Large Language Model (LLM) systems have been at the forefront of applied Artificial Intelligence (AI) research in a multitude of domains. One such domain is software development, where researchers have pushed the automation of a number of code tasks through LLM agents. Software development is a complex ecosystem, that stretches far beyond code implementation and well into the realm of code maintenance. In this paper, we propose a multi-agent system to localize bugs in large pre-existing codebases using information retrieval and LLMs. Our system introduces a novel Retrieval Augmented Generation (RAG) approach, Meta-RAG, where we utilize summaries to condense codebases by an average of 79.8\%, into a compact, structured, natural language representation. We then use an LLM agent to determine which parts of the codebase are critical for bug resolution, i.e. bug localization. We demonstrate the usefulness of Meta-RAG through evaluation with the SWE-bench Lite dataset. Meta-RAG scores 84.67 % and 53.0 % for file-level and function-level correct localization rates, respectively, achieving state-of-the-art performance.
Non-uniform structured network pruning methods can effectively reduce Large Language Model (LLM) size by eliminating redundant channels or layers, offering lower performance degradation than uniform strategies. However, existing non-uniform methods rely heavily on manually designed pruning policies (e.g., layer importance and scaling factors), and therefore cannot efficiently adapt to scenarios with dynamic pruning ratio requirements. Additionly, a critical bottleneck -- the time-consuming evaluation of pruning policies -- further limits the feasibility of iteratively and dynamically finding optimal pruning policies. To address these limitations, we propose PPF (Predictive Pruning Framework), a novel pruning framework for LLMs that eliminates manual design dependencies via second-level performance prediction. PPF not only supports real-time pruning decisions under dynamic pruning ratios but is also applicable to static pruning scenarios. It employs an agent for producing adaptive and real-time pruning actions, while a lightweight performance predictor that can evaluate a pruning policy in seconds, significantly speeding up the iterative optimization process. Experiments on Llama2-7B and Llama3-8B show that PPF can generate dynamic/static pruning policies and it reduces perplexity by up to 33.4% (dynamic pruning) and 84.78% (static pruning) over existing methods, outperforming manually designed pruning policies. The performance predictor achieves second-level performance prediction with high accuracy (prediction error < 0.0011). It reduces the mean evaluation latency from minute-level (1 minute and 38.02 seconds of test-set evaluation methods) to second-level (1.52 second), achieving over 64 times speedup. Our code will be available at https://github.com/Ma-zx/PPF .
Algorithmic trading requires short-term decisions aligned with long-term financial goals. While reinforcement learning (RL) has been explored for such tactical decisions, its adoption remains limited by myopic behavior and opaque policy rationale. In contrast, large language models (LLMs) have recently demonstrated strategic reasoning and multi-modal financial signal interpretation when guided by well-designed prompts. We propose a hybrid system where LLMs generate high-level trading strategies to guide RL agents in their actions. We evaluate (i) the rationale of LLM-generated strategies via expert review, and (ii) the Sharpe Ratio (SR) and Maximum Drawdown (MDD) of LLM-guided agents versus unguided baselines. Results show improved return and risk metrics over standard RL.
Fashion recommender systems (FaRS) face distinct challenges due to rapid trend shifts, nuanced user preferences, intricate item-item compatibility, and the complex interplay among consumers, brands, and influencers. Traditional recommendation approaches, largely static and retrieval-focused, struggle to effectively capture these dynamic elements, leading to decreased user satisfaction and elevated return rates. This paper synthesizes both academic and industrial viewpoints to map the distinctive output space and stakeholder ecosystem of modern FaRS, identifying the complex interplay among users, brands, platforms, and influencers, and highlighting the unique data and modeling challenges that arise. We outline a research agenda for industrial FaRS, centered on five representative scenarios spanning static queries, outfit composition, and multi-turn dialogue, and argue that mixed-modality refinement-the ability to combine image-based references (anchors) with nuanced textual constraints-is a particularly critical task for real-world deployment. To this end, we propose an Agentic Mixed-Modality Refinement (AMMR) pipeline, which fuses multimodal encoders with agentic LLM planners and dynamic retrieval, bridging the gap between expressive user intent and fast-changing fashion inventories. Our work shows that moving beyond static retrieval toward adaptive, generative, and stakeholder-aware systems is essential to satisfy the evolving expectations of fashion consumers and brands.
Financial AI holds great promise for transforming modern finance, with the potential to support a wide range of tasks such as market forecasting, portfolio management, quantitative trading, and automated analysis. However, existing platforms remain limited in task coverage, lack robust multimodal data integration, and offer insufficient support for the training and deployment of large language models (LLMs). In response to these limitations, we present FinWorld, an all-in-one open-source platform that provides end-to-end support for the entire financial AI workflow, from data acquisition to experimentation and deployment. FinWorld distinguishes itself through native integration of heterogeneous financial data, unified support for diverse AI paradigms, and advanced agent automation, enabling seamless development and deployment. Leveraging data from 2 representative markets, 4 stock pools, and over 800 million financial data points, we conduct comprehensive experiments on 4 key financial AI tasks. These experiments systematically evaluate deep learning and reinforcement learning algorithms, with particular emphasis on RL-based finetuning for LLMs and LLM Agents. The empirical results demonstrate that FinWorld significantly enhances reproducibility, supports transparent benchmarking, and streamlines deployment, thereby providing a strong foundation for future research and real-world applications. Code is available at Github~\footnote{https://github.com/DVampire/FinWorld}.
Virtual cell modeling represents an emerging frontier at the intersection of artificial intelligence and biology, aiming to predict quantities such as responses to diverse perturbations quantitatively. However, autonomously building computational models for virtual cells is challenging due to the complexity of biological systems, the heterogeneity of data modalities, and the need for domain-specific expertise across multiple disciplines. Here, we introduce CellForge, an agentic system that leverages a multi-agent framework that transforms presented biological datasets and research objectives directly into optimized computational models for virtual cells. More specifically, given only raw single-cell multi-omics data and task descriptions as input, CellForge outputs both an optimized model architecture and executable code for training virtual cell models and inference. The framework integrates three core modules: Task Analysis for presented dataset characterization and relevant literature retrieval, Method Design, where specialized agents collaboratively develop optimized modeling strategies, and Experiment Execution for automated generation of code. The agents in the Design module are separated into experts with differing perspectives and a central moderator, and have to collaboratively exchange solutions until they achieve a reasonable consensus. We demonstrate CellForge's capabilities in single-cell perturbation prediction, using six diverse datasets that encompass gene knockouts, drug treatments, and cytokine stimulations across multiple modalities. CellForge consistently outperforms task-specific state-of-the-art methods. Overall, CellForge demonstrates how iterative interaction between LLM agents with differing perspectives provides better solutions than directly addressing a modeling challenge. Our code is publicly available at https://github.com/gersteinlab/CellForge.
The emergence of the Internet of Agents (IoA) introduces critical challenges for communication privacy in sensitive, high-stakes domains. While standard Agent-to-Agent (A2A) protocols secure message content, they are not designed to protect the act of communication itself, leaving agents vulnerable to surveillance and traffic analysis. We find that the rich, event-driven nature of agent dialogues provides a powerful, yet untapped, medium for covert communication. To harness this potential, we introduce and formalize the Covert Event Channel, the first unified model for agent covert communication driven by three interconnected dimensions, which consist of the Storage, Timing,and Behavioral channels. Based on this model, we design and engineer {\Pi}CCAP, a novel protocol that operationalizes this event-driven paradigm. Our comprehensive evaluation demonstrates that {\Pi}CCAP achieves high capacity and robustness while remaining imperceptible to powerful LLM-based wardens, establishing its practical viability. By systematically engineering this channel, our work provides the foundational understanding essential for developing the next generation of monitoring systems and defensive protocols for a secure and trustworthy IoA.
As the reasoning capabilities of Large Language Models (LLMs) continue to advance, LLM-based agent systems offer advantages in flexibility and interpretability over traditional systems, garnering increasing attention. However, despite the widespread research interest and industrial application of agent systems, these systems, like their traditional counterparts, frequently encounter anomalies. These anomalies lead to instability and insecurity, hindering their further development. Therefore, a comprehensive and systematic approach to the operation and maintenance of agent systems is urgently needed. Unfortunately, current research on the operations of agent systems is sparse. To address this gap, we have undertaken a survey on agent system operations with the aim of establishing a clear framework for the field, defining the challenges, and facilitating further development. Specifically, this paper begins by systematically defining anomalies within agent systems, categorizing them into intra-agent anomalies and inter-agent anomalies. Next, we introduce a novel and comprehensive operational framework for agent systems, dubbed Agent System Operations (AgentOps). We provide detailed definitions and explanations of its four key stages: monitoring, anomaly detection, root cause analysis, and resolution.
Large language model (LLM) agents have demonstrated remarkable capabilities in complex reasoning and decision-making by leveraging external tools. However, this tool-centric paradigm introduces a previously underexplored attack surface: adversaries can manipulate tool metadata -- such as names, descriptions, and parameter schemas -- to influence agent behavior. We identify this as a new and stealthy threat surface that allows malicious tools to be preferentially selected by LLM agents, without requiring prompt injection or access to model internals. To demonstrate and exploit this vulnerability, we propose the Attractive Metadata Attack (AMA), a black-box in-context learning framework that generates highly attractive but syntactically and semantically valid tool metadata through iterative optimization. Our attack integrates seamlessly into standard tool ecosystems and requires no modification to the agent's execution framework. Extensive experiments across ten realistic, simulated tool-use scenarios and a range of popular LLM agents demonstrate consistently high attack success rates (81\%-95\%) and significant privacy leakage, with negligible impact on primary task execution. Moreover, the attack remains effective even under prompt-level defenses and structured tool-selection protocols such as the Model Context Protocol, revealing systemic vulnerabilities in current agent architectures. These findings reveal that metadata manipulation constitutes a potent and stealthy attack surface, highlighting the need for execution-level security mechanisms that go beyond prompt-level defenses.
Approximate nearest-neighbor search (ANNS) algorithms have become increasingly critical for recent AI applications, particularly in retrieval-augmented generation (RAG) and agent-based LLM applications. In this paper, we present CRINN, a new paradigm for ANNS algorithms. CRINN treats ANNS optimization as a reinforcement learning problem where execution speed serves as the reward signal. This approach enables the automatic generation of progressively faster ANNS implementations while maintaining accuracy constraints. Our experimental evaluation demonstrates CRINN's effectiveness across six widely-used NNS benchmark datasets. When compared against state-of-the-art open-source ANNS algorithms, CRINN achieves best performance on three of them (GIST-960-Euclidean, MNIST-784-Euclidean, and GloVe-25-angular), and tied for first place on two of them (SIFT-128-Euclidean and GloVe-25-angular). The implications of CRINN's success reach well beyond ANNS optimization: It validates that LLMs augmented with reinforcement learning can function as an effective tool for automating sophisticated algorithmic optimizations that demand specialized knowledge and labor-intensive manual refinement.Code can be found at https://github.com/deepreinforce-ai/CRINN
Large Language Model (LLM)-based agents have recently shown impressive capabilities in complex reasoning and tool use via multi-step interactions with their environments. While these agents have the potential to tackle complicated tasks, their problem-solving process, i.e., agents' interaction trajectory leading to task completion, remains underexploited. These trajectories contain rich feedback that can navigate agents toward the right directions for solving problems correctly. Although prevailing approaches, such as Monte Carlo Tree Search (MCTS), can effectively balance exploration and exploitation, they ignore the interdependence among various trajectories and lack the diversity of search spaces, which leads to redundant reasoning and suboptimal outcomes. To address these challenges, we propose SE-Agent, a Self-Evolution framework that enables Agents to optimize their reasoning processes iteratively. Our approach revisits and enhances former pilot trajectories through three key operations: revision, recombination, and refinement. This evolutionary mechanism enables two critical advantages: (1) it expands the search space beyond local optima by intelligently exploring diverse solution paths guided by previous trajectories, and (2) it leverages cross-trajectory inspiration to efficiently enhance performance while mitigating the impact of suboptimal reasoning paths. Through these mechanisms, SE-Agent achieves continuous self-evolution that incrementally improves reasoning quality. We evaluate SE-Agent on SWE-bench Verified to resolve real-world GitHub issues. Experimental results across five strong LLMs show that integrating SE-Agent delivers up to 55% relative improvement, achieving state-of-the-art performance among all open-source agents on SWE-bench Verified. Our code and demonstration materials are publicly available at https://github.com/wanghuacan/SE-Agent.
Coordinating multiple large language models (LLMs) to solve complex tasks collaboratively poses a fundamental trade-off between the computation costs and collective performance compared with individual model. We introduce a novel, game-theoretically grounded reinforcement learning (RL) framework, the Multi-Agent Cooperation Sequential Public Goods Game (MAC-SPGG), to systematically incentivize cooperation in multi-LLM ensembles. In MAC-SPGG, LLM agents move in sequence, observing predecessors' outputs and updating beliefs to condition their own contributions. By redesigning the public-goods reward, effortful contributions become the unique Subgame Perfect Nash Equilibrium (SPNE), which eliminates free-riding under traditional SPGG or PGG. Its sequential protocol replaces costly round-based information exchanges with a streamlined decision flow, cutting communication overhead while retaining strategic depth. We prove the existence and uniqueness of the SPNE under realistic parameters, and empirically show that MAC-SPGG-trained ensembles outperform single-agent baselines, chain-of-thought prompting, and other cooperative methods, even achieving comparable performance to large-scale models across reasoning, math, code generation, and NLP tasks. Our results highlight the power of structured, incentive-aligned MAC-SPGG cooperation for scalable and robust multi-agent language generation.
Electronic health records (EHRs) contain rich unstructured clinical notes that could enhance predictive modeling, yet extracting meaningful features from these notes remains challenging. Current approaches range from labor-intensive manual clinician feature generation (CFG) to fully automated representational feature generation (RFG) that lack interpretability and clinical relevance. Here we introduce SNOW (Scalable Note-to-Outcome Workflow), a modular multi-agent system powered by large language models (LLMs) that autonomously generates structured clinical features from unstructured notes without human intervention. We evaluated SNOW against manual CFG, clinician-guided LLM approaches, and RFG methods for predicting 5-year prostate cancer recurrence in 147 patients from Stanford Healthcare. While manual CFG achieved the highest performance (AUC-ROC: 0.771), SNOW matched this performance (0.761) without requiring any clinical expertise, significantly outperforming both baseline features alone (0.691) and all RFG approaches. The clinician-guided LLM method also performed well (0.732) but still required expert input. SNOW's specialized agents handle feature discovery, extraction, validation, post-processing, and aggregation, creating interpretable features that capture complex clinical information typically accessible only through manual review. Our findings demonstrate that autonomous LLM systems can replicate expert-level feature engineering at scale, potentially transforming how clinical ML models leverage unstructured EHR data while maintaining the interpretability essential for clinical deployment.
By combining classical planning methods with large language models (LLMs), recent research such as LLM+P has enabled agents to plan for general tasks given in natural language. However, scaling these methods to general-purpose service robots remains challenging: (1) classical planning algorithms generally require a detailed and consistent specification of the environment, which is not always readily available; and (2) existing frameworks mainly focus on isolated planning tasks, whereas robots are often meant to serve in long-term continuous deployments, and therefore must maintain a dynamic memory of the environment which can be updated with multi-modal inputs and extracted as planning knowledge for future tasks. To address these two issues, this paper introduces L3M+P (Lifelong LLM+P), a framework that uses an external knowledge graph as a representation of the world state. The graph can be updated from multiple sources of information, including sensory input and natural language interactions with humans. L3M+P enforces rules for the expected format of the absolute world state graph to maintain consistency between graph updates. At planning time, given a natural language description of a task, L3M+P retrieves context from the knowledge graph and generates a problem definition for classical planners. Evaluated on household robot simulators and on a real-world service robot, L3M+P achieves significant improvement over baseline methods both on accurately registering natural language state changes and on correctly generating plans, thanks to the knowledge graph retrieval and verification.
Anomaly detection in cloud sites remains a critical yet challenging task. Existing approaches that rely solely on metric data often suffer from high false positive rates (FPR) due to data imbalance between normal and anomalous events, leading to significant operational overhead for system reliance engineers. Recent advances in large language models (LLMs) offer new opportunities for integrating metrics with log data, enabling more accurate and interpretable anomaly detection. In this paper, we propose CloudAnoAgent, the first neuro-symbolic LLM-based agent for anomaly detection in cloud environments. CloudAnoAgent jointly processes structured metrics and textual log data in a unified pipeline, leveraging symbolic verification to validate detection hypotheses and generate structured anomaly reports. To support systematic evaluation, we introduce CloudAnoBench, the first benchmark that provides LLM-generated paired metrics and log data with fine-grained anomaly behavior annotations, filling a critical gap in existing datasets. Experimental results demonstrate that CloudAnoAgent improves anomaly classification accuracy by 46.36% and 36.67% on average and reduces the FPR by 36.67% and 33.89% on average over traditional baselines and LLM-only baseline, with a boost on anomaly type detection accuracy by 12.8% compared to vanilla LLM prompting. These results demonstrate the strengths of our approach in improving detection accuracy, reducing false positives, and enhancing interpretability, thereby supporting practical deployment in enterprise cloud environments.
With the rapid development of Model Context Protocol (MCP), the number of MCP servers has surpassed 10,000. However, existing MCP benchmarks are limited to single-server settings with only a few tools, hindering effective evaluation of agent capabilities in large-scale, real-world scenarios. To address this limitation, we present LiveMCPBench, the first comprehensive benchmark comprising 95 real-world tasks grounded in the MCP ecosystem, designed to evaluate LLM agents at scale across diverse servers. To support a scalable and reproducible evaluation pipeline in large-scale MCP environments, we curate LiveMCPTool, a diverse and readily deployable collection of 70 MCP servers and 527 tools. Furthermore, we introduce LiveMCPEval, an LLM-as-a-Judge framework that enables automated and adaptive evaluation in dynamic, time-varying task environments, achieving 81% agreement with human reviewers. Finally, we propose the MCP Copilot Agent, a multi-step agent that routes tools for dynamic planning and executes tools for API interaction across the entire LiveMCPTool suite. Our evaluation covers 10 leading models, with the best-performing model (Claude-Sonnet-4) reaching a 78.95% success rate. However, we observe large performance variance across models, and several widely-used models perform poorly in LiveMCPBench's complex, tool-rich environments. Overall, LiveMCPBench offers the first unified framework for benchmarking LLM agents in realistic, tool-rich, and dynamic MCP environments, laying a solid foundation for scalable and reproducible research on agent capabilities. Our code and data will be publicly available at https://icip-cas.github.io/LiveMCPBench.
Grounding natural language instructions to visual observations is fundamental for embodied agents operating in open-world environments. Recent advances in visual-language mapping have enabled generalizable semantic representations by leveraging vision-language models (VLMs). However, these methods often fall short in aligning free-form language commands with specific scene instances, due to limitations in both instance-level semantic consistency and instruction interpretation. We present OpenMap, a zero-shot open-vocabulary visual-language map designed for accurate instruction grounding in navigation tasks. To address semantic inconsistencies across views, we introduce a Structural-Semantic Consensus constraint that jointly considers global geometric structure and vision-language similarity to guide robust 3D instance-level aggregation. To improve instruction interpretation, we propose an LLM-assisted Instruction-to-Instance Grounding module that enables fine-grained instance selection by incorporating spatial context and expressive target descriptions. We evaluate OpenMap on ScanNet200 and Matterport3D, covering both semantic mapping and instruction-to-target retrieval tasks. Experimental results show that OpenMap outperforms state-of-the-art baselines in zero-shot settings, demonstrating the effectiveness of our method in bridging free-form language and 3D perception for embodied navigation.
The increasing use of Large Language Models (LLMs) in agentic applications highlights the need for robust safety guard models. While content safety in English is well-studied, non-English languages lack similar advancements due to the high cost of collecting culturally aligned labeled datasets. We present CultureGuard, a novel solution for curating culturally aligned, high-quality safety datasets across multiple languages. Our approach introduces a four-stage synthetic data generation and filtering pipeline: cultural data segregation, cultural data adaptation, machine translation, and quality filtering. This pipeline enables the conversion and expansion of the Nemotron-Content-Safety-Dataset-V2 English safety dataset into eight distinct languages: Arabic, German, Spanish, French, Hindi, Japanese, Thai, and Chinese. The resulting dataset, Nemotron-Content-Safety-Dataset-Multilingual-v1, comprises 386,661 samples in 9 languages and facilitates the training of Llama-3.1-Nemotron-Safety-Guard-Multilingual-8B-v1 via LoRA-based fine-tuning. The final model achieves state-of-the-art performance on several multilingual content safety benchmarks. We also benchmark the latest open LLMs on multilingual safety and observe that these LLMs are more prone to give unsafe responses when prompted in non-English languages. This work represents a significant step toward closing the safety gap in multilingual LLMs by enabling the development of culturally aware safety guard models.
Retrieval-Augmented Generation (RAG) has emerged as a promising framework for enhancing the capabilities of Large Language Models (LLMs), especially in knowledge-intensive tasks. Despite its advantages, current RAG methods often struggle to *fully exploit knowledge during generation*. In particular, the synergy between the model's internal parametric knowledge and external retrieved knowledge remains limited. Retrieved contents may sometimes mislead generation, while certain generated content can guide the model toward more accurate outputs. In this work, we propose Collaborative Chain-of-Agents, a framework designed to enhance explicitly synergy over both parametric and retrieved knowledge. Specifically, we first introduce CoCoA-zero, a multi-agent RAG framework that first performs conditional knowledge induction and then reasons answers. Building on this, we develop CoCoA, a long-chain training strategy that synthesizes extended multi-agent reasoning trajectories from CoCoA-zero to fine-tune the LLM. This strategy enhances the model's capability to explicitly integrate and jointly leverage parametric and retrieved knowledge. Experiments results show that CoCoA-zero and CoCoA achieve superior performance on open-domain and multi-hop QA tasks.
This research presents LLM Pokemon League, a competitive tournament system that leverages Large Language Models (LLMs) as intelligent agents to simulate strategic decision-making in Pok\'emon battles. The platform is designed to analyze and compare the reasoning, adaptability, and tactical depth exhibited by different LLMs in a type-based, turn-based combat environment. By structuring the competition as a single-elimination tournament involving diverse AI trainers, the system captures detailed decision logs, including team-building rationale, action selection strategies, and switching decisions. The project enables rich exploration into comparative AI behavior, battle psychology, and meta-strategy development in constrained, rule-based game environments. Through this system, we investigate how modern LLMs understand, adapt, and optimize decisions under uncertainty, making Pok\'emon League a novel benchmark for AI research in strategic reasoning and competitive learning.
The Polymorphic Combinatorial Framework (PCF) leverages Large Language Models (LLMs) and mathematical frameworks to guide the meta-prompt enabled design of solution spaces and adaptive AI agents for complex, dynamic environments. Unlike static agent architectures, PCF enables real-time parameter reconfiguration through mathematically-grounded combinatorial spaces, allowing agents to adapt their core behavioral traits dynamically. Grounded in combinatorial logic, topos theory, and rough fuzzy set theory, PCF defines a multidimensional SPARK parameter space (Skills, Personalities, Approaches, Resources, Knowledge) to capture agent behaviors. This paper demonstrates how LLMs can parameterize complex spaces and estimate likely parameter values/variabilities. Using PCF, we parameterized mock caf\'e domains (five levels of complexity), estimated variables/variabilities, and conducted over 1.25 million Monte Carlo simulations. The results revealed trends in agent adaptability and performance across the five complexity tiers, with diminishing returns at higher complexity levels highlighting thresholds for scalable designs. PCF enables the generation of optimized agent configurations for specific scenarios while maintaining logical consistency. This framework supports scalable, dynamic, explainable, and ethical AI applications in domains like customer service, healthcare, robotics, and collaborative systems, paving the way for adaptable and cooperative next-generation polymorphic agents.
Training software engineering (SWE) LLMs is bottlenecked by expensive infrastructure, inefficient evaluation pipelines, scarce training data, and costly quality control. We present RepoForge, an autonomous, end-to-end pipeline that generates, evaluates, and trains SWE agents at scale. Our key contributions include: (1) RepoForge-8B-Agent, achieving 17.4\% on SWE-Bench-Verified~\citep{swebench_verified2024}, establishing new state-of-the-art for $\leq$8B non-thinking LLMs; (2) 7,304 executable environments auto-generated from real GitHub commits with zero manual intervention; (3) 14$\times$ storage reduction (1.4GB $\rightarrow$ 102MB per instance) via intelligent dependency management and image pruning; (4) $>$70\% faster evaluation using a Ray-powered~\citep{ray2018} distributed RepoForge harness; (5) 19,000$\times$ cheaper labeling through our automated SPICE~\citep{spice2024} difficulty assessment technique. By unifying storage-efficient sandboxing, Ray-powered evaluation harness, automated data generation, SPICE-based labeling, and bubble-free RL scaffold, we demonstrate that even $\leq$8B models can reach new state-of-the-art performance on demanding benchmarks like SWE-Bench-Verified. Our approach addresses critical bottlenecks in SWE agent training: high storage costs of container-based evaluation, inefficient sequential reward pipelines, limited availability of high-quality training data, expensive manual labeling, and multi-turn RL pipeline bottlenecks.
Large Language Models (LLMs) are increasingly deployed in autonomous decision-making roles across high-stakes domains. However, since models are trained on human-generated data, they may inherit cognitive biases that systematically distort human judgment, including escalation of commitment, where decision-makers continue investing in failing courses of action due to prior investment. Understanding when LLMs exhibit such biases presents a unique challenge. While these biases are well-documented in humans, it remains unclear whether they manifest consistently in LLMs or require specific triggering conditions. This paper investigates this question using a two-stage investment task across four experimental conditions: model as investor, model as advisor, multi-agent deliberation, and compound pressure scenario. Across N = 6,500 trials, we find that bias manifestation in LLMs is highly context-dependent. In individual decision-making contexts (Studies 1-2, N = 4,000), LLMs demonstrate strong rational cost-benefit logic with minimal escalation of commitment. However, multi-agent deliberation reveals a striking hierarchy effect (Study 3, N = 500): while asymmetrical hierarchies show moderate escalation rates (46.2%), symmetrical peer-based decision-making produces near-universal escalation (99.2%). Similarly, when subjected to compound organizational and personal pressures (Study 4, N = 2,000), models exhibit high degrees of escalation of commitment (68.95% average allocation to failing divisions). These findings reveal that LLM bias manifestation depends critically on social and organizational context rather than being inherent, with significant implications for the deployment of multi-agent systems and unsupervised operations where such conditions may emerge naturally.
Large language models (LLMs) present new opportunities for creating pedagogical agents that engage in meaningful dialogue to support student learning. However, the current use of LLM systems like ChatGPT in classrooms often lacks the solid theoretical foundation found in earlier intelligent tutoring systems. To bridge this gap, we propose a framework that combines Evidence-Centered Design with Social Cognitive Theory for adaptive scaffolding in LLM-based agents focused on STEM+C learning. We illustrate this framework with Inquizzitor, an LLM-based formative assessment agent that integrates human-AI hybrid intelligence and provides feedback grounded in cognitive science principles. Our findings show that Inquizzitor delivers high-quality assessment and interaction aligned with core learning theories, offering teachers effective guidance that students value. This research underscores the potential for theory-driven LLM integration in education, highlighting the ability of these systems to provide adaptive and principled instruction.
Machine learning and Large language models (LLMs) for vulnerability detection has received significant attention in recent years. Unfortunately, state-of-the-art techniques show that LLMs are unsuccessful in even distinguishing the vulnerable function from its benign counterpart, due to three main problems: Vulnerability detection requires deep analysis, which LLMs often struggle with when making a one-shot prediction. Existing techniques typically perform function-level analysis, whereas effective vulnerability detection requires contextual information beyond the function scope. The focus on binary classification can result in identifying a vulnerability but associating it with the wrong security weaknesses (CWE), which may mislead developers. We propose a novel multi-agent LLM approach to address the challenges of identifying CWEs. This approach consists of three steps: (1) a team of LLM agents performs an exhaustive search for potential CWEs in the function under review, (2) another team of agents identifies relevant external context to support or refute each candidate CWE, and (3) a final agent makes informed acceptance or rejection decisions for each CWE based on the gathered context. A preliminary evaluation of our approach shows promising results. In the PrimeVul dataset, Step 1 correctly identifies the appropriate CWE in 40.9\% of the studied vulnerable functions. We further evaluated the full pipeline on ten synthetic programs and found that incorporating context information significantly reduced false positives from 6 to 9 CWEs to just 1 to 2, while still correctly identifying the true CWE in 9 out of 10 cases.
The continuous evolution and enhanced reasoning capabilities of large language models (LLMs) have elevated their role in complex tasks, notably in travel planning, where demand for personalized, high-quality itineraries is rising. However, current benchmarks often rely on unrealistic simulated data, failing to reflect the differences between LLM-generated and real-world itineraries. Existing evaluation metrics, which primarily emphasize constraints, fall short of providing a comprehensive assessment of the overall quality of travel plans. To address these limitations, we introduce TripTailor, a benchmark designed specifically for personalized travel planning in real-world scenarios. This dataset features an extensive collection of over 500,000 real-world points of interest (POIs) and nearly 4,000 diverse travel itineraries, complete with detailed information, providing a more authentic evaluation framework. Experiments show that fewer than 10\% of the itineraries generated by the latest state-of-the-art LLMs achieve human-level performance. Moreover, we identify several critical challenges in travel planning, including the feasibility, rationality, and personalized customization of the proposed solutions. We hope that TripTailor will drive the development of travel planning agents capable of understanding and meeting user needs while generating practical itineraries. Our code and dataset are available at https://github.com/swxkfm/TripTailor
Advances in generative models have led to AI-generated images visually indistinguishable from authentic ones. Despite numerous studies on detecting AI-generated images with classifiers, a gap persists between such methods and human cognitive forensic analysis. We present ForenX, a novel method that not only identifies the authenticity of images but also provides explanations that resonate with human thoughts. ForenX employs the powerful multimodal large language models (MLLMs) to analyze and interpret forensic cues. Furthermore, we overcome the limitations of standard MLLMs in detecting forgeries by incorporating a specialized forensic prompt that directs the MLLMs attention to forgery-indicative attributes. This approach not only enhance the generalization of forgery detection but also empowers the MLLMs to provide explanations that are accurate, relevant, and comprehensive. Additionally, we introduce ForgReason, a dataset dedicated to descriptions of forgery evidences in AI-generated images. Curated through collaboration between an LLM-based agent and a team of human annotators, this process provides refined data that further enhances our model's performance. We demonstrate that even limited manual annotations significantly improve explanation quality. We evaluate the effectiveness of ForenX on two major benchmarks. The model's explainability is verified by comprehensive subjective evaluations.
Online behavioural research faces an emerging threat as participants increasingly turn to large language models (LLMs) for advice, translation, or task delegation: LLM Pollution. We identify three interacting variants through which LLM Pollution threatens the validity and integrity of online behavioural research. First, Partial LLM Mediation occurs when participants make selective use of LLMs for specific aspects of a task, such as translation or wording support, leading researchers to (mis)interpret LLM-shaped outputs as human ones. Second, Full LLM Delegation arises when agentic LLMs complete studies with little to no human oversight, undermining the central premise of human-subject research at a more foundational level. Third, LLM Spillover signifies human participants altering their behaviour as they begin to anticipate LLM presence in online studies, even when none are involved. While Partial Mediation and Full Delegation form a continuum of increasing automation, LLM Spillover reflects second-order reactivity effects. Together, these variants interact and generate cascading distortions that compromise sample authenticity, introduce biases that are difficult to detect post hoc, and ultimately undermine the epistemic grounding of online research on human cognition and behaviour. Crucially, the threat of LLM Pollution is already co-evolving with advances in generative AI, creating an escalating methodological arms race. To address this, we propose a multi-layered response spanning researcher practices, platform accountability, and community efforts. As the challenge evolves, coordinated adaptation will be essential to safeguard methodological integrity and preserve the validity of online behavioural research.
We present an autonomous framework that leverages Large Language Models (LLMs) to automate end-to-end business analysis and market report generation. At its core, the system employs specialized agents - Researcher, Reviewer, Writer, and Retriever - that collaborate to analyze data and produce comprehensive reports. These agents learn from real professional consultants' presentation materials at Amazon through in-context learning to replicate professional analytical methodologies. The framework executes a multi-step process: querying databases, analyzing data, generating insights, creating visualizations, and composing market reports. We also introduce a novel LLM-based evaluation system for assessing report quality, which shows alignment with expert human evaluations. Building on these evaluations, we implement an iterative improvement mechanism that optimizes report quality through automated review cycles. Experimental results show that report quality can be improved by both automated review cycles and consultants' unstructured knowledge. In experimental validation, our framework generates detailed 6-page reports in 7 minutes at a cost of approximately \$1. Our work could be an important step to automatically create affordable market insights.
The rapid adoption of agentic AI, powered by large language models (LLMs), is transforming enterprise ecosystems with autonomous agents that execute complex workflows. Yet we observe several key security vulnerabilities in LLM-driven multi-agent systems (MASes): fragmented identity frameworks, insecure communication channels, and inadequate defenses against Byzantine agents or adversarial prompts. In this paper, we present the first systematic analysis of these emerging multi-agent risks and explain why the legacy security strategies cannot effectively address these risks. Afterwards, we propose BlockA2A, the first unified multi-agent trust framework that enables secure and verifiable and agent-to-agent interoperability. At a high level, BlockA2A adopts decentralized identifiers (DIDs) to enable fine-grained cross-domain agent authentication, blockchain-anchored ledgers to enable immutable auditability, and smart contracts to dynamically enforce context-aware access control policies. BlockA2A eliminates centralized trust bottlenecks, ensures message authenticity and execution integrity, and guarantees accountability across agent interactions. Furthermore, we propose a Defense Orchestration Engine (DOE) that actively neutralizes attacks through real-time mechanisms, including Byzantine agent flagging, reactive execution halting, and instant permission revocation. Empirical evaluations demonstrate BlockA2A's effectiveness in neutralizing prompt-based, communication-based, behavioral and systemic MAS attacks. We formalize its integration into existing MAS and showcase a practical implementation for Google's A2A protocol. Experiments confirm that BlockA2A and DOE operate with sub-second overhead, enabling scalable deployment in production LLM-based MAS environments.