How well do AI systems perform in algorithm engineering for hard optimization problems in domains such as package-delivery routing, crew scheduling, factory production planning, and power-grid balancing? We introduce ALE-Bench, a new benchmark for evaluating AI systems on score-based algorithmic programming contests. Drawing on real tasks from the AtCoder Heuristic Contests, ALE-Bench presents optimization problems that are computationally hard and admit no known exact solution. Unlike short-duration, pass/fail coding benchmarks, ALE-Bench encourages iterative solution refinement over long time horizons. Our software framework supports interactive agent architectures that leverage test-run feedback and visualizations. Our evaluation of frontier LLMs revealed that while they demonstrate high performance on specific problems, a notable gap remains compared to humans in terms of consistency across problems and long-horizon problem-solving capabilities. This highlights the need for this benchmark to foster future AI advancements.
Coordinating multiple embodied agents in dynamic environments remains a core challenge in artificial intelligence, requiring both perception-driven reasoning and scalable cooperation strategies. While recent works have leveraged large language models (LLMs) for multi-agent planning, a few have begun to explore vision-language models (VLMs) for visual reasoning. However, these VLM-based approaches remain limited in their support for diverse embodiment types. In this work, we introduce VIKI-Bench, the first hierarchical benchmark tailored for embodied multi-agent cooperation, featuring three structured levels: agent activation, task planning, and trajectory perception. VIKI-Bench includes diverse robot embodiments, multi-view visual observations, and structured supervision signals to evaluate reasoning grounded in visual inputs. To demonstrate the utility of VIKI-Bench, we propose VIKI-R, a two-stage framework that fine-tunes a pretrained vision-language model (VLM) using Chain-of-Thought annotated demonstrations, followed by reinforcement learning under multi-level reward signals. Our extensive experiments show that VIKI-R significantly outperforms baselines method across all task levels. Furthermore, we show that reinforcement learning enables the emergence of compositional cooperation patterns among heterogeneous agents. Together, VIKI-Bench and VIKI-R offer a unified testbed and method for advancing multi-agent, visual-driven cooperation in embodied AI systems.
Leveraging multiple Large Language Models(LLMs) has proven effective for addressing complex, high-dimensional tasks, but current approaches often rely on static, manually engineered multi-agent configurations. To overcome these constraints, we present the Agentic Neural Network(ANN), a framework that conceptualizes multi-agent collaboration as a layered neural network architecture. In this design, each agent operates as a node, and each layer forms a cooperative "team" focused on a specific subtask. Agentic Neural Network follows a two-phase optimization strategy: (1) Forward Phase-Drawing inspiration from neural network forward passes, tasks are dynamically decomposed into subtasks, and cooperative agent teams with suitable aggregation methods are constructed layer by layer. (2) Backward Phase-Mirroring backpropagation, we refine both global and local collaboration through iterative feedback, allowing agents to self-evolve their roles, prompts, and coordination. This neuro-symbolic approach enables ANN to create new or specialized agent teams post-training, delivering notable gains in accuracy and adaptability. Across four benchmark datasets, ANN surpasses leading multi-agent baselines under the same configurations, showing consistent performance improvements. Our findings indicate that ANN provides a scalable, data-driven framework for multi-agent systems, combining the collaborative capabilities of LLMs with the efficiency and flexibility of neural network principles. We plan to open-source the entire framework.
As AI agents powered by Large Language Models (LLMs) become increasingly versatile and capable of addressing a broad spectrum of tasks, ensuring their security has become a critical challenge. Among the most pressing threats are prompt injection attacks, which exploit the agent's resilience on natural language inputs -- an especially dangerous threat when agents are granted tool access or handle sensitive information. In this work, we propose a set of principled design patterns for building AI agents with provable resistance to prompt injection. We systematically analyze these patterns, discuss their trade-offs in terms of utility and security, and illustrate their real-world applicability through a series of case studies.
Data science aims to extract insights from data to support decision-making processes. Recently, Large Language Models (LLMs) are increasingly used as assistants for data science, by suggesting ideas, techniques and small code snippets, or for the interpretation of results and reporting. Proper automation of some data-science activities is now promised by the rise of LLM agents, i.e., AI systems powered by an LLM equipped with additional affordances--such as code execution and knowledge bases--that can perform self-directed actions and interact with digital environments. In this paper, we survey the evaluation of LLM assistants and agents for data science. We find (1) a dominant focus on a small subset of goal-oriented activities, largely ignoring data management and exploratory activities; (2) a concentration on pure assistance or fully autonomous agents, without considering intermediate levels of human-AI collaboration; and (3) an emphasis on human substitution, therefore neglecting the possibility of higher levels of automation thanks to task transformation.
Large language models (LLMs) have shown impressive capabilities on numerous natural language processing tasks. However, LLMs still struggle with numerical question answering for financial documents that include tabular and textual data. Recent works have showed the effectiveness of critic agents (i.e., self-correction) for this task given oracle labels. Building upon this framework, this paper examines the effectiveness of the traditional critic agent when oracle labels are not available, and show, through experiments, that this critic agent's performance deteriorates in this scenario. With this in mind, we present an improved critic agent, along with the calculator agent which outperforms the previous state-of-the-art approach (program-of-thought) and is safer. Furthermore, we investigate how our agents interact with each other, and how this interaction affects their performance.
In this work, we approach spoken Dialogue State Tracking (DST) by bridging the representation spaces of speech encoders and LLMs via a small connector module, with a focus on fully open-sourced and open-data components (WavLM-large, OLMo). We focus on ablating different aspects of such systems including full/LoRA adapter fine-tuning, the effect of agent turns in the dialogue history, as well as fuzzy matching-based output post-processing, which greatly improves performance of our systems on named entities in the dialogue slot values. We conduct our experiments on the SpokenWOZ dataset, and additionally utilize the Speech-Aware MultiWOZ dataset to augment our training data. Ultimately, our best-performing WavLM + connector + OLMo-1B aligned models achieve state of the art on the SpokenWOZ test set (34.66% JGA), and our system with Gemma-2-9B-instruct further surpasses this result, reaching 42.17% JGA on SpokenWOZ test.
Large Language Model (LLM)-driven Multi-agent systems (Mas) have recently emerged as a powerful paradigm for tackling complex real-world tasks. However, existing Mas construction methods typically rely on manually crafted interaction mechanisms or heuristic rules, introducing human biases and constraining the autonomous ability. Even with recent advances in adaptive Mas construction, existing systems largely remain within the paradigm of semi-autonomous patterns. In this work, we propose MasHost, a Reinforcement Learning (RL)-based framework for autonomous and query-adaptive Mas design. By formulating Mas construction as a graph search problem, our proposed MasHost jointly samples agent roles and their interactions through a unified probabilistic sampling mechanism. Beyond the accuracy and efficiency objectives pursued in prior works, we introduce component rationality as an additional and novel design principle in Mas. To achieve this multi-objective optimization, we propose Hierarchical Relative Policy Optimization (HRPO), a novel RL strategy that collaboratively integrates group-relative advantages and action-wise rewards. To our knowledge, our proposed MasHost is the first RL-driven framework for autonomous Mas graph construction. Extensive experiments on six benchmarks demonstrate that MasHost consistently outperforms most competitive baselines, validating its effectiveness, efficiency, and structure rationality.
Large language model (LLM) have become mainstream methods in the field of sarcasm detection. However, existing LLM methods face challenges in irony detection, including: 1. single-perspective limitations, 2. insufficient comprehensive understanding, and 3. lack of interpretability. This paper introduces the Collaborative Agent Framework for Irony (CAF-I), an LLM-driven multi-agent system designed to overcome these issues. CAF-I employs specialized agents for Context, Semantics, and Rhetoric, which perform multidimensional analysis and engage in interactive collaborative optimization. A Decision Agent then consolidates these perspectives, with a Refinement Evaluator Agent providing conditional feedback for optimization. Experiments on benchmark datasets establish CAF-I's state-of-the-art zero-shot performance. Achieving SOTA on the vast majority of metrics, CAF-I reaches an average Macro-F1 of 76.31, a 4.98 absolute improvement over the strongest prior baseline. This success is attained by its effective simulation of human-like multi-perspective analysis, enhancing detection accuracy and interpretability.
Machine translation has long been a central task in natural language processing. With the rapid advancement of large language models (LLMs), there has been remarkable progress in translation quality. However, fully realizing the translation potential of LLMs remains an open challenge. Recent studies have explored multi-agent systems to decompose complex translation tasks into collaborative subtasks, showing initial promise in enhancing translation quality through agent cooperation and specialization. Nevertheless, existing multi-agent translation frameworks largely neglect foundational insights from cognitive translation studies. These insights emphasize how human translators employ different cognitive strategies, such as balancing literal and free translation, refining expressions based on context, and iteratively evaluating outputs. To address this limitation, we propose a cognitively informed multi-agent framework called TACTIC, which stands for T ranslation A gents with Cognitive- T heoretic Interactive Collaboration. The framework comprises six functionally distinct agents that mirror key cognitive processes observed in human translation behavior. These include agents for drafting, refinement, evaluation, scoring, context reasoning, and external knowledge gathering. By simulating an interactive and theory-grounded translation workflow, TACTIC effectively leverages the full capacity of LLMs for high-quality translation. Experimental results on diverse language pairs from the FLORES-200 and WMT24 benchmarks show that our method consistently achieves state-of-the-art performance. Using DeepSeek-V3 as the base model, TACTIC surpasses GPT-4.1 by an average of +0.6 XCOMET and +1.18 COMETKIWI-23. Compared to DeepSeek-R1, it further improves by +0.84 XCOMET and +2.99 COMETKIWI-23. Code is available at https://github.com/weiyali126/TACTIC.
Leveraging more test-time computation has proven to be an effective way to boost the reasoning capabilities of large language models (LLMs). Among various methods, the verify-and-improve paradigm stands out for enabling dynamic solution exploration and feedback incorporation. However, existing approaches often suffer from restricted feedback spaces and lack of coordinated training of different parties, leading to suboptimal performance. To address this, we model this multi-turn refinement process as a Markov Decision Process and introduce DPSDP (Direct Policy Search by Dynamic Programming), a reinforcement learning algorithm that trains an actor-critic LLM system to iteratively refine answers via direct preference learning on self-generated data. Theoretically, DPSDP can match the performance of any policy within the training distribution. Empirically, we instantiate DPSDP with various base models and show improvements on both in- and out-of-distribution benchmarks. For example, on benchmark MATH 500, majority voting over five refinement steps increases first-turn accuracy from 58.2% to 63.2% with Ministral-based models. An ablation study further confirms the benefits of multi-agent collaboration and out-of-distribution generalization.
Large language models (LLMs) can face factual limitations when responding to
time-sensitive queries about recent events that arise after their knowledge
thresholds in the training corpus. Existing search-augmented approaches fall
into two categories, each with distinct limitations: multi-agent search
frameworks incur substantial computational overhead by separating search
planning and response synthesis across multiple LLMs, while single-LLM
tool-calling methods restrict themselves to sequential planned, single-query
searches from sole search sources. We present Reasoning-Search (R-Search), a
single-LLM search framework that unifies multi-step planning, multi-source
search execution, and answer synthesis within one coherent inference process.
Innovatively, it structure the output into four explicitly defined components,
including reasoning steps that guide the search process (
Despite their growing adoption across domains, large language model (LLM)-powered agents face significant security risks from backdoor attacks during training and fine-tuning. These compromised agents can subsequently be manipulated to execute malicious operations when presented with specific triggers in their inputs or environments. To address this pressing risk, we present ReAgent, a novel defense against a range of backdoor attacks on LLM-based agents. Intuitively, backdoor attacks often result in inconsistencies among the user's instruction, the agent's planning, and its execution. Drawing on this insight, ReAgent employs a two-level approach to detect potential backdoors. At the execution level, ReAgent verifies consistency between the agent's thoughts and actions; at the planning level, ReAgent leverages the agent's capability to reconstruct the instruction based on its thought trajectory, checking for consistency between the reconstructed instruction and the user's instruction. Extensive evaluation demonstrates ReAgent's effectiveness against various backdoor attacks across tasks. For instance, ReAgent reduces the attack success rate by up to 90\% in database operation tasks, outperforming existing defenses by large margins. This work reveals the potential of utilizing compromised agents themselves to mitigate backdoor risks.
Machine learning has been widely used to optimize complex engineering workflows across numerous domains. In the context of integrated circuit design, modern flows (e.g., going from a register-transfer level netlist to physical layouts) involve extensive configuration via thousands of parameters, and small changes to these parameters can have large downstream impacts on desired outcomes - namely design performance, power, and area. Recent advances in Large Language Models (LLMs) offer new opportunities for learning and reasoning within such high-dimensional optimization tasks. In this work, we introduce ORFS-agent, an LLM-based iterative optimization agent that automates parameter tuning in an open-source hardware design flow. ORFS-agent adaptively explores parameter configurations, demonstrating clear improvements over standard Bayesian optimization approaches in terms of resource efficiency and final design metrics. Our empirical evaluations on two different technology nodes and a range of circuit benchmarks indicate that ORFS-agent can improve both routed wirelength and effective clock period by over 13%, all while using 40% fewer optimization iterations. Moreover, by following natural language objectives to trade off certain metrics for others, ORFS-agent demonstrates a flexible and interpretable framework for multi-objective optimization. Crucially, RFS-agent is modular and model-agnostic, and can be plugged in to any frontier LLM without any further fine-tuning.
With the advent of large language models (LLMs), software engineering agents (SWE agents) have emerged as a powerful paradigm for automating a range of software tasks -- from code generation and repair to test case synthesis. These agents operate autonomously by interpreting user input and responding to environmental feedback. While various agent architectures have demonstrated strong empirical performance, the internal decision-making worfklows that drive their behavior remain poorly understood. Deeper insight into these workflows hold promise for improving both agent reliability and efficiency. In this work, we present the first systematic study of SWE agent behavior through the lens of execution traces. Our contributions are as follows: (1) we propose the first taxonomy of decision-making pathways across five representative agents; (2) using this taxonomy, we identify three core components essential to agent success -- bug localization, patch generation, and reproduction test generation -- and study each in depth; (3) we study the impact of test generation on successful patch production; and analyze strategies that can lead to successful test generation; (4) we further conduct the first large-scale code clone analysis comparing agent-generated and developer-written patches and provide a qualitative study revealing structural and stylistic differences in patch content. Together, these findings offer novel insights into agent design and open avenues for building agents that are both more effective and more aligned with human development practices.
While existing benchmarks probe the reasoning abilities of large language models (LLMs) across diverse domains, they predominantly assess passive reasoning, providing models with all the information needed to reach a solution. By contrast, active reasoning-where an LLM must interact with external systems to acquire missing evidence or data-has received little systematic attention. To address this shortfall, we present AR-Bench, a novel benchmark designed explicitly to evaluate an LLM's active reasoning skills. AR-Bench comprises three task families-detective cases, situation puzzles, and guessing numbers-that together simulate real-world, agentic scenarios and measure performance across commonsense, logical, and symbolic reasoning challenges. Empirical evaluation on AR-Bench demonstrates that contemporary LLMs exhibit pronounced difficulties with active reasoning: they frequently fail to acquire or leverage the information needed to solve tasks. This gap highlights a stark divergence between their passive and active reasoning abilities. Moreover, ablation studies indicate that even advanced strategies, such as tree-based searching or post-training approaches, yield only modest gains and fall short of the levels required for real-world deployment. Collectively, these findings highlight the critical need to advance methodology for active reasoning, e.g., incorporating interactive learning, real-time feedback loops, and environment-aware objectives for training. The benchmark is publicly available at: https://github.com/tmlr-group/AR-Bench.
Multi-agent frameworks can substantially boost the reasoning power of large language models (LLMs), but they typically incur heavy computational costs and lack convergence guarantees. To overcome these challenges, we recast multi-LLM coordination as an incomplete-information game and seek a Bayesian Nash equilibrium (BNE), in which each agent optimally responds to its probabilistic beliefs about the strategies of others. We introduce Efficient Coordination via Nash Equilibrium (ECON), a hierarchical reinforcement-learning paradigm that marries distributed reasoning with centralized final output. Under ECON, each LLM independently selects responses that maximize its expected reward, conditioned on its beliefs about co-agents, without requiring costly inter-agent exchanges. We mathematically prove that ECON attains a markedly tighter regret bound than non-equilibrium multi-agent schemes. Empirically, ECON outperforms existing multi-LLM approaches by 11.2% on average across six benchmarks spanning complex reasoning and planning tasks. Further experiments demonstrate ECON's ability to flexibly incorporate additional models, confirming its scalability and paving the way toward larger, more powerful multi-LLM ensembles. The code is publicly available at: https://github.com/tmlr-group/ECON.
We introduce EconWebArena, a benchmark for evaluating autonomous agents on complex, multimodal economic tasks in realistic web environments. The benchmark comprises 360 curated tasks from 82 authoritative websites spanning domains such as macroeconomics, labor, finance, trade, and public policy. Each task challenges agents to navigate live websites, interpret structured and visual content, interact with real interfaces, and extract precise, time-sensitive data through multi-step workflows. We construct the benchmark by prompting multiple large language models (LLMs) to generate candidate tasks, followed by rigorous human curation to ensure clarity, feasibility, and source reliability. Unlike prior work, EconWebArena emphasizes fidelity to authoritative data sources and the need for grounded web-based economic reasoning. We evaluate a diverse set of state-of-the-art multimodal LLMs as web agents, analyze failure cases, and conduct ablation studies to assess the impact of visual grounding, plan-based reasoning, and interaction design. Our results reveal substantial performance gaps and highlight persistent challenges in grounding, navigation, and multimodal understanding, positioning EconWebArena as a rigorous testbed for economic web intelligence.
Large Language Models (LLMs) demonstrate impressive general-purpose reasoning and problem-solving abilities. However, they struggle with executing complex, long-horizon workflows that demand strict adherence to Standard Operating Procedures (SOPs), a critical requirement for real-world industrial automation. Despite this need, there is a lack of public benchmarks that reflect the complexity, structure, and domain-specific nuances of SOPs. To address this, we present three main contributions. First, we introduce a synthetic data generation framework to create realistic, industry-grade SOPs that rigorously test the planning, reasoning, and tool-use capabilities of LLM-based agents. Second, using this framework, we develop SOP-Bench, a benchmark of over 1,800 tasks across 10 industrial domains, each with APIs, tool interfaces, and human-validated test cases. Third, we evaluate two prominent agent architectures: Function-Calling and ReAct Agents, on SOP-Bench, observing average success rates of only 27% and 48%, respectively. Remarkably, when the tool registry is much larger than necessary, agents invoke incorrect tools nearly 100% of the time. These findings underscore a substantial gap between current agentic capabilities of LLMs and the demands of automating real-world SOPs. Performance varies significantly by task and domain, highlighting the need for domain-specific benchmarking and architectural choices before deployment. SOP-Bench is publicly available at http://sop-bench.s3-website-us-west-2.amazonaws.com/. We also release the prompts underpinning the data generation framework to support new domain-specific SOP benchmarks. We invite the community to extend SOP-Bench with SOPs from their industrial domains.
The emergence of capable large language model (LLM) based agents necessitates memory architectures that transcend mere data storage, enabling continuous learning, nuanced reasoning, and dynamic adaptation. Current memory systems often grapple with fundamental limitations in structural flexibility, temporal awareness, and the ability to synthesize higher-level insights from raw interaction data. This paper introduces Cognitive Weave, a novel memory framework centered around a multi-layered spatio-temporal resonance graph (STRG). This graph manages information as semantically rich insight particles (IPs), which are dynamically enriched with resonance keys, signifiers, and situational imprints via a dedicated semantic oracle interface (SOI). These IPs are interconnected through typed relational strands, forming an evolving knowledge tapestry. A key component of Cognitive Weave is the cognitive refinement process, an autonomous mechanism that includes the synthesis of insight aggregates (IAs) condensed, higher-level knowledge structures derived from identified clusters of related IPs. We present comprehensive experimental results demonstrating Cognitive Weave's marked enhancement over existing approaches in long-horizon planning tasks, evolving question-answering scenarios, and multi-session dialogue coherence. The system achieves a notable 34% average improvement in task completion rates and a 42% reduction in mean query latency when compared to state-of-the-art baselines. Furthermore, this paper explores the ethical considerations inherent in such advanced memory systems, discusses the implications for long-term memory in LLMs, and outlines promising future research trajectories.
The construction industry is characterized by both high physical and psychological risks, yet supports of mental health remain limited. While advancements in artificial intelligence (AI), particularly large language models (LLMs), offer promising solutions, their potential in construction remains largely underexplored. To bridge this gap, we developed a conversational multi-agent system that addresses industry-specific challenges through an AI-driven approach integrated with domain knowledge. In parallel, it fulfills construction workers' basic psychological needs by enabling interactions with multiple agents, each has a distinct persona. This approach ensures that workers receive both practical problem-solving support and social engagement, ultimately contributing to their overall well-being. We evaluate its usability and effectiveness through a within-subjects user study with 12 participants. The results show that our system significantly outperforms the single-agent baseline, achieving improvements of 18% in usability, 40% in self-determination, 60% in social presence, and 60% in trust. These findings highlight the promise of LLM-driven AI systems in providing domain-specific support for construction workers.
While Large Language Models (LLMs) have demonstrated significant advancements in reasoning and agent-based problem-solving, current evaluation methodologies fail to adequately assess their capabilities: existing benchmarks either rely on closed-ended questions prone to saturation and memorization, or subjective comparisons that lack consistency and rigor. In this work, we introduce HeuriGym, an agentic framework designed for evaluating heuristic algorithms generated by LLMs for combinatorial optimization problems, characterized by clearly defined objectives and expansive solution spaces. HeuriGym empowers LLMs to propose heuristics, receive evaluative feedback via code execution, and iteratively refine their solutions. We evaluate nine state-of-the-art models on nine problems across domains such as computer systems, logistics, and biology, exposing persistent limitations in tool use, planning, and adaptive reasoning. To quantify performance, we propose the Quality-Yield Index (QYI), a metric that captures both solution pass rate and quality. Even top models like GPT-o4-mini-high and Gemini-2.5-Pro attain QYI scores of only 0.6, well below the expert baseline of 1. Our open-source benchmark aims to guide the development of LLMs toward more effective and realistic problem-solving in scientific and engineering domains.
In dynamic environments, the rapid obsolescence of pre-existing environmental knowledge creates a gap between an agent's internal model and the evolving reality of its operational context. This disparity between prior and updated environmental valuations fundamentally limits the effectiveness of autonomous decision-making. To bridge this gap, the contextual bias of human domain stakeholders, who naturally accumulate insights through direct, real-time observation, becomes indispensable. However, translating their nuanced, and context-rich input into actionable intelligence for autonomous systems remains an open challenge. To address this, we propose LUCIFER (Language Understanding and Context-Infused Framework for Exploration and Behavior Refinement), a domain-agnostic framework that integrates a hierarchical decision-making architecture with reinforcement learning (RL) and large language models (LLMs) into a unified system. This architecture mirrors how humans decompose complex tasks, enabling a high-level planner to coordinate specialised sub-agents, each focused on distinct objectives and temporally interdependent actions. Unlike traditional applications where LLMs are limited to single role, LUCIFER integrates them in two synergistic roles: as context extractors, structuring verbal stakeholder input into domain-aware representations that influence decision-making through an attention space mechanism aligning LLM-derived insights with the agent's learning process, and as zero-shot exploration facilitators guiding the agent's action selection process during exploration. We benchmark various LLMs in both roles and demonstrate that LUCIFER improves exploration efficiency and decision quality, outperforming flat, goal-conditioned policies. Our findings show the potential of context-driven decision-making, where autonomous systems leverage human contextual knowledge for operational success.
Query rewrite transforms SQL queries into semantically equivalent forms that run more efficiently. Existing approaches mainly rely on predefined rewrite rules, but they handle a limited subset of queries and can cause performance regressions. This limitation stems from three challenges of rule-based query rewrite: (1) it is hard to discover and verify new rules, (2) fixed rewrite rules do not generalize to new query patterns, and (3) some rewrite techniques cannot be expressed as fixed rules. Motivated by the fact that human experts exhibit significantly better rewrite ability but suffer from scalability, and Large Language Models (LLMs) have demonstrated nearly human-level semantic and reasoning abilities, we propose a new approach of using LLMs to rewrite SQL queries beyond rules. Due to the hallucination problems in LLMs, directly applying LLMs often leads to nonequivalent and suboptimal queries. To address this issue, we propose QUITE (query rewrite), a training-free and feedback-aware system based on LLM agents that rewrites SQL queries into semantically equivalent forms with significantly better performance, covering a broader range of query patterns and rewrite strategies compared to rule-based methods. Firstly, we design a multi-agent framework controlled by a finite state machine (FSM) to equip LLMs with the ability to use external tools and enhance the rewrite process with real-time database feedback. Secondly, we develop a rewrite middleware to enhance the ability of LLMs to generate optimized query equivalents. Finally, we employ a novel hint injection technique to improve execution plans for rewritten queries. Extensive experiments show that QUITE reduces query execution time by up to 35.8% over state-of-the-art approaches and produces 24.1% more rewrites than prior methods, covering query cases that earlier systems did not handle.
(M)LLM-powered computer use agents (CUA) are emerging as a transformative technique to automate human-computer interaction. However, existing CUA benchmarks predominantly target GUI agents, whose evaluation methods are susceptible to UI changes and ignore function interactions exposed by application APIs, e.g., Model Context Protocol (MCP). To this end, we propose MCPWorld, the first automatic CUA testbed for API, GUI, and API-GUI hybrid agents. A key principle of MCPWorld is the use of "white-box apps", i.e., those with source code availability and can be revised/re-compiled as needed (e.g., adding MCP support), with two notable advantages: (1) It greatly broadens the design space of CUA, such as what and how the app features to be exposed/extracted as CUA-callable APIs. (2) It allows MCPWorld to programmatically verify task completion by directly monitoring application behavior through techniques like dynamic code instrumentation, offering robust, accurate CUA evaluation decoupled from specific agent implementations or UI states. Currently, MCPWorld includes 201 well curated and annotated user tasks, covering diversified use cases and difficulty levels. MCPWorld is also fully containerized with GPU acceleration support for flexible adoption on different OS/hardware environments. Our preliminary experiments, using a representative LLM-powered CUA framework, achieve 75.12% task completion accuracy, simultaneously providing initial evidence on the practical effectiveness of agent automation leveraging MCP. Overall, we anticipate MCPWorld to facilitate and standardize the benchmarking of next-generation computer use agents that can leverage rich external tools. Our code and dataset are publicly available at https://github.com/SAAgent/MCPWorld.
Large language models (LLMs) have advanced rapidly from conversational problem solving to addressing real-world tasks involving tool use, such as software engineering (SWE). Recent LLM-powered toolkits, such as OpenAI Codex and Cursor, have offered end-to-end automation of the software development process. However, building effective SWE agents remains challenging due to the lack of high-quality training data and effective test cases. To address this issue, we present SWE-Dev, an SWE agent built upon open-source LLMs. First, we develop a robust pipeline to synthesize test cases for patch evaluation. Second, we scale up agent trajectories to construct the training data for building SWE-Dev. Experiments on the SWE-bench-Verified benchmark show that the SWE-Dev models can achieve top performance among all open SWE agents. Specifically, the success rates of the SWE-Dev 7B and 32B parameter models reach 23.4% and 36.6%, respectively, outperforming state-of-the-art open-source models. All code, models, and datasets are publicly available at https://github.com/THUDM/SWE-Dev.
The dual use nature of Large Language Models (LLMs) presents a growing challenge in cybersecurity. While LLM enhances automation and reasoning for defenders, they also introduce new risks, particularly their potential to be misused for generating evasive, AI crafted malware. Despite this emerging threat, the research community currently lacks controlled and extensible tools that can simulate such behavior for testing and defense preparation. We present MalGEN, a multi agent framework that simulates coordinated adversarial behavior to generate diverse, activity driven malware samples. The agents work collaboratively to emulate attacker workflows, including payload planning, capability selection, and evasion strategies, within a controlled environment built for ethical and defensive research. Using MalGEN, we synthesized ten novel malware samples and evaluated them against leading antivirus and behavioral detection engines. Several samples exhibited stealthy and evasive characteristics that bypassed current defenses, validating MalGEN's ability to model sophisticated and new threats. By transforming the threat of LLM misuse into an opportunity for proactive defense, MalGEN offers a valuable framework for evaluating and strengthening cybersecurity systems. The framework addresses data scarcity, enables rigorous testing, and supports the development of resilient and future ready detection strategies.
Despite the popularity of the large language models (LLMs), their application to machine translation is relatively underexplored, especially in context-aware settings. This work presents a literature review of context-aware translation with LLMs. The existing works utilise prompting and fine-tuning approaches, with few focusing on automatic post-editing and creating translation agents for context-aware machine translation. We observed that the commercial LLMs (such as ChatGPT and Tower LLM) achieved better results than the open-source LLMs (such as Llama and Bloom LLMs), and prompt-based approaches serve as good baselines to assess the quality of translations. Finally, we present some interesting future directions to explore.
Recent advances in large language models (LLMs) and vision-language models (VLMs) have enabled powerful autonomous agents capable of complex reasoning and multi-modal tool use. Despite their growing capabilities, today's agent frameworks remain fragile, lacking principled mechanisms for secure information flow, reliability, and multi-agent coordination. In this work, we introduce SAFEFLOW, a new protocol-level framework for building trustworthy LLM/VLM-based agents. SAFEFLOW enforces fine-grained information flow control (IFC), precisely tracking provenance, integrity, and confidentiality of all the data exchanged between agents, tools, users, and environments. By constraining LLM reasoning to respect these security labels, SAFEFLOW prevents untrusted or adversarial inputs from contaminating high-integrity decisions. To ensure robustness in concurrent multi-agent settings, SAFEFLOW introduces transactional execution, conflict resolution, and secure scheduling over shared state, preserving global consistency across agents. We further introduce mechanisms, including write-ahead logging, rollback, and secure caches, that further enhance resilience against runtime errors and policy violations. To validate the performances, we built SAFEFLOWBENCH, a comprehensive benchmark suite designed to evaluate agent reliability under adversarial, noisy, and concurrent operational conditions. Extensive experiments demonstrate that agents built with SAFEFLOW maintain impressive task performance and security guarantees even in hostile environments, substantially outperforming state-of-the-art. Together, SAFEFLOW and SAFEFLOWBENCH lay the groundwork for principled, robust, and secure agent ecosystems, advancing the frontier of reliable autonomy.
Large language models (LLMs) have recently demonstrated promising capabilities in chemistry tasks while still facing challenges due to outdated pretraining knowledge and the difficulty of incorporating specialized chemical expertise. To address these issues, we propose an LLM-based agent that synergistically integrates 137 external chemical tools created ranging from basic information retrieval to complex reaction predictions, and a dataset curation pipeline to generate the dataset ChemToolBench that facilitates both effective tool selection and precise parameter filling during fine-tuning and evaluation. We introduce a Hierarchical Evolutionary Monte Carlo Tree Search (HE-MCTS) framework, enabling independent optimization of tool planning and execution. By leveraging self-generated data, our approach supports step-level fine-tuning (FT) of the policy model and training task-adaptive PRM and ORM that surpass GPT-4o. Experimental evaluations demonstrate that our approach significantly improves performance in Chemistry QA and discovery tasks, offering a robust solution to integrate specialized tools with LLMs for advanced chemical applications. All datasets and code are available at https://github.com/AI4Chem/ChemistryAgent .