In e-commerce, behavioral data is collected for decision making which can be costly and slow. Simulation with LLM powered agents is emerging as a promising alternative for representing human population behavior. However, LLMs are known to exhibit certain biases, such as brand bias, review rating bias and limited representation of certain groups in the population, hence they need to be carefully benchmarked and aligned to user behavior. Ultimately, our goal is to synthesise an agent population and verify that it collectively approximates a real sample of humans. To this end, we propose a framework that: (i) creates synthetic shopping agents by automatically mining personas from anonymised historical shopping data, (ii) equips agents with retail-specific tools to synthesise shopping sessions and (iii) introduces a novel alignment suite measuring distributional differences between humans and shopping agents at the group (i.e. population) level rather than the traditional "individual" level. Experimental results demonstrate that using personas improves performance on the alignment suite, though a gap remains to human behaviour. We showcase an initial application of our framework for automated agentic A/B testing and compare the findings to human results. Finally, we discuss applications, limitations and challenges setting the stage for impactful future work.
Content Warning: This paper may contain unsafe or harmful content generated by LLMs that may be offensive to readers. Large Language Models (LLMs) are extensively used as tooling platforms through structured output APIs to ensure syntax compliance so that robust integration with existing softwares like agent systems, could be achieved. However, the feature enabling functionality of grammar-guided structured output presents significant security vulnerabilities. In this work, we reveal a critical control-plane attack surface orthogonal to traditional data-plane vulnerabilities. We introduce Constrained Decoding Attack (CDA), a novel jailbreak class that weaponizes structured output constraints to bypass safety mechanisms. Unlike prior attacks focused on input prompts, CDA operates by embedding malicious intent in schema-level grammar rules (control-plane) while maintaining benign surface prompts (data-plane). We instantiate this with a proof-of-concept Chain Enum Attack, achieves 96.2% attack success rates across proprietary and open-weight LLMs on five safety benchmarks with a single query, including GPT-4o and Gemini-2.0-flash. Our findings identify a critical security blind spot in current LLM architectures and urge a paradigm shift in LLM safety to address control-plane vulnerabilities, as current mechanisms focused solely on data-plane threats leave critical systems exposed.
The detection of telecom fraud faces significant challenges due to the lack of high-quality multimodal training data that integrates audio signals with reasoning-oriented textual analysis. To address this gap, we present TeleAntiFraud-28k, the first open-source audio-text slow-thinking dataset specifically designed for automated telecom fraud analysis. Our dataset is constructed through three strategies: (1) Privacy-preserved text-truth sample generation using automatically speech recognition (ASR)-transcribed call recordings (with anonymized original audio), ensuring real-world consistency through text-to-speech (TTS) model regeneration; (2) Semantic enhancement via large language model (LLM)-based self-instruction sampling on authentic ASR outputs to expand scenario coverage; (3) Multi-agent adversarial synthesis that simulates emerging fraud tactics through predefined communication scenarios and fraud typologies. The generated dataset contains 28,511 rigorously processed speech-text pairs, complete with detailed annotations for fraud reasoning. The dataset is divided into three tasks: scenario classification, fraud detection, fraud type classification. Furthermore, we construct TeleAntiFraud-Bench, a standardized evaluation benchmark comprising proportionally sampled instances from the dataset, to facilitate systematic testing of model performance on telecom fraud detection tasks. We also contribute a production-optimized supervised fine-tuning (SFT) model trained on hybrid real/synthetic data, while open-sourcing the data processing framework to enable community-driven dataset expansion. This work establishes a foundational framework for multimodal anti-fraud research while addressing critical challenges in data privacy and scenario diversity. The project will be released at https://github.com/JimmyMa99/TeleAntiFraud.
Despite advances in embodied AI, agent reasoning systems still struggle to capture the fundamental conceptual structures that humans naturally use to understand and interact with their environment. To address this, we propose a novel framework that bridges embodied cognition theory and agent systems by leveraging a formal characterization of image schemas, which are defined as recurring patterns of sensorimotor experience that structure human cognition. By customizing LLMs to translate natural language descriptions into formal representations based on these sensorimotor patterns, we will be able to create a neurosymbolic system that grounds the agent's understanding in fundamental conceptual structures. We argue that such an approach enhances both efficiency and interpretability while enabling more intuitive human-agent interactions through shared embodied understanding.
As scientific research becomes increasingly complex, innovative tools are needed to manage vast data, facilitate interdisciplinary collaboration, and accelerate discovery. Large language models (LLMs) are now evolving into LLM-based scientific agents that automate critical tasks, ranging from hypothesis generation and experiment design to data analysis and simulation. Unlike general-purpose LLMs, these specialized agents integrate domain-specific knowledge, advanced tool sets, and robust validation mechanisms, enabling them to handle complex data types, ensure reproducibility, and drive scientific breakthroughs. This survey provides a focused review of the architectures, design, benchmarks, applications, and ethical considerations surrounding LLM-based scientific agents. We highlight why they differ from general agents and the ways in which they advance research across various scientific fields. By examining their development and challenges, this survey offers a comprehensive roadmap for researchers and practitioners to harness these agents for more efficient, reliable, and ethically sound scientific discovery.
Since the disruption in LLM technology brought about by the release of GPT-3 and ChatGPT, LLMs have shown remarkable promise in programming-related tasks. While code generation remains a popular field of research, code evaluation using LLMs remains a problem with no conclusive solution. In this paper, we focus on LLM-based code evaluation and attempt to fill in the existing gaps. We propose multi-agentic novel approaches using question-specific rubrics tailored to the problem statement, arguing that these perform better for logical assessment than the existing approaches that use question-agnostic rubrics. To address the lack of suitable evaluation datasets, we introduce two datasets: a Data Structures and Algorithms dataset containing 150 student submissions from a popular Data Structures and Algorithms practice website, and an Object Oriented Programming dataset comprising 80 student submissions from undergraduate computer science courses. In addition to using standard metrics (Spearman Correlation, Cohen's Kappa), we additionally propose a new metric called as Leniency, which quantifies evaluation strictness relative to expert assessment. Our comprehensive analysis demonstrates that question-specific rubrics significantly enhance logical assessment of code in educational settings, providing better feedback aligned with instructional goals beyond mere syntactic correctness.
The relational database design would output a schema based on user's requirements, which defines table structures and their interrelated relations. Translating requirements into accurate schema involves several non-trivial subtasks demanding both database expertise and domain-specific knowledge. This poses unique challenges for automated design of relational databases. Existing efforts are mostly based on customized rules or conventional deep learning models, often producing suboptimal schema. Recently, large language models (LLMs) have significantly advanced intelligent application development across various domains. In this paper, we propose SchemaAgent, a unified LLM-based multi-agent framework for the automated generation of high-quality database schema. SchemaAgent is the first to apply LLMs for schema generation, which emulates the workflow of manual schema design by assigning specialized roles to agents and enabling effective collaboration to refine their respective subtasks. Schema generation is a streamlined workflow, where directly applying the multi-agent framework may cause compounding impact of errors. To address this, we incorporate dedicated roles for reflection and inspection, alongside an innovative error detection and correction mechanism to identify and rectify issues across various phases. For evaluation, we present a benchmark named \textit{RSchema}, which contains more than 500 pairs of requirement description and schema. Experimental results on this benchmark demonstrate the superiority of our approach over mainstream LLMs for relational database schema generation.
Recent advancements in software engineering agents have demonstrated promising capabilities in automating program improvements. However, their reliance on closed-source or resource-intensive models introduces significant deployment challenges in private environments, prompting a critical question: \textit{How can personally deployable open-source LLMs achieve comparable code reasoning performance?} To this end, we propose a unified Test-Time Compute scaling framework that leverages increased inference-time computation instead of larger models. Our framework incorporates two complementary strategies: internal TTC and external TTC. Internally, we introduce a \textit{development-contextualized trajectory synthesis} method leveraging real-world software repositories to bootstrap multi-stage reasoning processes, such as fault localization and patch generation. We further enhance trajectory quality through rejection sampling, rigorously evaluating trajectories along accuracy and complexity. Externally, we propose a novel \textit{development-process-based search} strategy guided by reward models and execution verification. This approach enables targeted computational allocation at critical development decision points, overcoming limitations of existing "end-point only" verification methods. Evaluations on SWE-bench Verified demonstrate our \textbf{32B model achieves a 46\% issue resolution rate}, surpassing significantly larger models such as DeepSeek R1 671B and OpenAI o1. Additionally, we provide the empirical validation of the test-time scaling phenomenon within SWE agents, revealing that \textbf{models dynamically allocate more tokens to increasingly challenging problems}, effectively enhancing reasoning capabilities. We publicly release all training data, models, and code to facilitate future research. https://github.com/yingweima2022/SWE-Reasoner
Large language models (LLMs) have demonstrated strong potential and impressive performance in automating the generation and optimization of workflows. However, existing approaches are marked by limited reasoning capabilities, high computational demands, and significant resource requirements. To address these issues, we propose DebFlow, a framework that employs a debate mechanism to optimize workflows and integrates reflexion to improve based on previous experiences. We evaluated our method across six benchmark datasets, including HotpotQA, MATH, and ALFWorld. Our approach achieved a 3\% average performance improvement over the latest baselines, demonstrating its effectiveness in diverse problem domains. In particular, during training, our framework reduces resource consumption by 37\% compared to the state-of-the-art baselines. Additionally, we performed ablation studies. Removing the Debate component resulted in a 4\% performance drop across two benchmark datasets, significantly greater than the 2\% drop observed when the Reflection component was removed. These findings strongly demonstrate the critical role of Debate in enhancing framework performance, while also highlighting the auxiliary contribution of reflexion to overall optimization.
Smart contracts are fundamental pillars of the blockchain, playing a crucial role in facilitating various business transactions. However, these smart contracts are vulnerable to exploitable bugs that can lead to substantial monetary losses. A recent study reveals that over 80% of these exploitable bugs, which are primarily functional bugs, can evade the detection of current tools. The primary issue is the significant gap between understanding the high-level logic of the business model and checking the low-level implementations in smart contracts. Furthermore, identifying deeply rooted functional bugs in smart contracts requires the automated generation of effective detection oracles based on various bug features. To address these challenges, we design and implement PROMFUZZ, an automated and scalable system to detect functional bugs, in smart contracts. In PROMFUZZ, we first propose a novel Large Language Model (LLM)-driven analysis framework, which leverages a dual-agent prompt engineering strategy to pinpoint potentially vulnerable functions for further scrutiny. We then implement a dual-stage coupling approach, which focuses on generating invariant checkers that leverage logic information extracted from potentially vulnerable functions. Finally, we design a bug-oriented fuzzing engine, which maps the logical information from the high-level business model to the low-level smart contract implementations, and performs the bug-oriented fuzzing on targeted functions. We compare PROMFUZZ with multiple state-of-the-art methods. The results show that PROMFUZZ achieves 86.96% recall and 93.02% F1-score in detecting functional bugs, marking at least a 50% improvement in both metrics over state-of-the-art methods. Moreover, we perform an in-depth analysis on real-world DeFi projects and detect 30 zero-day bugs. Up to now, 24 zero-day bugs have been assigned CVE IDs.
The advent of generative AI exemplified by large language models (LLMs) opens new ways to represent and compute geographic information and transcend the process of geographic knowledge production, driving geographic information systems (GIS) towards autonomous GIS. Leveraging LLMs as the decision core, autonomous GIS can independently generate and execute geoprocessing workflows to perform spatial analysis. In this vision paper, we elaborate on the concept of autonomous GIS and present a framework that defines its five autonomous goals, five levels of autonomy, five core functions, and three operational scales. We demonstrate how autonomous GIS could perform geospatial data retrieval, spatial analysis, and map making with four proof-of-concept GIS agents. We conclude by identifying critical challenges and future research directions, including fine-tuning and self-growing decision cores, autonomous modeling, and examining the ethical and practical implications of autonomous GIS. By establishing the groundwork for a paradigm shift in GIScience, this paper envisions a future where GIS moves beyond traditional workflows to autonomously reason, derive, innovate, and advance solutions to pressing global challenges.
We explore the use of GPT-4 on a humanoid robot in simulation and the real world as proof of concept of a novel large language model (LLM) driven behaviour method. LLMs have shown the ability to perform various tasks, including robotic agent behaviour. The problem involves prompting the LLM with a goal, and the LLM outputs the sub-tasks to complete to achieve that goal. Previous works focus on the executability and correctness of the LLM's generated tasks. We propose a method that successfully addresses practical concerns around safety, transitions between tasks, time horizons of tasks and state feedback. In our experiments we have found that our approach produces output for feasible requests that can be executed every time, with smooth transitions. User requests are achieved most of the time across a range of goal time horizons.
Large language models (LLMs) can carry out human-like dialogue, but unlike humans, they are stateless due to the superposition property. However, during multi-turn, multi-agent interactions, LLMs begin to exhibit consistent, character-like behaviors, hinting at a form of emergent lifelong learning. Despite this, existing benchmarks often fail to capture these dynamics, primarily focusing on static, open-ended evaluations. To address this gap, we introduce LIFESTATE-BENCH, a benchmark designed to assess lifelong learning in LLMs. It features two episodic datasets: Hamlet and a synthetic script collection, rich in narrative structure and character interactions. Our fact checking evaluation probes models' self-awareness, episodic memory retrieval, and relationship tracking, across both parametric and non-parametric approaches. Experiments on models like Llama3.1-8B, GPT-4-turbo, and DeepSeek R1, we demonstrate that nonparametric methods significantly outperform parametric ones in managing stateful learning. However, all models exhibit challenges with catastrophic forgetting as interactions extend, highlighting the need for further advancements in lifelong learning.
Language-based object detection (LOD) aims to align visual objects with language expressions. A large amount of paired data is utilized to improve LOD model generalizations. During the training process, recent studies leverage vision-language models (VLMs) to automatically generate human-like expressions for visual objects, facilitating training data scaling up. In this process, we observe that VLM hallucinations bring inaccurate object descriptions (e.g., object name, color, and shape) to deteriorate VL alignment quality. To reduce VLM hallucinations, we propose an agentic workflow controlled by an LLM to re-align language to visual objects via adaptively adjusting image and text prompts. We name this workflow Real-LOD, which includes planning, tool use, and reflection steps. Given an image with detected objects and VLM raw language expressions, Real-LOD reasons its state automatically and arranges action based on our neural symbolic designs (i.e., planning). The action will adaptively adjust the image and text prompts and send them to VLMs for object re-description (i.e., tool use). Then, we use another LLM to analyze these refined expressions for feedback (i.e., reflection). These steps are conducted in a cyclic form to gradually improve language descriptions for re-aligning to visual objects. We construct a dataset that contains a tiny amount of 0.18M images with re-aligned language expression and train a prevalent LOD model to surpass existing LOD methods by around 50% on the standard benchmarks. Our Real-LOD workflow, with automatic VL refinement, reveals a potential to preserve data quality along with scaling up data quantity, which further improves LOD performance from a data-alignment perspective.
The rapid advancement of video generation has rendered existing evaluation systems inadequate for assessing state-of-the-art models, primarily due to simple prompts that cannot showcase the model's capabilities, fixed evaluation operators struggling with Out-of-Distribution (OOD) cases, and misalignment between computed metrics and human preferences. To bridge the gap, we propose VideoGen-Eval, an agent evaluation system that integrates LLM-based content structuring, MLLM-based content judgment, and patch tools designed for temporal-dense dimensions, to achieve a dynamic, flexible, and expandable video generation evaluation. Additionally, we introduce a video generation benchmark to evaluate existing cutting-edge models and verify the effectiveness of our evaluation system. It comprises 700 structured, content-rich prompts (both T2V and I2V) and over 12,000 videos generated by 20+ models, among them, 8 cutting-edge models are selected as quantitative evaluation for the agent and human. Extensive experiments validate that our proposed agent-based evaluation system demonstrates strong alignment with human preferences and reliably completes the evaluation, as well as the diversity and richness of the benchmark.
Large Language Models (LLMs) have demonstrated superior listwise ranking performance. However, their superior performance often relies on large-scale parameters (\eg, GPT-4) and a repetitive sliding window process, which introduces significant efficiency challenges. In this paper, we propose \textbf{CoRanking}, a novel collaborative ranking framework that combines small and large ranking models for efficient and effective ranking. CoRanking first employs a small-size reranker to pre-rank all the candidate passages, bringing relevant ones to the top part of the list (\eg, top-20). Then, the LLM listwise reranker is applied to only rerank these top-ranked passages instead of the whole list, substantially enhancing overall ranking efficiency. Although more efficient, previous studies have revealed that the LLM listwise reranker have significant positional biases on the order of input passages. Directly feed the top-ranked passages from small reranker may result in the sub-optimal performance of LLM listwise reranker. To alleviate this problem, we introduce a passage order adjuster trained via reinforcement learning, which reorders the top passages from the small reranker to align with the LLM's preferences of passage order. Extensive experiments on three IR benchmarks demonstrate that CoRanking significantly improves efficiency (reducing ranking latency by about 70\%) while achieving even better effectiveness compared to using only the LLM listwise reranker.
Large Language Models (LLMs) frequently produce factually inaccurate outputs - a phenomenon known as hallucination - which limits their accuracy in knowledge-intensive NLP tasks. Retrieval-augmented generation and agentic frameworks such as Reasoning and Acting (ReAct) can address this issue by giving the model access to external knowledge. However, LLMs often fail to remain faithful to retrieved information. Mitigating this is critical, especially if LLMs are required to reason about the retrieved information. Recent research has explored training-free decoding strategies to improve the faithfulness of model generations. We present a systematic analysis of how the combination of the ReAct framework and decoding strategies (i.e., DeCoRe, DoLa, and CAD) can influence the faithfulness of LLM-generated answers. Our results show that combining an agentic framework for knowledge retrieval with decoding methods that enhance faithfulness can increase accuracy on the downstream Multi-Hop Question Answering tasks. For example, we observe an F1 increase from 19.5 to 32.6 on HotpotQA when using ReAct and DoLa.
Misinformation spans various domains, but detection methods trained on specific domains often perform poorly when applied to others. With the rapid development of Large Language Models (LLMs), researchers have begun to utilize LLMs for cross-domain misinformation detection. However, existing LLM-based methods often fail to adequately analyze news in the target domain, limiting their detection capabilities. More importantly, these methods typically rely on manually designed decision rules, which are limited by domain knowledge and expert experience, thus limiting the generalizability of decision rules to different domains. To address these issues, we propose a MultiAgent Framework for cross-domain misinformation detection with Automated Decision Rule Optimization (MARO). Under this framework, we first employs multiple expert agents to analyze target-domain news. Subsequently, we introduce a question-reflection mechanism that guides expert agents to facilitate higherquality analysis. Furthermore, we propose a decision rule optimization approach based on carefully-designed cross-domain validation tasks to iteratively enhance the effectiveness of decision rules in different domains. Experimental results and in-depth analysis on commonlyused datasets demonstrate that MARO achieves significant improvements over existing methods.
We introduce the concept of "Design Agents" for engineering applications, particularly focusing on the automotive design process, while emphasizing that our approach can be readily extended to other engineering and design domains. Our framework integrates AI-driven design agents into the traditional engineering workflow, demonstrating how these specialized computational agents interact seamlessly with engineers and designers to augment creativity, enhance efficiency, and significantly accelerate the overall design cycle. By automating and streamlining tasks traditionally performed manually, such as conceptual sketching, styling enhancements, 3D shape retrieval and generative modeling, computational fluid dynamics (CFD) meshing, and aerodynamic simulations, our approach reduces certain aspects of the conventional workflow from weeks and days down to minutes. These agents leverage state-of-the-art vision-language models (VLMs), large language models (LLMs), and geometric deep learning techniques, providing rapid iteration and comprehensive design exploration capabilities. We ground our methodology in industry-standard benchmarks, encompassing a wide variety of conventional automotive designs, and utilize high-fidelity aerodynamic simulations to ensure practical and applicable outcomes. Furthermore, we present design agents that can swiftly and accurately predict simulation outcomes, empowering engineers and designers to engage in more informed design optimization and exploration. This research underscores the transformative potential of integrating advanced generative AI techniques into complex engineering tasks, paving the way for broader adoption and innovation across multiple engineering disciplines.
Large Language Models (LLMs) have revolutionized automated data analytics and machine learning by enabling dynamic reasoning and adaptability. While recent approaches have advanced multi-stage pipelines through multi-agent systems, they typically rely on rigid, single-path workflows that limit the exploration and integration of diverse strategies, often resulting in suboptimal predictions. To address these challenges, we propose SPIO (Sequential Plan Integration and Optimization), a novel framework that leverages LLM-driven decision-making to orchestrate multi-agent planning across four key modules: data preprocessing, feature engineering, modeling, and hyperparameter tuning. In each module, dedicated planning agents independently generate candidate strategies that cascade into subsequent stages, fostering comprehensive exploration. A plan optimization agent refines these strategies by suggesting several optimized plans. We further introduce two variants: SPIO-S, which selects a single best solution path as determined by the LLM, and SPIO-E, which selects the top k candidate plans and ensembles them to maximize predictive performance. Extensive experiments on Kaggle and OpenML datasets demonstrate that SPIO significantly outperforms state-of-the-art methods, providing a robust and scalable solution for automated data science task.
There are a growing number of AI applications, but none tailored specifically to help residents answer their questions about municipal budget, a topic most are interested in but few have a solid comprehension of. In this research paper, we propose GRASP, a custom AI chatbot framework which stands for Generation with Retrieval and Action System for Prompts. GRASP provides more truthful and grounded responses to user budget queries than traditional information retrieval systems like general Large Language Models (LLMs) or web searches. These improvements come from the novel combination of a Retrieval-Augmented Generation (RAG) framework ("Generation with Retrieval") and an agentic workflow ("Action System"), as well as prompt engineering techniques, the incorporation of municipal budget domain knowledge, and collaboration with local town officials to ensure response truthfulness. During testing, we found that our GRASP chatbot provided precise and accurate responses for local municipal budget queries 78% of the time, while GPT-4o and Gemini were only accurate 60% and 35% of the time, respectively. GRASP chatbots greatly reduce the time and effort needed for the general public to get an intuitive and correct understanding of their town's budget, thus fostering greater communal discourse, improving government transparency, and allowing citizens to make more informed decisions.
Inductive program synthesis, or programming by example, requires synthesizing functions from input-output examples that generalize to unseen inputs. While large language model agents have shown promise in programming tasks guided by natural language, their ability to perform inductive program synthesis is underexplored. Existing evaluation protocols rely on static sets of examples and held-out tests, offering no feedback when synthesized functions are incorrect and failing to reflect real-world scenarios such as reverse engineering. We propose CodeARC, the Code Abstraction and Reasoning Challenge, a new evaluation framework where agents interact with a hidden target function by querying it with new inputs, synthesizing candidate functions, and iteratively refining their solutions using a differential testing oracle. This interactive setting encourages agents to perform function calls and self-correction based on feedback. We construct the first large-scale benchmark for general-purpose inductive program synthesis, featuring 1114 functions. Among 18 models evaluated, o3-mini performs best with a success rate of 52.7%, highlighting the difficulty of this task. Fine-tuning LLaMA-3.1-8B-Instruct on curated synthesis traces yields up to a 31% relative performance gain. CodeARC provides a more realistic and challenging testbed for evaluating LLM-based program synthesis and inductive reasoning.
Communication encryption is crucial in computer technology, but existing algorithms struggle with balancing cost and security. We propose EncGPT, a multi-agent framework using large language models (LLM). It includes rule, encryption, and decryption agents that generate encryption rules and apply them dynamically. This approach addresses gaps in LLM-based multi-agent systems for communication security. We tested GPT-4o's rule generation and implemented a substitution encryption workflow with homomorphism preservation, achieving an average execution time of 15.99 seconds.
Large Reasoning Models (LRMs) significantly improve the reasoning ability of Large Language Models (LLMs) by learning to reason, exhibiting promising performance in complex task-solving. However, their deliberative reasoning process leads to inefficiencies in token usage, memory consumption, and inference time. Thus, this survey provides a review of efficient inference methods designed specifically for LRMs, focusing on mitigating token inefficiency while preserving the reasoning quality. First, we introduce a taxonomy to group the recent methods into two main categories: (a) explicit compact Chain-of-Thought (CoT), which reduces tokens while keeping the explicit reasoning structure, and (b) implicit latent CoT, which encodes reasoning steps within hidden representations instead of explicit tokens. Meanwhile, we discuss their strengths and weaknesses. Then, we conduct empirical analyses on existing methods from performance and efficiency aspects. Besides, we present open challenges in this field, including human-centric controllable reasoning, trade-off between interpretability and efficiency of reasoning, ensuring safety of efficient reasoning, and broader applications of efficient reasoning. In addition, we highlight key insights for enhancing LRMs' inference efficiency via techniques such as model merging, new architectures, and agent routers. We hope this work serves as a valuable guide, helping researchers overcome challenges in this vibrant field\footnote{https://github.com/yueliu1999/Awesome-Efficient-Inference-for-LRMs}.
There is great interest in agentic LLMs, large language models that act as agents. We review the growing body of work in this area and provide a research agenda. Agentic LLMs are LLMs that (1) reason, (2) act, and (3) interact. We organize the literature according to these three categories. The research in the first category focuses on reasoning, reflection, and retrieval, aiming to improve decision making; the second category focuses on action models, robots, and tools, aiming for agents that act as useful assistants; the third category focuses on multi-agent systems, aiming for collaborative task solving and simulating interaction to study emergent social behavior. We find that works mutually benefit from results in other categories: retrieval enables tool use, reflection improves multi-agent collaboration, and reasoning benefits all categories. We discuss applications of agentic LLMs and provide an agenda for further research. Important applications are in medical diagnosis, logistics and financial market analysis. Meanwhile, self-reflective agents playing roles and interacting with one another augment the process of scientific research itself. Further, agentic LLMs may provide a solution for the problem of LLMs running out of training data: inference-time behavior generates new training states, such that LLMs can keep learning without needing ever larger datasets. We note that there is risk associated with LLM assistants taking action in the real world, while agentic LLMs are also likely to benefit society.
In this paper, we propose a novel factored agent architecture designed to overcome the limitations of traditional single-agent systems in agentic AI. Our approach decomposes the agent into two specialized components: (1) a large language model (LLM) that serves as a high level planner and in-context learner, which may use dynamically available information in user prompts, (2) a smaller language model which acts as a memorizer of tool format and output. This decoupling addresses prevalent issues in monolithic designs, including malformed, missing, and hallucinated API fields, as well as suboptimal planning in dynamic environments. Empirical evaluations demonstrate that our factored architecture significantly improves planning accuracy and error resilience, while elucidating the inherent trade-off between in-context learning and static memorization. These findings suggest that a factored approach is a promising pathway for developing more robust and adaptable agentic AI systems.
Fact-checking is a potentially useful application of Large Language Models (LLMs) to combat the growing dissemination of disinformation. However, the performance of LLMs varies across geographic regions. In this paper, we evaluate the factual accuracy of open and private models across a diverse set of regions and scenarios. Using a dataset containing 600 fact-checked statements balanced across six global regions we examine three experimental setups of fact-checking a statement: (1) when just the statement is available, (2) when an LLM-based agent with Wikipedia access is utilized, and (3) as a best case scenario when a Retrieval-Augmented Generation (RAG) system provided with the official fact check is employed. Our findings reveal that regardless of the scenario and LLM used, including GPT-4, Claude Sonnet, and LLaMA, statements from the Global North perform substantially better than those from the Global South. Furthermore, this gap is broadened for the more realistic case of a Wikipedia agent-based system, highlighting that overly general knowledge bases have a limited ability to address region-specific nuances. These results underscore the urgent need for better dataset balancing and robust retrieval strategies to enhance LLM fact-checking capabilities, particularly in geographically diverse contexts.
In this work, we introduce MedAgentSim, an open-source simulated clinical environment with doctor, patient, and measurement agents designed to evaluate and enhance LLM performance in dynamic diagnostic settings. Unlike prior approaches, our framework requires doctor agents to actively engage with patients through multi-turn conversations, requesting relevant medical examinations (e.g., temperature, blood pressure, ECG) and imaging results (e.g., MRI, X-ray) from a measurement agent to mimic the real-world diagnostic process. Additionally, we incorporate self improvement mechanisms that allow models to iteratively refine their diagnostic strategies. We enhance LLM performance in our simulated setting by integrating multi-agent discussions, chain-of-thought reasoning, and experience-based knowledge retrieval, facilitating progressive learning as doctor agents interact with more patients. We also introduce an evaluation benchmark for assessing the LLM's ability to engage in dynamic, context-aware diagnostic interactions. While MedAgentSim is fully automated, it also supports a user-controlled mode, enabling human interaction with either the doctor or patient agent. Comprehensive evaluations in various simulated diagnostic scenarios demonstrate the effectiveness of our approach. Our code, simulation tool, and benchmark are available at \href{https://medagentsim.netlify.app/}.
Recent advances in leveraging LLMs for APR have demonstrated impressive capabilities in fixing software defects. However, current LLM-based approaches predominantly focus on mainstream programming languages like Java and Python, neglecting less prevalent but emerging languages such as Rust due to expensive training resources, limited datasets, and insufficient community support. This narrow focus creates a significant gap in repair capabilities across the programming language spectrum, where the full potential of LLMs for comprehensive multilingual program repair remains largely unexplored. To address this limitation, we introduce a novel cross-language program repair approach LANTERN that leverages LLMs' differential proficiency across languages through a multi-agent iterative repair paradigm. Our technique strategically translates defective code from languages where LLMs exhibit weaker repair capabilities to languages where they demonstrate stronger performance, without requiring additional training. A key innovation of our approach is an LLM-based decision-making system that dynamically selects optimal target languages based on bug characteristics and continuously incorporates feedback from previous repair attempts. We evaluate our method on xCodeEval, a comprehensive multilingual benchmark comprising 5,068 bugs across 11 programming languages. Results demonstrate significant enhancement in repair effectiveness, particularly for underrepresented languages, with Rust showing a 22.09% improvement in Pass@10 metrics. Our research provides the first empirical evidence that cross-language translation significantly expands the repair capabilities of LLMs and effectively bridges the performance gap between programming languages with different levels of popularity, opening new avenues for truly language-agnostic automated program repair.
Workflows play a crucial role in enhancing enterprise efficiency by orchestrating complex processes with multiple tools or components. However, hand-crafted workflow construction requires expert knowledge, presenting significant technical barriers. Recent advancements in Large Language Models (LLMs) have improved the generation of workflows from natural language instructions (aka NL2Workflow), yet existing single LLM agent-based methods face performance degradation on complex tasks due to the need for specialized knowledge and the strain of task-switching. To tackle these challenges, we propose WorkTeam, a multi-agent NL2Workflow framework comprising a supervisor, orchestrator, and filler agent, each with distinct roles that collaboratively enhance the conversion process. As there are currently no publicly available NL2Workflow benchmarks, we also introduce the HW-NL2Workflow dataset, which includes 3,695 real-world business samples for training and evaluation. Experimental results show that our approach significantly increases the success rate of workflow construction, providing a novel and effective solution for enterprise NL2Workflow services.