethora of possibilities across diverse tasks. Specifically, instruction-tuning has enabled LLMs to execute tasks based on natural language instructions, occasionally surpassing the performance of human crowdworkers. Additionally, these models possess the capability to function in various languages within a single thread. Consequently, to generate new samples in different languages, we propose leveraging these capabilities to replicate the data collection process. We introduce a pipeline for generating Open-Domain Dialogue data in multiple Target Languages using LLMs, with demonstrations provided in a unique Source Language. By eschewing explicit Machine Translation in this approach, we enhance the adherence to language-specific nuances. We apply this methodology to the PersonaChat dataset. To enhance the openness of generated dialogues and mimic real life scenarii, we added the notion of speech events corresponding to the type of conversation the speakers are involved in and also that of common ground which represents the premises of a conversation.
Large language models (LLMs) have recently demonstrated remarkable capabilities across domains, tasks, and languages (e.g., ChatGPT and GPT-4), reviving the research of general autonomous agents with human-like cognitive abilities.Such human-level agents require semantic comprehension and instruction-following capabilities, which exactly fall into the strengths of LLMs.Although there have been several initial attempts to build human-level agents based on LLMs, the theoretical foundation remains a challenging open problem. In this paper, we propose a novel theoretical cognitive architecture, the Unified Mind Model (UMM), which offers guidance to facilitate the rapid creation of autonomous agents with human-level cognitive abilities. Specifically, our UMM starts with the global workspace theory and further leverage LLMs to enable the agent with various cognitive abilities, such as multi-modal perception, planning, reasoning, tool use, learning, memory, reflection and motivation. Building upon UMM, we then develop an agent-building engine, MindOS, which allows users to quickly create domain-/task-specific autonomous agents without any programming effort.
How capable are large language models (LLMs) in the domain of taxation? Although numerous studies have explored the legal domain in general, research dedicated to taxation remain scarce. Moreover, the datasets used in these studies are either simplified, failing to reflect the real-world complexities, or unavailable as open source. To address this gap, we introduce PLAT, a new benchmark designed to assess the ability of LLMs to predict the legitimacy of additional tax penalties. PLAT is constructed to evaluate LLMs' understanding of tax law, particularly in cases where resolving the issue requires more than just applying related statutes. Our experiments with six LLMs reveal that their baseline capabilities are limited, especially when dealing with conflicting issues that demand a comprehensive understanding. However, we found that enabling retrieval, self-reasoning, and discussion among multiple agents with specific role assignments, this limitation can be mitigated.
Automatic evaluation for Open Domain Event Detection (ODED) is a highly challenging task, because ODED is characterized by a vast diversity of un-constrained output labels from various domains. Nearly all existing evaluation methods for ODED usually first construct evaluation benchmarks with limited labels and domain coverage, and then evaluate ODED methods using metrics based on token-level label matching rules. However, this kind of evaluation framework faces two issues: (1) The limited evaluation benchmarks lack representatives of the real world, making it difficult to accurately reflect the performance of various ODED methods in real-world scenarios; (2) Evaluation metrics based on token-level matching rules fail to capture semantic similarity between predictions and golden labels. To address these two problems above, we propose a scalable and reliable Semantic-level Evaluation framework for Open domain Event detection (SEOE) by constructing a more representative evaluation benchmark and introducing a semantic evaluation metric. Specifically, our proposed framework first constructs a scalable evaluation benchmark that currently includes 564 event types covering 7 major domains, with a cost-effective supplementary annotation strategy to ensure the benchmark's representativeness. The strategy also allows for the supplement of new event types and domains in the future. Then, the proposed SEOE leverages large language models (LLMs) as automatic evaluation agents to compute a semantic F1-score, incorporating fine-grained definitions of semantically similar labels to enhance the reliability of the evaluation. Extensive experiments validate the representatives of the benchmark and the reliability of the semantic evaluation metric. Existing ODED methods are thoroughly evaluated, and the error patterns of predictions are analyzed, revealing several insightful findings.
With the rise of large language models (LLMs), there has been growing interest in Graph Foundation Models (GFMs) for graph-based tasks. By leveraging LLMs as predictors, GFMs have demonstrated impressive generalizability across various tasks and datasets. However, existing research on LLMs as predictors has predominantly focused on static graphs, leaving their potential in dynamic graph prediction unexplored. In this work, we pioneer using LLMs for predictive tasks on dynamic graphs. We identify two key challenges: the constraints imposed by context length when processing large-scale historical data and the significant variability in domain characteristics, both of which complicate the development of a unified predictor. To address these challenges, we propose the GraphAgent-Dynamic (GAD) Framework, a multi-agent system that leverages collaborative LLMs. In contrast to using a single LLM as the predictor, GAD incorporates global and local summary agents to generate domain-specific knowledge, enhancing its transferability across domains. Additionally, knowledge reflection agents enable adaptive updates to GAD's knowledge, maintaining a unified and self-consistent architecture. In experiments, GAD demonstrates performance comparable to or even exceeds that of full-supervised graph neural networks without dataset-specific training. Finally, to enhance the task-specific performance of LLM-based predictors, we discuss potential improvements, such as dataset-specific fine-tuning to LLMs. By developing tailored strategies for different tasks, we provide new insights for the future design of LLM-based predictors.
Solving mathematical problems using computer-verifiable languages like Lean has significantly impacted mathematical and computer science communities. State-of-the-art methods utilize single Large Language Models (LLMs) as agents or provers to either generate complete proof or perform tree searches. However, single-agent methods inherently lack a structured way to combine high-level reasoning in Natural Language (NL) with Formal Language (FL) verification feedback. To solve these issues, we propose MA-LoT: Multi-Agent Lean-based Long Chain-of-Thought framework, (to the best of our knowledge), the first multi-agent framework for Lean4 theorem proving that balance high-level NL reasoning and FL verification in Long CoT. Using this structured interaction, our approach enables deeper insights and long-term coherence in proof generation, with which past methods struggle. We do this by leveraging emergent formal reasoning ability in Long CoT using our novel LoT-Transfer Learning training-inference pipeline. Extensive experiments show that our framework achieves 54.51% accuracy rate on the Lean4 version of MiniF2F-Test dataset, largely outperforming GPT-4 (22.95%), single-agent tree search (InternLM-Step-Prover, 50.70%), and whole-proof generation (DeepSeek-Prover-v1.5, 48.36%) baselines. Furthermore, our findings highlight the potential of combining Long CoT with formal verification for a more insightful generation in a broader perspective.
Data wrangling is a time-consuming and challenging task in a data science pipeline. While many tools have been proposed to automate or facilitate data wrangling, they often misinterpret user intent, especially in complex tasks. We propose Dango, a mixed-initiative multi-agent system for data wrangling. Compared to existing tools, Dango enhances user communication of intent by allowing users to demonstrate on multiple tables and use natural language prompts in a conversation interface, enabling users to clarify their intent by answering LLM-posed multiple-choice clarification questions, and providing multiple forms of feedback such as step-by-step natural language explanations and data provenance to help users evaluate the data wrangling scripts. We conducted a within-subjects user study with 38 participants and demonstrated that Dango's features can significantly improve intent clarification, accuracy, and efficiency in data wrangling. Furthermore, we demonstrated the generalizability of Dango by applying it to a broader set of data wrangling tasks.
Large language models (LLMs), initially developed for generative AI, are now evolving into agentic AI systems, which make decisions in complex, real-world contexts. Unfortunately, while their generative capabilities are well-documented, their decision-making processes remain poorly understood. This is particularly evident when models are handling exceptions, a critical and challenging aspect of decision-making made relevant by the inherent incompleteness of contracts. Here we demonstrate that LLMs, even ones that excel at reasoning, deviate significantly from human judgments because they adhere strictly to policies, even when such adherence is impractical, suboptimal, or even counterproductive. We then evaluate three approaches to tuning AI agents to handle exceptions: ethical framework prompting, chain-of-thought reasoning, and supervised fine-tuning. We find that while ethical framework prompting fails and chain-of-thought prompting provides only slight improvements, supervised fine-tuning, specifically with human explanations, yields markedly better results. Surprisingly, in our experiments, supervised fine-tuning even enabled models to generalize human-like decision-making to novel scenarios, demonstrating transfer learning of human-aligned decision-making across contexts. Furthermore, fine-tuning with explanations, not just labels, was critical for alignment, suggesting that aligning LLMs with human judgment requires explicit training on how decisions are made, not just which decisions are made. These findings highlight the need to address LLMs' shortcomings in handling exceptions in order to guide the development of agentic AI toward models that can effectively align with human judgment and simultaneously adapt to novel contexts.
Metaphorical expressions are abundant in Traditional Chinese Medicine (TCM), conveying complex disease mechanisms and holistic health concepts through culturally rich and often abstract terminology. Bridging these metaphors to anatomically driven Western medical (WM) concepts poses significant challenges for both automated language processing and real-world clinical practice. To address this gap, we propose a novel multi-agent and chain-of-thought (CoT) framework designed to interpret TCM metaphors accurately and map them to WM pathophysiology. Specifically, our approach combines domain-specialized agents (TCM Expert, WM Expert) with a Coordinator Agent, leveraging stepwise chain-of-thought prompts to ensure transparent reasoning and conflict resolution. We detail a methodology for building a metaphor-rich TCM dataset, discuss strategies for effectively integrating multi-agent collaboration and CoT reasoning, and articulate the theoretical underpinnings that guide metaphor interpretation across distinct medical paradigms. We present a comprehensive system design and highlight both the potential benefits and limitations of our approach, while leaving placeholders for future experimental validation. Our work aims to support clinical decision-making, cross-system educational initiatives, and integrated healthcare research, ultimately offering a robust scaffold for reconciling TCM's symbolic language with the mechanistic focus of Western medicine.
To improve stock trend predictions and support personalized investment decisions, this paper proposes FinArena, a novel Human-Agent collaboration framework. Inspired by the mixture of experts (MoE) approach, FinArena combines multimodal financial data analysis with user interaction. The human module features an interactive interface that captures individual risk preferences, allowing personalized investment strategies. The machine module utilizes a Large Language Model-based (LLM-based) multi-agent system to integrate diverse data sources, such as stock prices, news articles, and financial statements. To address hallucinations in LLMs, FinArena employs the adaptive Retrieval-Augmented Generative (RAG) method for processing unstructured news data. Finally, a universal expert agent makes investment decisions based on the features extracted from multimodal data and investors' individual risk preferences. Extensive experiments show that FinArena surpasses both traditional and state-of-the-art benchmarks in stock trend prediction and yields promising results in trading simulations across various risk profiles. These findings highlight FinArena's potential to enhance investment outcomes by aligning strategic insights with personalized risk considerations.
Recent advancements in large language models (LLMs) have enabled LLM-based agents to successfully tackle interactive planning tasks. However, despite their successes, existing approaches often suffer from planning hallucinations and require retraining for each new agent. To address these challenges, we propose the Meta Plan Optimization (MPO) framework, which enhances agent planning capabilities by directly incorporating explicit guidance. Unlike previous methods that rely on complex knowledge, which either require significant human effort or lack quality assurance, MPO leverages high-level general guidance through meta plans to assist agent planning and enables continuous optimization of the meta plans based on feedback from the agent's task execution. Our experiments conducted on two representative tasks demonstrate that MPO significantly outperforms existing baselines. Moreover, our analysis indicates that MPO provides a plug-and-play solution that enhances both task completion efficiency and generalization capabilities in previous unseen scenarios.
Playing games has a long history of describing intricate interactions in simplified forms. In this paper we explore if large language models (LLMs) can play games, investigating their capabilities for randomisation and strategic adaptation through both simultaneous and sequential game interactions. We focus on GPT-4o-Mini-2024-08-17 and test two games between LLMs: Rock Paper Scissors (RPS) and games of strategy (Prisoners Dilemma PD). LLMs are often described as stochastic parrots, and while they may indeed be parrots, our results suggest that they are not very stochastic in the sense that their outputs - when prompted to be random - are often very biased. Our research reveals that LLMs appear to develop loss aversion strategies in repeated games, with RPS converging to stalemate conditions while PD shows systematic shifts between cooperative and competitive outcomes based on prompt design. We detail programmatic tools for independent agent interactions and the Agentic AI challenges faced in implementation. We show that LLMs can indeed play games, just not very well. These results have implications for the use of LLMs in multi-agent LLM systems and showcase limitations in current approaches to model output for strategic decision-making.
Large language model (LLM) agents typically adopt a step-by-step reasoning framework, in which they interleave the processes of thinking and acting to accomplish the given task. However, this paradigm faces a deep-rooted one-pass issue whereby each generated intermediate thought is plugged into the trajectory regardless of its correctness, which can cause irreversible error propagation. To address the issue, this paper proposes a novel framework called Generator-Assistant Stepwise Rollback (GA-Rollback) to induce better decision-making for LLM agents. Particularly, GA-Rollback utilizes a generator to interact with the environment and an assistant to examine each action produced by the generator, where the assistant triggers a rollback operation upon detection of incorrect actions. Moreover, we introduce two additional strategies tailored for the rollback scenario to further improve its effectiveness. Extensive experiments show that GA-Rollback achieves significant improvements over several strong baselines on three widely used benchmarks. Our analysis further reveals that GA-Rollback can function as a robust plug-and-play module, integrating seamlessly with other methods.
Time-series Generation (TSG) is a prominent research area with broad applications in simulations, data augmentation, and counterfactual analysis. While existing methods have shown promise in unconditional single-domain TSG, real-world applications demand for cross-domain approaches capable of controlled generation tailored to domain-specific constraints and instance-level requirements. In this paper, we argue that text can provide semantic insights, domain information and instance-specific temporal patterns, to guide and improve TSG. We introduce ``Text-Controlled TSG'', a task focused on generating realistic time series by incorporating textual descriptions. To address data scarcity in this setting, we propose a novel LLM-based Multi-Agent framework that synthesizes diverse, realistic text-to-TS datasets. Furthermore, we introduce BRIDGE, a hybrid text-controlled TSG framework that integrates semantic prototypes with text description for supporting domain-level guidance. This approach achieves state-of-the-art generation fidelity on 11 of 12 datasets, and improves controllability by 12.52% on MSE and 6.34% MAE compared to no text input generation, highlighting its potential for generating tailored time-series data.
Recommendation agents leverage large language models for user modeling LLM UM to construct textual personas guiding alignment with real users. However existing LLM UM methods struggle with long user generated content UGC due to context limitations and performance degradation. To address this sampling strategies prioritize relevance or recency are often applied yet they inevitably neglect the diverse user interests embedded within the discarded behaviors resulting in incomplete modeling and degraded profiling quality. Furthermore relevance based sampling requires real time retrieval forcing the user modeling process to operate online which introduces significant latency overhead. In this paper we propose PersonaX an agent agnostic LLM UM framework that tackles these challenges through sub behavior sequence SBS selection and offline multi persona construction. PersonaX extracts compact SBS segments offline to capture diverse user interests generating fine grained textual personas that are cached for efficient online retrieval. This approach ensures that the user persona used for prompting remains highly relevant to the current context while eliminating the need for online user modeling. For SBS selection we ensure both efficiency length less than five and high representational quality by balancing prototypicality and diversity within the sampled data. Extensive experiments validate the effectiveness and versatility of PersonaX in high quality user profiling. Utilizing only 30 to 50 percent of the behavioral data with a sequence length of 480 integrating PersonaX with AgentCF yields an absolute performance improvement of 3 to 11 percent while integration with Agent4Rec results in a gain of 10 to 50 percent. PersonaX as an agent agnostic framework sets a new benchmark for scalable user modeling paving the way for more accurate and efficient LLM driven recommendation agents.
Multi-agent systems have emerged as a promising approach for enhancing the reasoning capabilities of large language models in complex problem-solving. However, current MAS frameworks are limited by poor flexibility and scalability, with underdeveloped optimization strategies. To address these challenges, we propose ReSo, which integrates task graph generation with a reward-driven two-stage agent selection process. The core of ReSo is the proposed Collaborative Reward Model, which can provide fine-grained reward signals for MAS cooperation for optimization. We also introduce an automated data synthesis framework for generating MAS benchmarks, without human annotations. Experimentally, ReSo matches or outperforms existing methods. ReSo achieves \textbf{33.7\%} and \textbf{32.3\%} accuracy on Math-MAS and SciBench-MAS SciBench, while other methods completely fail. Code is available at: \href{https://github.com/hengzzzhou/ReSo}{ReSo}
We introduce a novel question-answering (QA) dataset using echocardiogram reports sourced from the Medical Information Mart for Intensive Care database. This dataset is specifically designed to enhance QA systems in cardiology, consisting of 771,244 QA pairs addressing a wide array of cardiac abnormalities and their severity. We compare large language models (LLMs), including open-source and biomedical-specific models for zero-shot evaluation, and closed-source models for zero-shot and three-shot evaluation. Our results show that fine-tuning LLMs improves performance across various QA metrics, validating the value of our dataset. Clinicians also qualitatively evaluate the best-performing model to assess the LLM responses for correctness. Further, we conduct fine-grained fairness audits to assess the bias-performance trade-off of LLMs across various social determinants of health. Our objective is to propel the field forward by establishing a benchmark for LLM AI agents aimed at supporting clinicians with cardiac differential diagnoses, thereby reducing the documentation burden that contributes to clinician burnout and enabling healthcare professionals to focus more on patient care.
Recent advancements in Large Language Models (LLMs) have led to the development of intelligent LLM-based agents capable of interacting with graphical user interfaces (GUIs). These agents demonstrate strong reasoning and adaptability, enabling them to perform complex tasks that traditionally required predefined rules. However, the reliance on step-by-step reasoning in LLM-based agents often results in inefficiencies, particularly for routine tasks. In contrast, traditional rule-based systems excel in efficiency but lack the intelligence and flexibility to adapt to novel scenarios. To address this challenge, we propose a novel evolutionary framework for GUI agents that enhances operational efficiency while retaining intelligence and flexibility. Our approach incorporates a memory mechanism that records the agent's task execution history. By analyzing this history, the agent identifies repetitive action sequences and evolves high-level actions that act as shortcuts, replacing these low-level operations and improving efficiency. This allows the agent to focus on tasks requiring more complex reasoning, while simplifying routine actions. Experimental results on multiple benchmark tasks demonstrate that our approach significantly outperforms existing methods in both efficiency and accuracy. The code will be open-sourced to support further research.
While Large Language Model-based agents have demonstrated substantial progress in task completion, existing evaluation benchmarks tend to overemphasize single-task performance, with insufficient attention given to the crucial aspects of multitask planning and execution efficiency required in real-world scenarios. To bridge this gap, we present Recipe2Plan, a novel benchmark framework based on real-world cooking scenarios. Unlike conventional benchmarks, Recipe2Plan challenges agents to optimize cooking time through parallel task execution while respecting temporal constraints i.e. specific actions need to be performed within a particular time intervals following the preceding steps. Overly aggressive local parallelization may disrupt this constraint, potentially compromising the entire cooking process. This strict time constraint between actions raises a unique challenge for agents to balance between maximizing concurrent operations and adhering to critical timing constraints. Extensive experiments with state-of-the-art models reveal challenges in maintaining this balance between efficiency and feasibility. The results highlight the need for improved temporal awareness and global multitasking capabilities in large language models. We open-source our benchmark and code at https://github.com/WilliamZR/Recipe2Plan.
Large Language Model (LLM) agents have demonstrated remarkable generalization capabilities across multi-domain tasks. Existing agent tuning approaches typically employ supervised finetuning on entire expert trajectories. However, behavior-cloning of full trajectories can introduce expert bias and weaken generalization to states not covered by the expert data. Additionally, critical steps, such as planning, complex reasoning for intermediate subtasks, and strategic decision-making, are essential to success in agent tasks, so learning these steps is the key to improving LLM agents. For more effective and efficient agent tuning, we propose ATLaS that identifies the critical steps in expert trajectories and finetunes LLMs solely on these steps with reduced costs. By steering the training's focus to a few critical steps, our method mitigates the risk of overfitting entire trajectories and promotes generalization across different environments and tasks. In extensive experiments, an LLM finetuned on only 30% critical steps selected by ATLaS outperforms the LLM finetuned on all steps and recent open-source LLM agents. ATLaS maintains and improves base LLM skills as generalist agents interacting with diverse environments.
In this paper, we present Corridor-Agent (CorrA), a framework that integrates large language models (LLMs) with model predictive control (MPC) to address the challenges of dynamic obstacle avoidance in autonomous vehicles. Our approach leverages LLM reasoning ability to generate appropriate parameters for sigmoid-based boundary functions that define safe corridors around obstacles, effectively reducing the state-space of the controlled vehicle. The proposed framework adjusts these boundaries dynamically based on real-time vehicle data that guarantees collision-free trajectories while also ensuring both computational efficiency and trajectory optimality. The problem is formulated as an optimal control problem and solved with differential dynamic programming (DDP) for constrained optimization, and the proposed approach is embedded within an MPC framework. Extensive simulation and real-world experiments demonstrate that the proposed framework achieves superior performance in maintaining safety and efficiency in complex, dynamic environments compared to a baseline MPC approach.
Fully autonomous teams of LLM-powered AI agents are emerging that collaborate to perform complex tasks for users. What challenges do developers face when trying to build and debug these AI agent teams? In formative interviews with five AI agent developers, we identify core challenges: difficulty reviewing long agent conversations to localize errors, lack of support in current tools for interactive debugging, and the need for tool support to iterate on agent configuration. Based on these needs, we developed an interactive multi-agent debugging tool, AGDebugger, with a UI for browsing and sending messages, the ability to edit and reset prior agent messages, and an overview visualization for navigating complex message histories. In a two-part user study with 14 participants, we identify common user strategies for steering agents and highlight the importance of interactive message resets for debugging. Our studies deepen understanding of interfaces for debugging increasingly important agentic workflows.
Pro-environmental behavior (PEB) is vital to combat climate change, yet turning awareness into intention and action remains elusive. We explore large language models (LLMs) as tools to promote PEB, comparing their impact across 3,200 participants: real humans (n=1,200), simulated humans based on actual participant data (n=1,200), and fully synthetic personas (n=1,200). All three participant groups faced personalized or standard chatbots, or static statements, employing four persuasion strategies (moral foundations, future self-continuity, action orientation, or "freestyle" chosen by the LLM). Results reveal a "synthetic persuasion paradox": synthetic and simulated agents significantly affect their post-intervention PEB stance, while human responses barely shift. Simulated participants better approximate human trends but still overestimate effects. This disconnect underscores LLM's potential for pre-evaluating PEB interventions but warns of its limits in predicting real-world behavior. We call for refined synthetic modeling and sustained and extended human trials to align conversational AI's promise with tangible sustainability outcomes.