Cooperative multi-agent planning requires agents to make joint decisions with partial information and limited communication. Coordination at the trajectory level often fails, as small deviations in timing or movement cascade into conflicts. Symbolic planning mitigates this challenge by raising the level of abstraction and providing a minimal vocabulary of actions that enable synchronization and collective progress. We present DR. WELL, a decentralized neurosymbolic framework for cooperative multi-agent planning. Cooperation unfolds through a two-phase negotiation protocol: agents first propose candidate roles with reasoning and then commit to a joint allocation under consensus and environment constraints. After commitment, each agent independently generates and executes a symbolic plan for its role without revealing detailed trajectories. Plans are grounded in execution outcomes via a shared world model that encodes the current state and is updated as agents act. By reasoning over symbolic plans rather than raw trajectories, DR. WELL avoids brittle step-level alignment and enables higher-level operations that are reusable, synchronizable, and interpretable. Experiments on cooperative block-push tasks show that agents adapt across episodes, with the dynamic world model capturing reusable patterns and improving task completion rates and efficiency. Experiments on cooperative block-push tasks show that our dynamic world model improves task completion and efficiency through negotiation and self-refinement, trading a time overhead for evolving, more efficient collaboration strategies.
Text-to-SQL systems provide a natural language interface that can enable even laymen to access information stored in databases. However, existing Large Language Models (LLM) struggle with SQL generation from natural instructions due to large schema sizes and complex reasoning. Prior work often focuses on complex, somewhat impractical pipelines using flagship models, while smaller, efficient models remain overlooked. In this work, we explore three multi-agent LLM pipelines, with systematic performance benchmarking across a range of small to large open-source models: (1) Multi-agent discussion pipeline, where agents iteratively critique and refine SQL queries, and a judge synthesizes the final answer; (2) Planner-Coder pipeline, where a thinking model planner generates stepwise SQL generation plans and a coder synthesizes queries; and (3) Coder-Aggregator pipeline, where multiple coders independently generate SQL queries, and a reasoning agent selects the best query. Experiments on the Bird-Bench Mini-Dev set reveal that Multi-Agent discussion can improve small model performance, with up to 10.6% increase in Execution Accuracy for Qwen2.5-7b-Instruct seen after three rounds of discussion. Among the pipelines, the LLM Reasoner-Coder pipeline yields the best results, with DeepSeek-R1-32B and QwQ-32B planners boosting Gemma 3 27B IT accuracy from 52.4% to the highest score of 56.4%. Codes are available at https://github.com/treeDweller98/bappa-sql.
Redistricting plays a central role in shaping how votes are translated into political power. While existing computational methods primarily aim to generate large ensembles of legally valid districting plans, they often neglect the strategic dynamics involved in the selection process. This oversight creates opportunities for partisan actors to cherry-pick maps that, while technically compliant, are politically advantageous. Simply satisfying formal constraints does not ensure fairness when the selection process itself can be manipulated. We propose \textbf{Agentmandering}, a framework that reimagines redistricting as a turn-based negotiation between two agents representing opposing political interests. Drawing inspiration from game-theoretic ideas, particularly the \textit{Choose-and-Freeze} protocol, our method embeds strategic interaction into the redistricting process via large language model (LLM) agents. Agents alternate between selecting and freezing districts from a small set of candidate maps, gradually partitioning the state through constrained and interpretable choices. Evaluation on post-2020 U.S. Census data across all states shows that Agentmandering significantly reduces partisan bias and unfairness, while achieving 2 to 3 orders of magnitude lower variance than standard baselines. These results demonstrate both fairness and stability, especially in swing-state scenarios. Our code is available at https://github.com/Lihaogx/AgentMandering.
Temporal Knowledge Graph Question Answering (TKGQA) aims to answer time-sensitive questions by leveraging factual information from Temporal Knowledge Graphs (TKGs). While previous studies have employed pre-trained TKG embeddings or graph neural networks to inject temporal knowledge, they fail to fully understand the complex semantic information of time constraints. Recently, Large Language Models (LLMs) have shown remarkable progress, benefiting from their strong semantic understanding and reasoning generalization capabilities. However, their temporal reasoning ability remains limited. LLMs frequently suffer from hallucination and a lack of knowledge. To address these limitations, we propose the Plan of Knowledge framework with a contrastive temporal retriever, which is named PoK. Specifically, the proposed Plan of Knowledge module decomposes a complex temporal question into a sequence of sub-objectives from the pre-defined tools, serving as intermediate guidance for reasoning exploration. In parallel, we construct a Temporal Knowledge Store (TKS) with a contrastive retrieval framework, enabling the model to selectively retrieve semantically and temporally aligned facts from TKGs. By combining structured planning with temporal knowledge retrieval, PoK effectively enhances the interpretability and factual consistency of temporal reasoning. Extensive experiments on four benchmark TKGQA datasets demonstrate that PoK significantly improves the retrieval precision and reasoning accuracy of LLMs, surpassing the performance of the state-of-the-art TKGQA methods by 56.0% at most.
The development of LLM-based autonomous agents for end-to-end software development represents a significant paradigm shift in software engineering. However, the scientific evaluation of these systems is hampered by significant challenges, including overly simplistic benchmarks and the difficulty of conducting fair comparisons between different agent architectures due to confounding implementation variables. To address these limitations, we first construct a challenging and dynamically curated E2EDevBench to simulate realistic development scenarios. Second, we propose a hybrid evaluation framework that combines test-case-based functional assessment with fine-grained, LLM-based requirement verification. Using this framework, we conduct a controlled empirical study on three representative agent architectures implemented upon a unified foundation to isolate the impact of workflow design. Our findings reveal that state-of-the-art agents can fulfill approximately 50\% of requirements on \bench{}, but their success is critically dependent on the architectural strategy for task decomposition and collaboration. Furthermore, our analysis indicates that the primary bottleneck is the omission of requirements and inadequate self-verification. This work provides the community with a more realistic benchmark, a comprehensive evaluation framework, and crucial insights into the current capabilities and core challenges of software development agents, guiding future research toward enhancing requirement comprehension and planning.
Large-scale disaster Search And Rescue (SAR) operations are persistently challenged by complex terrain and disrupted communications. While Unmanned Aerial Vehicle (UAV) swarms offer a promising solution for tasks like wide-area search and supply delivery, yet their effective coordination places a significant cognitive burden on human operators. The core human-machine collaboration bottleneck lies in the ``intention-to-action gap'', which is an error-prone process of translating a high-level rescue objective into a low-level swarm command under high intensity and pressure. To bridge this gap, this study proposes a novel LLM-CRF system that leverages Large Language Models (LLMs) to model and augment human-swarm teaming cognition. The proposed framework initially captures the operator's intention through natural and multi-modal interactions with the device via voice or graphical annotations. It then employs the LLM as a cognitive engine to perform intention comprehension, hierarchical task decomposition, and mission planning for the UAV swarm. This closed-loop framework enables the swarm to act as a proactive partner, providing active feedback in real-time while reducing the need for manual monitoring and control, which considerably advances the efficacy of the SAR task. We evaluate the proposed framework in a simulated SAR scenario. Experimental results demonstrate that, compared to traditional order and command-based interfaces, the proposed LLM-driven approach reduced task completion time by approximately $64.2\%$ and improved task success rate by $7\%$. It also leads to a considerable reduction in subjective cognitive workload, with NASA-TLX scores dropping by $42.9\%$. This work establishes the potential of LLMs to create more intuitive and effective human-swarm collaborations in high-stakes scenarios.
Large Language Models (LLMs) have been widely deployed across various applications, yet their potential security and ethical risks have raised increasing concerns. Existing research employs red teaming evaluations, utilizing multi-turn jailbreaks to identify potential vulnerabilities in LLMs. However, these approaches often lack exploration of successful dialogue trajectories within the attack space, and they tend to overlook the considerable overhead associated with the attack process. To address these limitations, this paper first introduces a theoretical model based on dynamically weighted graph topology, abstracting the multi-turn attack process as a path planning problem. Based on this framework, we propose ABC, an enhanced Artificial Bee Colony algorithm for multi-turn jailbreaks, featuring a collaborative search mechanism with employed, onlooker, and scout bees. This algorithm significantly improves the efficiency of optimal attack path search while substantially reducing the average number of queries required. Empirical evaluations on three open-source and two proprietary language models demonstrate the effectiveness of our approach, achieving attack success rates above 90\% across the board, with a peak of 98\% on GPT-3.5-Turbo, and outperforming existing baselines. Furthermore, it achieves comparable success with only 26 queries on average, significantly reducing red teaming overhead and highlighting its superior efficiency.
Large Language Models (LLMs) have substantially influenced various software engineering tasks. Indeed, in the case of software refactoring, traditional LLMs have shown the ability to reduce development time and enhance code quality. However, these LLMs often rely on static, detailed instructions for specific tasks. In contrast, LLM-based agents can dynamically adapt to evolving contexts and autonomously make decisions by interacting with software tools and executing workflows. In this paper, we explore the potential of LLM-based agents in supporting refactoring activities. Specifically, we introduce RefAgent, a multi-agent LLM-based framework for end-to-end software refactoring. RefAgent consists of specialized agents responsible for planning, executing, testing, and iteratively refining refactorings using self-reflection and tool-calling capabilities. We evaluate RefAgent on eight open-source Java projects, comparing its effectiveness against a single-agent approach, a search-based refactoring tool, and historical developer refactorings. Our assessment focuses on: (1) the impact of generated refactorings on software quality, (2) the ability to identify refactoring opportunities, and (3) the contribution of each LLM agent through an ablation study. Our results show that RefAgent achieves a median unit test pass rate of 90%, reduces code smells by a median of 52.5%, and improves key quality attributes (e.g., reusability) by a median of 8.6%. Additionally, it closely aligns with developer refactorings and the search-based tool in identifying refactoring opportunities, attaining a median F1-score of 79.15% and 72.7%, respectively. Compared to single-agent approaches, RefAgent improves the median unit test pass rate by 64.7% and the median compilation success rate by 40.1%. These findings highlight the promise of multi-agent architectures in advancing automated software refactoring.
Large language models enable flexible multi-agent planning but remain fragile in practice: verification is often circular, state changes are not tracked for repair, and small faults trigger costly global recomputation. We present ALAS, a stateful, disruption-aware framework that separates planning from non-circular validation, records a versioned execution log for grounded checks and restore points, and performs localized repair that preserves work in progress. The validator operates independently of the planning LLM with fresh, bounded context, avoiding self-check loops and mid-context attrition. The repair protocol edits only the minimal affected region under explicit policies (retry, catch, timeout, backoff, idempotency keys, compensation, loop guards) defined in a canonical workflow IR that maps to Amazon States Language and Argo Workflows. On job-shop scheduling suites (DMU, TA) across five classical benchmarks, ALAS matches or exceeds strong single-LLM and multi-agent baselines, achieving 83.7% success, reducing token usage by 60%, and running 1.82times faster under comparable settings. A minimal reliability study shows that the validator detects injected structural faults with low overhead, and that localized repair contains runtime perturbations with a bounded edit radius and less makespan degradation than global recompute. Results indicate that the combination of validator isolation, versioned execution logs, and localized repair provides measurable efficiency, feasibility, and scalability for multi-agent LLM planning. Code and seeds will be released.
Current evaluations of Large Language Model (LLM) agents primarily emphasize task completion, often overlooking resource efficiency and adaptability. This neglects a crucial capability: agents' ability to devise and adjust cost-optimal plans in response to changing environments. To bridge this gap, we introduce CostBench, a scalable, cost-centric benchmark designed to evaluate agents' economic reasoning and replanning abilities. Situated in the travel-planning domain, CostBench comprises tasks solvable via multiple sequences of atomic and composite tools with diverse, customizable costs. It also supports four types of dynamic blocking events, such as tool failures and cost changes, to simulate real-world unpredictability and necessitate agents to adapt in real time. Evaluating leading open-sourced and proprietary models on CostBench reveals a substantial gap in cost-aware planning: agents frequently fail to identify cost-optimal solutions in static settings, with even GPT-5 achieving less than 75% exact match rate on the hardest tasks, and performance further dropping by around 40% under dynamic conditions. By diagnosing these weaknesses, CostBench lays the groundwork for developing future agents that are both economically rational and robust.
Recent advancements in large language models (LLMs) have enabled significant progress in decision-making and task planning for embodied autonomous agents. However, most existing methods still struggle with complex, long-horizon tasks because they rely on a monolithic trajectory that entangles all past decisions and observations, attempting to solve the entire task in a single unified process. To address this limitation, we propose ReAcTree, a hierarchical task-planning method that decomposes a complex goal into more manageable subgoals within a dynamically constructed agent tree. Each subgoal is handled by an LLM agent node capable of reasoning, acting, and further expanding the tree, while control flow nodes coordinate the execution strategies of agent nodes. In addition, we integrate two complementary memory systems: each agent node retrieves goal-specific, subgoal-level examples from episodic memory and shares environment-specific observations through working memory. Experiments on the WAH-NL and ALFRED datasets demonstrate that ReAcTree consistently outperforms strong task-planning baselines such as ReAct across diverse LLMs. Notably, on WAH-NL, ReAcTree achieves a 61% goal success rate with Qwen 2.5 72B, nearly doubling ReAct's 31%.
In this work, we propose LiveSecBench, a dynamic and continuously updated safety benchmark specifically for Chinese-language LLM application scenarios. LiveSecBench evaluates models across six critical dimensions (Legality, Ethics, Factuality, Privacy, Adversarial Robustness, and Reasoning Safety) rooted in the Chinese legal and social frameworks. This benchmark maintains relevance through a dynamic update schedule that incorporates new threat vectors, such as the planned inclusion of Text-to-Image Generation Safety and Agentic Safety in the next update. For now, LiveSecBench (v251030) has evaluated 18 LLMs, providing a landscape of AI safety in the context of Chinese language. The leaderboard is publicly accessible at https://livesecbench.intokentech.cn/.
Large Language Models (LLMs) trained with reinforcement learning and verifiable rewards have achieved strong results on complex reasoning tasks. Recent work extends this paradigm to a multi-agent setting, where a meta-thinking agent proposes plans and monitors progress while a reasoning agent executes subtasks through sequential conversational turns. Despite promising performance, we identify a critical limitation: lazy agent behavior, in which one agent dominates while the other contributes little, undermining collaboration and collapsing the setup to an ineffective single agent. In this paper, we first provide a theoretical analysis showing why lazy behavior naturally arises in multi-agent reasoning. We then introduce a stable and efficient method for measuring causal influence, helping mitigate this issue. Finally, as collaboration intensifies, the reasoning agent risks getting lost in multi-turn interactions and trapped by previous noisy responses. To counter this, we propose a verifiable reward mechanism that encourages deliberation by allowing the reasoning agent to discard noisy outputs, consolidate instructions, and restart its reasoning process when necessary. Extensive experiments demonstrate that our framework alleviates lazy agent behavior and unlocks the full potential of multi-agent framework for complex reasoning tasks.
Background: Modern large language models (LLMs) offer powerful reasoning that converts narratives into structured, taxonomy-aligned data, revealing patterns across planning, delivery, and verification. Embedded as agentic tools, LLMs can assist root-cause analysis and risk assessment (e.g., failure mode and effect analysis FMEA), produce auditable rationales, and draft targeted mitigation actions. Methods: We developed a data-driven pipeline utilizing an LLM to perform automated root cause analysis on 254 institutional safety incidents. The LLM systematically classified each incident into structured taxonomies for radiotherapy pathway steps and contributory factors. Subsequent quantitative analyses included descriptive statistics, Analysis of Variance (ANOVA), multiple Ordinal Logistic Regression (OLR) analyses to identify predictors of event severity, and Association Rule Mining (ARM) to uncover systemic vulnerabilities. Results: The high-level Ordinal Logistic Regression (OLR) models identified specific, significant drivers of severity. The Pathway model was statistically significant (Pseudo R2 = 0.033, LR p = 0.015), as was the Responsibility model (Pseudo R2 = 0.028, LR p < 0.001). Association Rule Mining (ARM) identified high-confidence systemic rules, such as "CF5 Teamwork, management and organisational" (n = 8, Conf = 1.0) and the high-frequency link between "(11) Pre-treatment planning process" and "CF2 Procedural" (n = 152, Conf = 0.916). Conclusion: The LLM-powered, data-driven framework provides a more objective and powerful methodology for risk assessment than traditional approaches. Our findings empirically demonstrate that interventions focused on fortifying high-risk process steps and mitigating systemic failures are most effective for improving patient safety.
Length control in Large Language Models (LLMs) is a crucial but under-addressed challenge, with applications ranging from voice interfaces requiring concise responses to research summaries needing comprehensive outputs. Current approaches to length control, including Regularized DPO, Length-Instruction Fine Tuning, and tool-augmented methods, typically require expensive model retraining or complex inference-time tooling. This paper presents a prompt engineering methodology that enables precise length control without model retraining. Our structure-guided approach implements deliberate planning and word counting mechanisms within the prompt, encouraging the model to carefully track and adhere to specified length constraints. Comprehensive evaluations across six state-of-the-art LLMs demonstrate that our method significantly improves length fidelity for several models compared to standard prompting when applied to document summarization tasks, particularly for shorter-to-medium length constraints. The proposed technique shows varying benefits across different model architectures, with some models demonstrating up to 37.6% improvement in length adherence. Quality evaluations further reveal that our approach maintains or enhances overall output quality compared to standard prompting techniques. Our approach provides an immediately deployable solution for applications requiring precise length control, particularly valuable for production environments where model retraining is impractical or cost-prohibitive.
Large language model (LLM) agents have exhibited strong problem-solving competence across domains like research and coding. Yet, it remains underexplored whether LLM agents can tackle compounding real-world problems that require a diverse set of tools to complete. Given a broad, heterogeneous tool repository, LLM agents must not only select appropriate tools based on task planning analysis but also strategically schedule the execution order to ensure efficiency. This paper introduces TPS-Bench to benchmark the ability of LLM agents in solving such problems that demand Tool Planning and Scheduling. TPS-Bench collects 200 compounding tasks of two difficulty levels, based on a tool repository containing hundreds of model context protocol (MCP) tools. In particular, each task is composed of multiple subtasks, such as web search, map navigation, calendar checking, etc., and each subtask can be completed by a basic tool. Our evaluation emphasizes both task completion rate and efficiency. The empirical studies on popular closed-source and open-source LLMs indicate that most models can perform reasonable tool planning, but differ in scheduling. For example, GLM-4.5 achieves an outperforming task completion rate of 64.72% with extensive sequential tool calls, hence suffering from significantly long execution time. By contrast, GPT-4o prioritizes parallel tool calls but achieves only a 45.08% completion rate. Considering reinforcement learning (RL) can be a viable way to improve the scheduling efficiency without compromising performance, we perform an initial study on Qwen3-1.7B and witness a 14% reduction in execution time alongside a 6% gain in task completion rate based on rarely 100 RL training samples. Our code is available https://github.com/hanwenxu1/mcp-agent.
Endowed with inherent dynamical properties that grant them remarkable ruggedness and adaptability, spherical tensegrity robots stand as prototypical examples of hybrid softrigid designs and excellent mobile platforms. However, path planning for these robots in unknown environments presents a significant challenge, requiring a delicate balance between efficient exploration and robust planning. Traditional path planners, which treat the environment as a geometric grid, often suffer from redundant searches and are prone to failure in complex scenarios due to their lack of semantic understanding. To overcome these limitations, we reframe path planning in unknown environments as a semantic reasoning task. We introduce a Semantic Agent for Tensegrity robots (SATPlanner) driven by a Large Language Model (LLM). SATPlanner leverages high-level environmental comprehension to generate efficient and reliable planning strategies.At the core of SATPlanner is an Adaptive Observation Window mechanism, inspired by the "fast" and "slow" thinking paradigms of LLMs. This mechanism dynamically adjusts the perceptual field of the agent: it narrows for rapid traversal of open spaces and expands to reason about complex obstacle configurations. This allows the agent to construct a semantic belief of the environment, enabling the search space to grow only linearly with the path length (O(L)) while maintaining path quality. We extensively evaluate SATPlanner in 1,000 simulation trials, where it achieves a 100% success rate, outperforming other real-time planning algorithms. Critically, SATPlanner reduces the search space by 37.2% compared to the A* algorithm while achieving comparable, near-optimal path lengths. Finally, the practical feasibility of SATPlanner is validated on a physical spherical tensegrity robot prototype.
Cancer staging is critical for patient prognosis and treatment planning, yet extracting pathologic TNM staging from unstructured pathology reports poses a persistent challenge. Existing natural language processing (NLP) and machine learning (ML) strategies often depend on large annotated datasets, limiting their scalability and adaptability. In this study, we introduce two Knowledge Elicitation methods designed to overcome these limitations by enabling large language models (LLMs) to induce and apply domain-specific rules for cancer staging. The first, Knowledge Elicitation with Long-Term Memory (KEwLTM), uses an iterative prompting strategy to derive staging rules directly from unannotated pathology reports, without requiring ground-truth labels. The second, Knowledge Elicitation with Retrieval-Augmented Generation (KEwRAG), employs a variation of RAG where rules are pre-extracted from relevant guidelines in a single step and then applied, enhancing interpretability and avoiding repeated retrieval overhead. We leverage the ability of LLMs to apply broad knowledge learned during pre-training to new tasks. Using breast cancer pathology reports from the TCGA dataset, we evaluate their performance in identifying T and N stages, comparing them against various baseline approaches on two open-source LLMs. Our results indicate that KEwLTM outperforms KEwRAG when Zero-Shot Chain-of-Thought (ZSCOT) inference is effective, whereas KEwRAG achieves better performance when ZSCOT inference is less effective. Both methods offer transparent, interpretable interfaces by making the induced rules explicit. These findings highlight the promise of our Knowledge Elicitation methods as scalable, high-performing solutions for automated cancer staging with enhanced interpretability, particularly in clinical settings with limited annotated data.
Effective modeling of how human travelers learn and adjust their travel behavior from interacting with transportation systems is critical for system assessment and planning. However, this task is also difficult due to the complex cognition and decision-making involved in such behavior. Recent research has begun to leverage Large Language Model (LLM) agents for this task. Building on this, we introduce a novel dual-agent framework that enables continuous learning and alignment between LLM agents and human travelers on learning and adaptation behavior from online data streams. Our approach involves a set of LLM traveler agents, equipped with a memory system and a learnable persona, which serve as simulators for human travelers. To ensure behavioral alignment, we introduce an LLM calibration agent that leverages the reasoning and analytical capabilities of LLMs to train the personas of these traveler agents. Working together, this dual-agent system is designed to track and align the underlying decision-making mechanisms of travelers and produce realistic, adaptive simulations. Using a real-world dataset from a day-to-day route choice experiment, we show our approach significantly outperforms existing LLM-based methods in both individual behavioral alignment and aggregate simulation accuracy. Furthermore, we demonstrate that our method moves beyond simple behavioral mimicry to capture the evolution of underlying learning processes, a deeper alignment that fosters robust generalization. Overall, our framework provides a new approach for creating adaptive and behaviorally realistic agents to simulate travelers' learning and adaptation that can benefit transportation simulation and policy analysis.
Patient-generated health data (PGHD) allows healthcare professionals to have a holistic and objective view of their patients. However, its integration in cardiac risk reduction remains unexplored. Through co-design with experienced healthcare professionals (n=5) in cardiac rehabilitation, we designed a dashboard, INSIGHT (INvestigating the potentialS of PatIent Generated Health data for CVD Prevention and ReHabiliTation), integrating multi-modal PGHD to support healthcare professionals in physical activity planning in cardiac risk reduction. To further augment healthcare professionals' (HCPs') data sensemaking and exploration capabilities, we integrate large language models (LLMs) for generating summaries and insights and for using natural language interaction to perform personalized data analysis. The aim of this integration is to explore the potential of AI in augmenting HCPs' data sensemaking and analysis capabilities.
The rapid appearance of large language models (LLMs) has led to systems that turn natural-language intent into real user interfaces (UIs). Free-form code generation maximizes expressiveness but often hurts reliability, security, and design-system compliance. In contrast, fully static UIs are easy to govern but lack adaptability. We present the Portal UX Agent, a practical middle way that makes bounded generation work: an LLM plans the UI at a high level, and a deterministic renderer assembles the final interface from a vetted set of components and layout templates. The agent maps intents to a typed composition-template and component specifications-constrained by a schema. This enables auditability, reuse, and safety while preserving flexibility. We also introduce a mixed-methods evaluation framework that combines automatic checks (coverage, property fidelity, layout, accessibility, performance) with an LLM-as-a-Judge rubric to assess semantic alignment and visual polish. Experiments on multi-domain portal scenarios show that the Portal UX Agent reliably turns intent into coherent, usable UIs and performs well on compositionality and clarity. This work advances agentic UI design by combining model-driven representations, plug-and-play rendering, and structured evaluation, paving the way for controllable and trustworthy UI generation.
Agentic AI frameworks add a decision-making orchestrator embedded with external tools, including web search, Python interpreter, contextual database, and others, on top of monolithic LLMs, turning them from passive text oracles into autonomous problem-solvers that can plan, call tools, remember past steps, and adapt on the fly. This paper aims to characterize and understand the system bottlenecks introduced by agentic AI workloads from a largely overlooked CPU-centric perspective. We first systematically characterize Agentic AI on the basis of orchestrator/decision making component, inference path dynamics and repetitiveness of the agentic flow which directly influences the system-level performance. Thereafter, based on the characterization, we choose five representative agentic AI workloads- Haystack RAG, Toolformer, ChemCrow, Langchain and SWE-Agent to profile latency, throughput and energy metrics and demystify the significant impact of CPUs on these metrics relative to GPUs. We observe that - 1. Tool processing on CPUs can take up to 90.6% of the total latency; 2. Agentic throughput gets bottlenecked either by CPU factors - coherence, synchronization and over-subscription of cores or GPU factors - main memory capacity and bandwidth; \circled{3} CPU dynamic energy consumes up to 44% of the total dynamic energy at large batch sizes. Based on the profiling insights, we present two key optimizations- 1. CPU and GPU-Aware Micro-batching (CGAM) and 2. Mixed Agentic Workload Scheduling (MAWS) for homogeneous and heterogeneous agentic workloads respectively to demonstrate the potential to improve the performance, efficiency, and scalability of agentic AI. We achieve up to 2.1x and 1.41x P50 latency speedup compared to the multi-processing benchmark for homogeneous and heterogeneous agentic workloads respectively.
Telecom networks are rapidly growing in scale and complexity, making effective management, operation, and optimization increasingly challenging. Although Artificial Intelligence (AI) has been applied to many telecom tasks, existing models are often narrow in scope, require large amounts of labeled data, and struggle to generalize across heterogeneous deployments. Consequently, network troubleshooting continues to rely heavily on Subject Matter Experts (SMEs) to manually correlate various data sources to identify root causes and corrective actions. To address these limitations, we propose a Multi-Agent System (MAS) that employs an agentic workflow, with Large Language Models (LLMs) coordinating multiple specialized tools for fully automated network troubleshooting. Once faults are detected by AI/ML-based monitors, the framework dynamically activates agents such as an orchestrator, solution planner, executor, data retriever, and root-cause analyzer to diagnose issues and recommend remediation strategies within a short time frame. A key component of this system is the solution planner, which generates appropriate remediation plans based on internal documentation. To enable this, we fine-tuned a Small Language Model (SLM) on proprietary troubleshooting documents to produce domain-grounded solution plans. Experimental results demonstrate that the proposed framework significantly accelerates troubleshooting automation across both Radio Access Network (RAN) and Core network domains.
Planning has been a cornerstone of artificial intelligence for solving complex problems, and recent progress in LLM-based multi-agent frameworks have begun to extend this capability. However, the role of human-like memory within these frameworks remains largely unexplored. Understanding how agents coordinate through memory is critical for natural language planning, where iterative reasoning, constraint tracking, and error correction drive the success. Inspired by working memory model in cognitive psychology, we present EvoMem, a multi-agent framework built on a dual-evolving memory mechanism. The framework consists of three agents (Constraint Extractor, Verifier, and Actor) and two memory modules: Constraint Memory (CMem), which evolves across queries by storing task-specific rules and constraints while remains fixed within a query, and Query-feedback Memory (QMem), which evolves within a query by accumulating feedback across iterations for solution refinement. Both memory modules are reset at the end of each query session. Evaluations on trip planning, meeting planning, and calendar scheduling show consistent performance improvements, highlighting the effectiveness of EvoMem. This success underscores the importance of memory in enhancing multi-agent planning.
AI agents could accelerate scientific discovery by automating hypothesis formation, experiment design, coding, execution, and analysis, yet existing benchmarks probe narrow skills in simplified settings. To address this gap, we introduce InnovatorBench, a benchmark-platform pair for realistic, end-to-end assessment of agents performing Large Language Model (LLM) research. It comprises 20 tasks spanning Data Construction, Filtering, Augmentation, Loss Design, Reward Design, and Scaffold Construction, which require runnable artifacts and assessment of correctness, performance, output quality, and uncertainty. To support agent operation, we develop ResearchGym, a research environment offering rich action spaces, distributed and long-horizon execution, asynchronous monitoring, and snapshot saving. We also implement a lightweight ReAct agent that couples explicit reasoning with executable planning using frontier models such as Claude-4, GPT-5, GLM-4.5, and Kimi-K2. Our experiments demonstrate that while frontier models show promise in code-driven research tasks, they struggle with fragile algorithm-related tasks and long-horizon decision making, such as impatience, poor resource management, and overreliance on template-based reasoning. Furthermore, agents require over 11 hours to achieve their best performance on InnovatorBench, underscoring the benchmark's difficulty and showing the potential of InnovatorBench to be the next generation of code-based research benchmark.
Most work interpreting reasoning models studies only a single chain-of-thought (CoT), yet these models define distributions over many possible CoTs. We argue that studying a single sample is inadequate for understanding causal influence and the underlying computation. Though fully specifying this distribution is intractable, it can be understood by sampling. We present case studies using resampling to investigate model decisions. First, when a model states a reason for its action, does that reason actually cause the action? In "agentic misalignment" scenarios, we resample specific sentences to measure their downstream effects. Self-preservation sentences have small causal impact, suggesting they do not meaningfully drive blackmail. Second, are artificial edits to CoT sufficient for steering reasoning? These are common in literature, yet take the model off-policy. Resampling and selecting a completion with the desired property is a principled on-policy alternative. We find off-policy interventions yield small and unstable effects compared to resampling in decision-making tasks. Third, how do we understand the effect of removing a reasoning step when the model may repeat it post-edit? We introduce a resilience metric that repeatedly resamples to prevent similar content from reappearing downstream. Critical planning statements resist removal but have large effects when eliminated. Fourth, since CoT is sometimes "unfaithful", can our methods teach us anything in these settings? Adapting causal mediation analysis, we find that hints that have a causal effect on the output without being explicitly mentioned exert a subtle and cumulative influence on the CoT that persists even if the hint is removed. Overall, studying distributions via resampling enables reliable causal analysis, clearer narratives of model reasoning, and principled CoT interventions.
In the aftermath of COVID-19, many universities implemented supplementary "reinforcement" roles to support students in demanding courses. Although the name for such roles may differ between institutions, the underlying idea of providing structured supplementary support is common. However, these roles were often poorly defined, lacking structured materials, pedagogical oversight, and integration with the core teaching team. This paper reports on the redesign of reinforcement sessions in a challenging undergraduate course on formal methods and computational models, using a large language model (LLM) as a reflective planning tool. The LLM was prompted to simulate the perspective of a second-year student, enabling the identification of conceptual bottlenecks, gaps in intuition, and likely reasoning breakdowns before classroom delivery. These insights informed a structured, repeatable session format combining targeted review, collaborative examples, independent student work, and guided walkthroughs. Conducted over a single semester, the intervention received positive student feedback, indicating increased confidence, reduced anxiety, and improved clarity, particularly in abstract topics such as the pumping lemma and formal language expressive power comparisons. The findings suggest that reflective, instructor-facing use of LLMs can enhance pedagogical design in theoretically dense domains and may be adaptable to other cognitively demanding computer science courses.
Recently, large language models (LLMs) have demonstrated remarkable problem-solving capabilities by autonomously integrating with external tools for collaborative reasoning. However, due to the inherently complex and diverse nature of multimodal information, enabling multimodal large language models (MLLMs) to flexibly and efficiently utilize external tools during reasoning remains an underexplored challenge. In this work, we introduce ToolScope, an agentic framework designed to unify global planning with local multimodal perception, adopting a specialized Perceive tool to mitigates visual context degradation in long-horizon VQA task. ToolScope comprises three primary components: the Global Navigator, the Agentic Executor, and the Response Synthesizer. The Global Navigator functions as a "telescope", offering high-level strategic guidance. The Agentic Executor operates iteratively to augment MLLM with local perception through the integration of external tools-Search, Code, and Perceive. Finally, the Response Synthesizer consolidates and organizes the reasoning process into a coherent, user-friendly output. We evaluate ToolScope on four VQA benchmarks across diverse domains, including VQA 2.0, ScienceQA, MAT-Search and MathVista. It demonstrates strong generalization capabilities, achieving an average performance improvement of up to +6.69% across all datasets.
As large language models (LLMs) enter the medical domain, most benchmarks evaluate them on question answering or descriptive reasoning, overlooking quantitative reasoning critical to clinical decision-making. Existing datasets like MedCalc-Bench cover few calculation tasks and fail to reflect real-world computational scenarios. We introduce MedCalc-Eval, the largest benchmark for assessing LLMs' medical calculation abilities, comprising 700+ tasks across two types: equation-based (e.g., Cockcroft-Gault, BMI, BSA) and rule-based scoring systems (e.g., Apgar, Glasgow Coma Scale). These tasks span diverse specialties including internal medicine, surgery, pediatrics, and cardiology, offering a broader and more challenging evaluation setting. To improve performance, we further develop MedCalc-Env, a reinforcement learning environment built on the InternBootcamp framework, enabling multi-step clinical reasoning and planning. Fine-tuning a Qwen2.5-32B model within this environment achieves state-of-the-art results on MedCalc-Eval, with notable gains in numerical sensitivity, formula selection, and reasoning robustness. Remaining challenges include unit conversion, multi-condition logic, and contextual understanding. Code and datasets are available at https://github.com/maokangkun/MedCalc-Eval.
With powerful and integrative large language models (LLMs), medical AI agents have demonstrated unique advantages in providing personalized medical consultations, continuous health monitoring, and precise treatment plans. Retrieval-Augmented Generation (RAG) integrates personal medical documents into LLMs by an external retrievable database to address the costly retraining or fine-tuning issues in deploying customized agents. While deploying medical agents in edge devices ensures privacy protection, RAG implementations impose substantial memory access and energy consumption during the retrieval stage. This paper presents a hierarchical retrieval architecture for edge RAG, leveraging a two-stage retrieval scheme that combines approximate retrieval for candidate set generation, followed by high-precision retrieval on pre-selected document embeddings. The proposed architecture significantly reduces energy consumption and external memory access while maintaining retrieval accuracy. Simulation results show that, under TSMC 28nm technology, the proposed hierarchical retrieval architecture has reduced the overall memory access by nearly 50% and the computation by 75% compared to pure INT8 retrieval, and the total energy consumption for 1 MB data retrieval is 177.76 {\mu}J/query.