We introduce MLE-Dojo, a Gym-style framework for systematically reinforcement learning, evaluating, and improving autonomous large language model (LLM) agents in iterative machine learning engineering (MLE) workflows. Unlike existing benchmarks that primarily rely on static datasets or single-attempt evaluations, MLE-Dojo provides an interactive environment enabling agents to iteratively experiment, debug, and refine solutions through structured feedback loops. Built upon 200+ real-world Kaggle challenges, MLE-Dojo covers diverse, open-ended MLE tasks carefully curated to reflect realistic engineering scenarios such as data processing, architecture search, hyperparameter tuning, and code debugging. Its fully executable environment supports comprehensive agent training via both supervised fine-tuning and reinforcement learning, facilitating iterative experimentation, realistic data sampling, and real-time outcome verification. Extensive evaluations of eight frontier LLMs reveal that while current models achieve meaningful iterative improvements, they still exhibit significant limitations in autonomously generating long-horizon solutions and efficiently resolving complex errors. Furthermore, MLE-Dojo's flexible and extensible architecture seamlessly integrates diverse data sources, tools, and evaluation protocols, uniquely enabling model-based agent tuning and promoting interoperability, scalability, and reproducibility. We open-source our framework and benchmarks to foster community-driven innovation towards next-generation MLE agents.
Large Language Models (LLMs) often struggle with mathematical reasoning tasks requiring precise, verifiable computation. While Reinforcement Learning (RL) from outcome-based rewards enhances text-based reasoning, understanding how agents autonomously learn to leverage external tools like code execution remains crucial. We investigate RL from outcome-based rewards for Tool-Integrated Reasoning, ZeroTIR, training base LLMs to spontaneously generate and execute Python code for mathematical problems without supervised tool-use examples. Our central contribution is we demonstrate that as RL training progresses, key metrics scale predictably. Specifically, we observe strong positive correlations where increased training steps lead to increases in the spontaneous code execution frequency, the average response length, and, critically, the final task accuracy. This suggests a quantifiable relationship between computational effort invested in training and the emergence of effective, tool-augmented reasoning strategies. We implement a robust framework featuring a decoupled code execution environment and validate our findings across standard RL algorithms and frameworks. Experiments show ZeroTIR significantly surpasses non-tool ZeroRL baselines on challenging math benchmarks. Our findings provide a foundational understanding of how autonomous tool use is acquired and scales within Agent RL, offering a reproducible benchmark for future studies. Code is released at \href{https://github.com/Anonymize-Author/AgentRL}{https://github.com/Anonymize-Author/AgentRL}.
This paper introduces Codified Profiles for role-playing, a novel approach that represents character logic as structured, executable functions for behavioral decision-making. Each profile defines a set of functions parse_by_scene(scene) that outputs a list of logic-grounded assertions triggered_statements, using both explicit control structures (e.g., if-then-else) and condition checks like check_condition(scene, question), where each question is a semantically meaningful prompt about the scene (e.g., "Is the character in danger?") discriminated by the role-playing LLM as true, false, or unknown. This explicit representation offers three key advantages over traditional prompt-based profiles, which append character descriptions directly into text prompts: (1) Persistence, by enforcing complete and consistent execution of character logic, rather than relying on the model's implicit reasoning; (2) Updatability, through systematic inspection and revision of behavioral logic, which is difficult to track or debug in prompt-only approaches; (3) Controllable Randomness, by supporting stochastic behavior directly within the logic, enabling fine-grained variability that prompting alone struggles to achieve. To validate these advantages, we introduce a new benchmark constructed from 83 characters and 5,141 scenes curated from Fandom, using NLI-based scoring to compare character responses against ground-truth actions. Our experiments demonstrate the significant benefits of codified profiles in improving persistence, updatability, and behavioral diversity. Notably, by offloading a significant portion of reasoning to preprocessing, codified profiles enable even 1B-parameter models to perform high-quality role-playing, providing a scalable and efficient foundation for local deployment of role-play agents.
KAQG introduces a decisive breakthrough for Retrieval-Augmented Generation (RAG) by explicitly tackling the two chronic weaknesses of current pipelines: transparent multi-step reasoning and fine-grained cognitive difficulty control. This transforms RAG from a passive retriever into an accountable generator of calibrated exam items. Technically, the framework fuses knowledge graphs, RAG retrieval, and educational assessment theory into a single pipeline. Domain passages are parsed into a structured graph; graph-aware retrieval feeds fact chains to an LLM; and an assessment layer governed by Bloom's Taxonomy levels and Item Response Theory (IRT) transforms those chains into psychometrically sound questions. This cross-disciplinary marriage yields two scholarly contributions: it shows how semantic graph contexts guide LLM reasoning paths, and it operationalizes difficulty metrics within the generation process, producing items whose IRT parameters match expert benchmarks. Every module, from KG construction scripts to the multi-agent reasoning scheduler and the automatic IRT validator, is openly released on GitHub. This enables peer laboratories to replicate experiments, benchmark against baselines, and extend individual components without licensing barriers. Its reproducible design paves the way for rigorous ablation studies, cross-domain transfer experiments, and shared leaderboards on multi-step reasoning benchmarks.
Retrieval-augmented generation (RAG) is a common strategy to reduce hallucinations in Large Language Models (LLMs). While reinforcement learning (RL) can enable LLMs to act as search agents by activating retrieval capabilities, existing ones often underutilize their internal knowledge. This can lead to redundant retrievals, potential harmful knowledge conflicts, and increased inference latency. To address these limitations, an efficient and adaptive search agent capable of discerning optimal retrieval timing and synergistically integrating parametric (internal) and retrieved (external) knowledge is in urgent need. This paper introduces the Reinforced Internal-External Knowledge Synergistic Reasoning Agent (IKEA), which could indentify its own knowledge boundary and prioritize the utilization of internal knowledge, resorting to external search only when internal knowledge is deemed insufficient. This is achieved using a novel knowledge-boundary aware reward function and a knowledge-boundary aware training dataset. These are designed for internal-external knowledge synergy oriented RL, incentivizing the model to deliver accurate answers, minimize unnecessary retrievals, and encourage appropriate external searches when its own knowledge is lacking. Evaluations across multiple knowledge reasoning tasks demonstrate that IKEA significantly outperforms baseline methods, reduces retrieval frequency significantly, and exhibits robust generalization capabilities.
Leveraging large language model (LLM) based agents to simulate human social behaviors has recently gained significant attention. In this paper, we introduce a novel social simulator called YuLan-OneSim. Compared to previous works, YuLan-OneSim distinguishes itself in five key aspects: (1) Code-free scenario construction: Users can simply describe and refine their simulation scenarios through natural language interactions with our simulator. All simulation code is automatically generated, significantly reducing the need for programming expertise. (2) Comprehensive default scenarios: We implement 50 default simulation scenarios spanning 8 domains, including economics, sociology, politics, psychology, organization, demographics, law, and communication, broadening access for a diverse range of social researchers. (3) Evolvable simulation: Our simulator is capable of receiving external feedback and automatically fine-tuning the backbone LLMs, significantly enhancing the simulation quality. (4) Large-scale simulation: By developing a fully responsive agent framework and a distributed simulation architecture, our simulator can handle up to 100,000 agents, ensuring more stable and reliable simulation results. (5) AI social researcher: Leveraging the above features, we develop an AI social researcher. Users only need to propose a research topic, and the AI researcher will automatically analyze the input, construct simulation environments, summarize results, generate technical reports, review and refine the reports--completing the social science research loop. To demonstrate the advantages of YuLan-OneSim, we conduct experiments to evaluate the quality of the automatically generated scenarios, the reliability, efficiency, and scalability of the simulation process, as well as the performance of the AI social researcher.
The remote embodied referring expression (REVERIE) task requires an agent to navigate through complex indoor environments and localize a remote object specified by high-level instructions, such as "bring me a spoon", without pre-exploration. Hence, an efficient navigation plan is essential for the final success. This paper proposes a novel parameter-efficient action planner using large language models (PEAP-LLM) to generate a single-step instruction at each location. The proposed model consists of two modules, LLM goal planner (LGP) and LoRA action planner (LAP). Initially, LGP extracts the goal-oriented plan from REVERIE instructions, including the target object and room. Then, LAP generates a single-step instruction with the goal-oriented plan, high-level instruction, and current visual observation as input. PEAP-LLM enables the embodied agent to interact with LAP as the path planner on the fly. A simple direct application of LLMs hardly achieves good performance. Also, existing hard-prompt-based methods are error-prone in complicated scenarios and need human intervention. To address these issues and prevent the LLM from generating hallucinations and biased information, we propose a novel two-stage method for fine-tuning the LLM, consisting of supervised fine-tuning (STF) and direct preference optimization (DPO). SFT improves the quality of generated instructions, while DPO utilizes environmental feedback. Experimental results show the superiority of our proposed model on REVERIE compared to the previous state-of-the-art.
The application of large language models (LLMs) in the field of coding is evolving rapidly: from code assistants, to autonomous coding agents, and then to generating complete projects through natural language. Early LLM code benchmarks primarily focused on code generation accuracy, but these benchmarks have gradually become saturated. Benchmark saturation weakens their guiding role for LLMs. For example, HumanEval Pass@1 has reached 99.4% and MBPP 94.2%. Among various attempts to address benchmark saturation, approaches based on software engineering have stood out, but the saturation of existing software engineering benchmarks is rapidly increasing. To address this, we propose a new benchmark, Web-Bench, which contains 50 projects, each consisting of 20 tasks with sequential dependencies. The tasks implement project features in sequence, simulating real-world human development workflows. When designing Web-Bench, we aim to cover the foundational elements of Web development: Web Standards and Web Frameworks. Given the scale and complexity of these projects, which were designed by engineers with 5 to 10 years of experience, each presents a significant challenge. On average, a single project takes 4 to 8 hours for a senior engineer to complete. On our given benchmark agent (Web-Agent), SOTA (Claude 3.7 Sonnet) achieves only 25.1% Pass@1, significantly lower (better) than SWE-Bench's Verified (65.4%) and Full (33.8%) scores. Finally, we discuss that in any development field, Standards and Frameworks represent foundational knowledge and efficiency tools, respectively, and LLMs require optimization tailored to them.
We explore the potential of Large Language Models (LLMs) to replicate human behavior in economic market experiments. Compared to previous studies, we focus on dynamic feedback between LLM agents: the decisions of each LLM impact the market price at the current step, and so affect the decisions of the other LLMs at the next step. We compare LLM behavior to market dynamics observed in laboratory settings and assess their alignment with human participants' behavior. Our findings indicate that LLMs do not adhere strictly to rational expectations, displaying instead bounded rationality, similarly to human participants. Providing a minimal context window i.e. memory of three previous time steps, combined with a high variability setting capturing response heterogeneity, allows LLMs to replicate broad trends seen in human experiments, such as the distinction between positive and negative feedback markets. However, differences remain at a granular level--LLMs exhibit less heterogeneity in behavior than humans. These results suggest that LLMs hold promise as tools for simulating realistic human behavior in economic contexts, though further research is needed to refine their accuracy and increase behavioral diversity.
Preserving data confidentiality during the fine-tuning of open-source Large Language Models (LLMs) is crucial for sensitive applications. This work introduces an interactive protocol adapting the Low-Rank Adaptation (LoRA) technique for private fine-tuning. Homomorphic Encryption (HE) protects the confidentiality of training data and gradients handled by remote worker nodes performing the bulk of computations involving the base model weights. The data owner orchestrates training, requiring minimal local computing power and memory, thus alleviating the need for expensive client-side GPUs. We demonstrate feasibility by fine-tuning a Llama-3.2-1B model, presenting convergence results using HE-compatible quantization and performance benchmarks for HE computations on GPU hardware. This approach enables applications such as confidential knowledge base question answering, private codebase fine-tuning for AI code assistants, AI agents for drafting emails based on a company's email archive, and adapting models to analyze sensitive legal or healthcare documents.
Designing effective collaboration structure for multi-agent LLM systems to enhance collective reasoning is crucial yet remains under-explored. In this paper, we systematically investigate how collaborative reasoning performance is affected by three key design dimensions: (1) Expertise-Domain Alignment, (2) Collaboration Paradigm (structured workflow vs. diversity-driven integration), and (3) System Scale. Our findings reveal that expertise alignment benefits are highly domain-contingent, proving most effective for contextual reasoning tasks. Furthermore, collaboration focused on integrating diverse knowledge consistently outperforms rigid task decomposition. Finally, we empirically explore the impact of scaling the multi-agent system with expertise specialization and study the computational trade off, highlighting the need for more efficient communication protocol design. This work provides concrete guidelines for configuring specialized multi-agent system and identifies critical architectural trade-offs and bottlenecks for scalable multi-agent reasoning. The code will be made available upon acceptance.
We present UAV-CodeAgents, a scalable multi-agent framework for autonomous UAV mission generation, built on large language and vision-language models (LLMs/VLMs). The system leverages the ReAct (Reason + Act) paradigm to interpret satellite imagery, ground high-level natural language instructions, and collaboratively generate UAV trajectories with minimal human supervision. A core component is a vision-grounded, pixel-pointing mechanism that enables precise localization of semantic targets on aerial maps. To support real-time adaptability, we introduce a reactive thinking loop, allowing agents to iteratively reflect on observations, revise mission goals, and coordinate dynamically in evolving environments. UAV-CodeAgents is evaluated on large-scale mission scenarios involving industrial and environmental fire detection. Our results show that a lower decoding temperature (0.5) yields higher planning reliability and reduced execution time, with an average mission creation time of 96.96 seconds and a success rate of 93%. We further fine-tune Qwen2.5VL-7B on 9,000 annotated satellite images, achieving strong spatial grounding across diverse visual categories. To foster reproducibility and future research, we will release the full codebase and a novel benchmark dataset for vision-language-based UAV planning.
Retrieval-augmented generation (RAG) systems combine large language models (LLMs) with external knowledge retrieval, making them highly effective for knowledge-intensive tasks. A crucial but often under-explored component of these systems is the reranker, which refines retrieved documents to enhance generation quality and explainability. The challenge of selecting the optimal number of documents (k) remains unsolved: too few may omit critical information, while too many introduce noise and inefficiencies. Although recent studies have explored LLM-based rerankers, they primarily leverage internal model knowledge and overlook the rich supervisory signals that LLMs can provide, such as using response quality as feedback for optimizing reranking decisions. In this paper, we propose DynamicRAG, a novel RAG framework where the reranker dynamically adjusts both the order and number of retrieved documents based on the query. We model the reranker as an agent optimized through reinforcement learning (RL), using rewards derived from LLM output quality. Across seven knowledge-intensive datasets, DynamicRAG demonstrates superior performance, achieving state-of-the-art results. The model, data and code are available at https://github.com/GasolSun36/DynamicRAG
We present gg-bench, a collection of game environments designed to evaluate general reasoning capabilities in language models. Unlike most static benchmarks, gg-bench is a data generating process where new evaluation instances can be generated at will. In particular, gg-bench is synthetically generated by (1) using a large language model (LLM) to generate natural language descriptions of novel games, (2) using the LLM to implement each game in code as a Gym environment, and (3) training reinforcement learning (RL) agents via self-play on the generated games. We evaluate language models by their winrate against these RL agents by prompting models with the game description, current board state, and a list of valid moves, after which models output the moves they wish to take. gg-bench is challenging: state-of-the-art LLMs such as GPT-4o and Claude 3.7 Sonnet achieve winrates of 7-9% on gg-bench using in-context learning, while reasoning models such as o1, o3-mini and DeepSeek-R1 achieve average winrates of 31-36%. We release the generated games, data generation process, and evaluation code in order to support future modeling work and expansion of our benchmark.
Large language models (LLMs) have achieved unprecedented performance by leveraging vast pretraining corpora, yet their performance remains suboptimal in knowledge-intensive domains such as medicine and scientific research, where high factual precision is required. While synthetic data provides a promising avenue for augmenting domain knowledge, existing methods frequently generate redundant samples that do not align with the model's true knowledge gaps. To overcome this limitation, we propose a novel Structural Entropy-guided Knowledge Navigator (SENATOR) framework that addresses the intrinsic knowledge deficiencies of LLMs. Our approach employs the Structure Entropy (SE) metric to quantify uncertainty along knowledge graph paths and leverages Monte Carlo Tree Search (MCTS) to selectively explore regions where the model lacks domain-specific knowledge. Guided by these insights, the framework generates targeted synthetic data for supervised fine-tuning, enabling continuous self-improvement. Experimental results on LLaMA-3 and Qwen2 across multiple domain-specific benchmarks show that SENATOR effectively detects and repairs knowledge deficiencies, achieving notable performance improvements. The code and data for our methods and experiments are available at https://github.com/weiyifan1023/senator.
The paper investigates the integration of Large Language Models (LLMs) into Conversational Agents (CAs) to encourage a shift in consumption patterns from a demand-driven to a supply-based paradigm. Specifically, the research examines the role of anthropomorphic design in delivering environmentally conscious messages by comparing two CA designs: a personified agent representing an appliance and a traditional, non-personified assistant. A lab study (N=26) assessed the impact of these designs on interaction, perceived self-efficacy, and engagement. Results indicate that LLM-based CAs significantly enhance users' self-reported eco-friendly behaviors, with participants expressing greater confidence in managing energy consumption. While the anthropomorphic design did not notably affect self-efficacy, those interacting with the personified agent reported a stronger sense of connection with the system. These findings suggest that although anthropomorphic CAs may improve user engagement, both designs hold promise for fostering sustainable behaviors in home energy management.
One goal of AI (and AGI) is to identify and understand specific mechanisms and representations sufficient for general intelligence. Often, this work manifests in research focused on architectures and many cognitive architectures have been explored in AI/AGI. However, different research groups and even different research traditions have somewhat independently identified similar/common patterns of processes and representations or cognitive design patterns that are manifest in existing architectures. Today, AI systems exploiting large language models (LLMs) offer a relatively new combination of mechanism and representation available for exploring the possibilities of general intelligence. In this paper, we summarize a few recurring cognitive design patterns that have appeared in various pre-transformer AI architectures. We then explore how these patterns are evident in systems using LLMs, especially for reasoning and interactive ("agentic") use cases. By examining and applying these recurring patterns, we can also predict gaps or deficiencies in today's Agentic LLM Systems and identify likely subjects of future research towards general intelligence using LLMs and other generative foundation models.
Large Language Models (LLMs) have recently been leveraged for asset pricing tasks and stock trading applications, enabling AI agents to generate investment decisions from unstructured financial data. However, most evaluations of LLM timing-based investing strategies are conducted on narrow timeframes and limited stock universes, overstating effectiveness due to survivorship and data-snooping biases. We critically assess their generalizability and robustness by proposing FINSABER, a backtesting framework evaluating timing-based strategies across longer periods and a larger universe of symbols. Systematic backtests over two decades and 100+ symbols reveal that previously reported LLM advantages deteriorate significantly under broader cross-section and over a longer-term evaluation. Our market regime analysis further demonstrates that LLM strategies are overly conservative in bull markets, underperforming passive benchmarks, and overly aggressive in bear markets, incurring heavy losses. These findings highlight the need to develop LLM strategies that are able to prioritise trend detection and regime-aware risk controls over mere scaling of framework complexity.
We present Seed1.5-VL, a vision-language foundation model designed to advance general-purpose multimodal understanding and reasoning. Seed1.5-VL is composed with a 532M-parameter vision encoder and a Mixture-of-Experts (MoE) LLM of 20B active parameters. Despite its relatively compact architecture, it delivers strong performance across a wide spectrum of public VLM benchmarks and internal evaluation suites, achieving the state-of-the-art performance on 38 out of 60 public benchmarks. Moreover, in agent-centric tasks such as GUI control and gameplay, Seed1.5-VL outperforms leading multimodal systems, including OpenAI CUA and Claude 3.7. Beyond visual and video understanding, it also demonstrates strong reasoning abilities, making it particularly effective for multimodal reasoning challenges such as visual puzzles. We believe these capabilities will empower broader applications across diverse tasks. In this report, we mainly provide a comprehensive review of our experiences in building Seed1.5-VL across model design, data construction, and training at various stages, hoping that this report can inspire further research. Seed1.5-VL is now accessible at https://www.volcengine.com/ (Volcano Engine Model ID: doubao-1-5-thinking-vision-pro-250428)
We propose DialogueReason, a reasoning paradigm that uncovers the lost roles in monologue-style reasoning models, aiming to boost diversity and coherency of the reasoning process. Recent advances in RL-based large reasoning models have led to impressive long CoT capabilities and high performance on math and science benchmarks. However, these reasoning models rely mainly on monologue-style reasoning, which often limits reasoning diversity and coherency, frequently recycling fixed strategies or exhibiting unnecessary shifts in attention. Our work consists of an analysis of monologue reasoning patterns and the development of a dialogue-based reasoning approach. We first introduce the Compound-QA task, which concatenates multiple problems into a single prompt to assess both diversity and coherency of reasoning. Our analysis shows that Compound-QA exposes weaknesses in monologue reasoning, evidenced by both quantitative metrics and qualitative reasoning traces. Building on the analysis, we propose a dialogue-based reasoning, named DialogueReason, structured around agents, environment, and interactions. Using PPO with rule-based rewards, we train open-source LLMs (Qwen-QWQ and Qwen-Base) to adopt dialogue reasoning. We evaluate trained models on MATH, AIME, and GPQA datasets, showing that the dialogue reasoning model outperforms monologue models under more complex compound questions. Additionally, we discuss how dialogue-based reasoning helps enhance interpretability, facilitate more intuitive human interaction, and inspire advances in multi-agent system design.
With the widespread application of large AI models in various fields, the automation level of multi-agent systems has been continuously improved. However, in high-risk decision-making scenarios such as healthcare and finance, human participation and the alignment of intelligent systems with human intentions remain crucial. This paper focuses on the financial scenario and constructs a multi-agent brainstorming framework based on the BDI theory. A human-computer collaborative multi-agent financial analysis process is built using Streamlit. The system plans tasks according to user intentions, reduces users' cognitive load through real-time updated structured text summaries and the interactive Cothinker module, and reasonably integrates general and reasoning large models to enhance the ability to handle complex problems. By designing a quantitative analysis algorithm for the sentiment tendency of interview content based on LLMs and a method for evaluating the diversity of ideas generated by LLMs in brainstorming based on k-means clustering and information entropy, the system is comprehensively evaluated. The results of human factors testing show that the system performs well in terms of usability and user experience. Although there is still room for improvement, it can effectively support users in completing complex financial tasks. The research shows that the system significantly improves the efficiency of human-computer interaction and the quality of decision-making in financial decision-making scenarios, providing a new direction for the development of related fields.
Large language models (LLMs) have demonstrated an impressive ability to role-play humans and replicate complex social dynamics. While large-scale social simulations are gaining increasing attention, they still face significant challenges, particularly regarding high time and computation costs. Existing solutions, such as distributed mechanisms or hybrid agent-based model (ABM) integrations, either fail to address inference costs or compromise accuracy and generalizability. To this end, we propose EcoLANG: Efficient and Effective Agent Communication Language Induction for Social Simulation. EcoLANG operates in two stages: (1) language evolution, where we filter synonymous words and optimize sentence-level rules through natural selection, and (2) language utilization, where agents in social simulations communicate using the evolved language. Experimental results demonstrate that EcoLANG reduces token consumption by over 20%, enhancing efficiency without sacrificing simulation accuracy.
Autonomous driving has made significant strides through data-driven techniques, achieving robust performance in standardized tasks. However, existing methods frequently overlook user-specific preferences, offering limited scope for interaction and adaptation with users. To address these challenges, we propose a "fast-slow" decision-making framework that integrates a Large Language Model (LLM) for high-level instruction parsing with a Reinforcement Learning (RL) agent for low-level real-time decision. In this dual system, the LLM operates as the "slow" module, translating user directives into structured guidance, while the RL agent functions as the "fast" module, making time-critical maneuvers under stringent latency constraints. By decoupling high-level decision making from rapid control, our framework enables personalized user-centric operation while maintaining robust safety margins. Experimental evaluations across various driving scenarios demonstrate the effectiveness of our method. Compared to baseline algorithms, the proposed architecture not only reduces collision rates but also aligns driving behaviors more closely with user preferences, thereby achieving a human-centric mode. By integrating user guidance at the decision level and refining it with real-time control, our framework bridges the gap between individual passenger needs and the rigor required for safe, reliable driving in complex traffic environments.
Current hardware security verification processes predominantly rely on manual threat modeling and test plan generation, which are labor-intensive, error-prone, and struggle to scale with increasing design complexity and evolving attack methodologies. To address these challenges, we propose ThreatLens, an LLM-driven multi-agent framework that automates security threat modeling and test plan generation for hardware security verification. ThreatLens integrates retrieval-augmented generation (RAG) to extract relevant security knowledge, LLM-powered reasoning for threat assessment, and interactive user feedback to ensure the generation of practical test plans. By automating these processes, the framework reduces the manual verification effort, enhances coverage, and ensures a structured, adaptable approach to security verification. We evaluated our framework on the NEORV32 SoC, demonstrating its capability to automate security verification through structured test plans and validating its effectiveness in real-world scenarios.
Agentic AI systems represent a new frontier in artificial intelligence, where agents often based on large language models(LLMs) interact with tools, environments, and other agents to accomplish tasks with a degree of autonomy. These systems show promise across a range of domains, but their architectural underpinnings remain immature. This paper conducts a comprehensive review of the types of agents, their modes of interaction with the environment, and the infrastructural and architectural challenges that emerge. We identify a gap in how these systems manage tool orchestration at scale and propose a reusable design abstraction: the "Control Plane as a Tool" pattern. This pattern allows developers to expose a single tool interface to an agent while encapsulating modular tool routing logic behind it. We position this pattern within the broader context of agent design and argue that it addresses several key challenges in scaling, safety, and extensibility.
Pedagogical Agents (PAs) show significant potential for boosting student engagement and learning outcomes by providing adaptive, on-demand support in educational contexts. However, existing PA solutions are often hampered by pre-scripted dialogue, unnatural animations, uncanny visual realism, and high development costs. To address these gaps, we introduce VTutor, an open-source SDK leveraging lightweight WebGL, Unity, and JavaScript frameworks. VTutor receives text outputs from a large language model (LLM), converts them into audio via text-to-speech, and then renders a real-time, lip-synced pedagogical agent (PA) for immediate, large-scale deployment on web-based learning platforms. By providing on-demand, personalized feedback, VTutor strengthens students' motivation and deepens their engagement with instructional material. Using an anime-like aesthetic, VTutor alleviates the uncanny valley effect, allowing learners to engage with expressive yet comfortably stylized characters. Our evaluation with 50 participants revealed that VTutor significantly outperforms the existing talking-head approaches (e.g., SadTalker) on perceived synchronization accuracy, naturalness, emotional expressiveness, and overall preference. As an open-source project, VTutor welcomes community-driven contributions - from novel character designs to specialized showcases of pedagogical agent applications - that fuel ongoing innovation in AI-enhanced education. By providing an accessible, customizable, and learner-centered PA solution, VTutor aims to elevate human-AI interaction experience in education fields, ultimately broadening the impact of AI in learning contexts. The demo link to VTutor is at https://vtutor-aied25.vercel.app.
As the Large-Language-Model-driven (LLM-driven) Artificial Intelligence (AI) bots became popular, people realized their strong potential in Task-Oriented Dialogue (TOD). However, bots relying wholly on LLMs are unreliable in their knowledge, and whether they can finally produce a correct result for the task is not guaranteed. The collaboration among these agents also remains a challenge, since the necessary information to convey is unclear, and the information transfer is by prompts -- unreliable, and malicious knowledge is easy to inject. With the help of logic programming tools such as Answer Set Programming (ASP), conversational agents can be built safely and reliably, and communication among the agents made more efficient and secure. We proposed an Administrator-Assistant Dual-Agent paradigm, where the two ASP-driven bots share the same knowledge base and complete their tasks independently, while the information can be passed by a Collaborative Rule Set (CRS). The knowledge and information conveyed are encapsulated and invisible to the users, ensuring the security of information transmission. We have constructed AutoManager, a dual-agent system for managing the drive-through window of a fast-food restaurant such as Taco Bell in the US. In AutoManager, the assistant bot takes the customer's order while the administrator bot manages the menu and food supply. We evaluated our AutoManager and compared it with the real-world Taco Bell Drive-Thru AI Order Taker, and the results show that our method is more reliable.
Recent advancements in Large Language Models (LLMs) and the introduction of the Model Context Protocol (MCP) have significantly expanded LLM agents' capability to interact dynamically with external tools and APIs. However, existing tool selection frameworks do not integrate MCP servers, instead relying heavily on error-prone manual updates to monolithic local tool repositories, leading to duplication, inconsistencies, and inefficiencies. Additionally, current approaches abstract tool selection before the LLM agent is invoked, limiting its autonomy and hindering dynamic re-querying capabilities during multi-turn interactions. To address these issues, we introduce ScaleMCP, a novel tool selection approach that dynamically equips LLM agents with a MCP tool retriever, giving agents the autonomy to add tools into their memory, as well as an auto-synchronizing tool storage system pipeline through CRUD (create, read, update, delete) operations with MCP servers as the single source of truth. We also propose a novel embedding strategy, Tool Document Weighted Average (TDWA), designed to selectively emphasize critical components of tool documents (e.g. tool name or synthetic questions) during the embedding process. Comprehensive evaluations conducted on a created dataset of 5,000 financial metric MCP servers, across 10 LLM models, 5 embedding models, and 5 retriever types, demonstrate substantial improvements in tool retrieval and agent invocation performance, emphasizing ScaleMCP's effectiveness in scalable, dynamic tool selection and invocation.
Recent advances in reinforcement learning, such as Dynamic Sampling Policy Optimization (DAPO), show strong performance when paired with large language models (LLMs). Motivated by this success, we ask whether similar gains can be realized in financial trading. We design a trading agent that combines an improved Group Relative Policy Optimization (GRPO) algorithm, augmented with ideas from DAPO, with LLM-based risk and sentiment signals extracted from financial news. On the NASDAQ-100 index (FNSPID dataset), our agent attains a cumulative return of 230.49 percent and an information ratio of 0.37, outperforming the CPPO-DeepSeek baseline. It also cuts training time from about 8 hours to 2.5 hours over 100 epochs while markedly reducing RAM usage. The proposed RL-LLM framework offers a scalable path toward data-efficient trading agents. Code: https://github.com/Ruijian-Zha/FinRL-DAPO-SR/
Security Operations Centers (SOCs) face growing challenges in managing cybersecurity threats due to an overwhelming volume of alerts, a shortage of skilled analysts, and poorly integrated tools. Human-AI collaboration offers a promising path to augment the capabilities of SOC analysts while reducing their cognitive overload. To this end, we introduce an AI-driven human-machine co-teaming paradigm that leverages large language models (LLMs) to enhance threat intelligence, alert triage, and incident response workflows. We present a vision in which LLM-based AI agents learn from human analysts the tacit knowledge embedded in SOC operations, enabling the AI agents to improve their performance on SOC tasks through this co-teaming. We invite SOCs to collaborate with us to further develop this process and uncover replicable patterns where human-AI co-teaming yields measurable improvements in SOC productivity.