Human mobility prediction is crucial for applications ranging from location-based recommendations to urban planning, which aims to forecast users' next location visits based on historical trajectories. Despite the severe long-tailed distribution of locations, the problem of long-tailed mobility prediction remains largely underexplored. Existing long-tailed learning methods primarily focus on rebalancing the skewed distribution at the data, model, or class level, neglecting to exploit the spatiotemporal semantics of locations. To address this gap, we propose the first plug-and-play framework for long-tailed mobility prediction in an exploitation and exploration manner, named \textbf{A}daptive \textbf{LO}cation \textbf{H}ier\textbf{A}rchy learning (ALOHA). First, we construct city-tailored location hierarchy based on Large Language Models (LLMs) by exploiting Maslow's theory of human motivation to design Chain-of-Thought (CoT) prompts that captures spatiotemporal semantics. Second, we optimize the location hierarchy predictions by Gumbel disturbance and node-wise adaptive weights within the hierarchical tree structure. Experiments on state-of-the-art models across six datasets demonstrate the framework's consistent effectiveness and generalizability, which strikes a well balance between head and tail locations. Weight analysis and ablation studies reveal the optimization differences of each component for head and tail locations. Furthermore, in-depth analyses of hierarchical distance and case study demonstrate the effective semantic guidance from the location hierarchy. Our code will be made publicly available.
Large Language Models (LLMs) are increasingly used for decision making in embodied agents, yet existing safety evaluations often rely on coarse success rates and domain-specific setups, making it difficult to diagnose why and where these models fail. This obscures our understanding of embodied safety and limits the selective deployment of LLMs in high-risk physical environments. We introduce SAFEL, the framework for systematically evaluating the physical safety of LLMs in embodied decision making. SAFEL assesses two key competencies: (1) rejecting unsafe commands via the Command Refusal Test, and (2) generating safe and executable plans via the Plan Safety Test. Critically, the latter is decomposed into functional modules, goal interpretation, transition modeling, action sequencing, enabling fine-grained diagnosis of safety failures. To support this framework, we introduce EMBODYGUARD, a PDDL-grounded benchmark containing 942 LLM-generated scenarios covering both overtly malicious and contextually hazardous instructions. Evaluation across 13 state-of-the-art LLMs reveals that while models often reject clearly unsafe commands, they struggle to anticipate and mitigate subtle, situational risks. Our results highlight critical limitations in current LLMs and provide a foundation for more targeted, modular improvements in safe embodied reasoning.
Temporal reasoning and planning are essential capabilities for large language models (LLMs), yet most existing benchmarks evaluate them in isolation and under limited forms of complexity. To address this gap, we introduce the Temporal Constraint-based Planning (TCP) benchmark, that jointly assesses both capabilities. Each instance in TCP features a naturalistic dialogue around a collaborative project, where diverse and interdependent temporal constraints are explicitly or implicitly expressed, and models must infer an optimal schedule that satisfies all constraints. To construct TCP, we first generate abstract problem prototypes that are paired with realistic scenarios from various domains and enriched into dialogues using an LLM. A human quality check is performed on a sampled subset to confirm the reliability of our benchmark. We evaluate state-of-the-art LLMs and find that even the strongest models struggle with TCP, highlighting its difficulty and revealing limitations in LLMs' temporal constraint-based planning abilities. We analyze underlying failure cases, open source our benchmark, and hope our findings can inspire future research.
Although LLMs demonstrate proficiency in several text-based reasoning and planning tasks, their implementation in robotics control is constrained by significant deficiencies: (1) LLM agents are designed to work mainly with textual inputs rather than visual conditions; (2) Current multimodal agents treat LLMs as static planners, which separates their reasoning from environment dynamics, resulting in actions that do not take domain-specific knowledge into account; and (3) LLMs are not designed to learn from visual interactions, which makes it harder for them to make better policies for specific domains. In this paper, we introduce EMAC+, an Embodied Multimodal Agent that collaboratively integrates LLM and VLM via a bidirectional training paradigm. Unlike existing methods, EMAC+ dynamically refines high-level textual plans generated by an LLM using real-time feedback from a VLM executing low-level visual control tasks. We address critical limitations of previous models by enabling the LLM to internalize visual environment dynamics directly through interactive experience, rather than relying solely on static symbolic mappings. Extensive experimental evaluations on ALFWorld and RT-1 benchmarks demonstrate that EMAC+ achieves superior task performance, robustness against noisy observations, and efficient learning. We also conduct thorough ablation studies and provide detailed analyses of success and failure cases.
While showing sophisticated reasoning abilities, large language models (LLMs) still struggle with long-horizon decision-making tasks due to deficient exploration and long-term credit assignment, especially in sparse-reward scenarios. Inspired by the divide-and-conquer principle, we propose an innovative framework **GLIDER** (**G**rounding **L**anguage Models as Eff**I**cient **D**ecision-Making Agents via Offline Hi**E**rarchical **R**einforcement Learning) that introduces a parameter-efficient and generally applicable hierarchy to LLM policies. We develop a scheme where the low-level controller is supervised with abstract, step-by-step plans that are learned and instructed by the high-level policy. This design decomposes complicated problems into a series of coherent chain-of-thought reasoning sub-tasks, providing flexible temporal abstraction to significantly enhance exploration and learning for long-horizon tasks. Furthermore, GLIDER facilitates fast online adaptation to non-stationary environments owing to the strong transferability of its task-agnostic low-level skills. Experiments on ScienceWorld and ALFWorld benchmarks show that GLIDER achieves consistent performance gains, along with enhanced generalization capabilities.
In this work, we introduce CAD-Coder, a novel framework that reformulates text-to-CAD as the generation of CadQuery scripts - a Python-based, parametric CAD language. This representation enables direct geometric validation, a richer modeling vocabulary, and seamless integration with existing LLMs. To further enhance code validity and geometric fidelity, we propose a two-stage learning pipeline: (1) supervised fine-tuning on paired text-CadQuery data, and (2) reinforcement learning with Group Reward Policy Optimization (GRPO), guided by a CAD-specific reward comprising both a geometric reward (Chamfer Distance) and a format reward. We also introduce a chain-of-thought (CoT) planning process to improve model reasoning, and construct a large-scale, high-quality dataset of 110K text-CadQuery-3D model triplets and 1.5K CoT samples via an automated pipeline. Extensive experiments demonstrate that CAD-Coder enables LLMs to generate diverse, valid, and complex CAD models directly from natural language, advancing the state of the art of text-to-CAD generation and geometric reasoning.
Planning represents a fundamental capability of intelligent agents, requiring comprehensive environmental understanding, rigorous logical reasoning, and effective sequential decision-making. While Large Language Models (LLMs) have demonstrated remarkable performance on certain planning tasks, their broader application in this domain warrants systematic investigation. This paper presents a comprehensive review of LLM-based planning. Specifically, this survey is structured as follows: First, we establish the theoretical foundations by introducing essential definitions and categories about automated planning. Next, we provide a detailed taxonomy and analysis of contemporary LLM-based planning methodologies, categorizing them into three principal approaches: 1) External Module Augmented Methods that combine LLMs with additional components for planning, 2) Finetuning-based Methods that involve using trajectory data and feedback signals to adjust LLMs in order to improve their planning abilities, and 3) Searching-based Methods that break down complex tasks into simpler components, navigate the planning space, or enhance decoding strategies to find the best solutions. Subsequently, we systematically summarize existing evaluation frameworks, including benchmark datasets, evaluation metrics and performance comparisons between representative planning methods. Finally, we discuss the underlying mechanisms enabling LLM-based planning and outline promising research directions for this rapidly evolving field. We hope this survey will serve as a valuable resource to inspire innovation and drive progress in this field.
The electricity system becomes more complex, connecting massive numbers of end-users and distributed generators. Adding or removing grid connections requires expert studies to align technical constraints with user requests. In times of labour shortages, carrying out these studies represents a significant amount of time that engineers at system operators spend in planning departments. As time is limited, only standard block connectivity contracts can be offered to end-users, or the requests pile up. Even if offers are made, these often do not perfectly match the user's requirements, leading to overpaying or underusing the grid capacity. This paper investigates whether end-users can negotiate individual, flexible time-of-use contracts directly with the grid using Large Language Models (LLM) in chats at scale. The LLM-based chat has direct access to a model of the grid and studies the grid's technical constraints just as an expert engineer. The advantage of this system is that end-users can directly interact with grid models through natural language; no intermediate is needed to service, analyse, study, assess, advise, consult and engineer. This initial study paves the way toward developing this tailored LLM system, resulting in possible high-efficiency gains for grid planning and customer management.
This review presents a comprehensive analysis of two emerging paradigms in AI-assisted software development: vibe coding and agentic coding. While both leverage large language models (LLMs), they differ fundamentally in autonomy, architectural design, and the role of the developer. Vibe coding emphasizes intuitive, human-in-the-loop interaction through prompt-based, conversational workflows that support ideation, experimentation, and creative exploration. In contrast, agentic coding enables autonomous software development through goal-driven agents capable of planning, executing, testing, and iterating tasks with minimal human intervention. We propose a detailed taxonomy spanning conceptual foundations, execution models, feedback loops, safety mechanisms, debugging strategies, and real-world tool ecosystems. Through comparative workflow analysis and 20 detailed use cases, we illustrate how vibe systems thrive in early-stage prototyping and education, while agentic systems excel in enterprise-grade automation, codebase refactoring, and CI/CD integration. We further examine emerging trends in hybrid architectures, where natural language interfaces are coupled with autonomous execution pipelines. Finally, we articulate a future roadmap for agentic AI, outlining the infrastructure needed for trustworthy, explainable, and collaborative systems. Our findings suggest that successful AI software engineering will rely not on choosing one paradigm, but on harmonizing their strengths within a unified, human-centered development lifecycle.
Large Language Models (LLMs) falter in multi-step interactions -- often hallucinating, repeating actions, or misinterpreting user corrections -- due to reliance on linear, unstructured context. This fragility stems from the lack of persistent memory to track evolving goals and task dependencies, undermining trust in autonomous agents. We introduce the Task Memory Engine (TME), a modular memory controller that transforms existing LLMs into robust, revision-aware agents without fine-tuning. TME implements a spatial memory framework that replaces flat context with graph-based structures to support consistent, multi-turn reasoning. Departing from linear concatenation and ReAct-style prompting, TME builds a dynamic task graph -- either a tree or directed acyclic graph (DAG) -- to map user inputs to subtasks, align them with prior context, and enable dependency-tracked revisions. Its Task Representation and Intent Management (TRIM) component models task semantics and user intent to ensure accurate interpretation. Across four multi-turn scenarios-trip planning, cooking, meeting scheduling, and shopping cart editing -- TME eliminates 100% of hallucinations and misinterpretations in three tasks, and reduces hallucinations by 66.7% and misinterpretations by 83.3% across 27 user turns, outperforming ReAct. TME's modular design supports plug-and-play deployment and domain-specific customization, adaptable to both personal assistants and enterprise automation. We release TME's codebase, benchmarks, and components as open-source resources, enabling researchers to develop reliable LLM agents. TME's scalable architecture addresses a critical gap in agent performance across complex, interactive settings.
Recently, large language models (LLMs) have demonstrated remarkable capabilities in natural language processing tasks, yet they remain prone to hallucinations when reasoning with insufficient internal knowledge. While integrating LLMs with knowledge graphs (KGs) provides access to structured, verifiable information, existing approaches often generate incomplete or factually inconsistent reasoning paths. To this end, we propose Self-Reflective Planning (SRP), a framework that synergizes LLMs with KGs through iterative, reference-guided reasoning. Specifically, given a question and topic entities, SRP first searches for references to guide planning and reflection. In the planning process, it checks initial relations and generates a reasoning path. After retrieving knowledge from KGs through a reasoning path, it implements iterative reflection by judging the retrieval result and editing the reasoning path until the answer is correctly retrieved. Extensive experiments on three public datasets demonstrate that SRP surpasses various strong baselines and further underscore its reliable reasoning ability.
Ensuring that large language models (LLMs) can effectively assess, detect, explain, and remediate software vulnerabilities is critical for building robust and secure software systems. We introduce VADER, a human-evaluated benchmark designed explicitly to assess LLM performance across four key vulnerability-handling dimensions: assessment, detection, explanation, and remediation. VADER comprises 174 real-world software vulnerabilities, each carefully curated from GitHub repositories and annotated by security experts. For each vulnerability case, models are tasked with identifying the flaw, classifying it using Common Weakness Enumeration (CWE), explaining its underlying cause, proposing a patch, and formulating a test plan. Using a one-shot prompting strategy, we benchmark six state-of-the-art LLMs (Claude 3.7 Sonnet, Gemini 2.5 Pro, GPT-4.1, GPT-4.5, Grok 3 Beta, and o3) on VADER, and human security experts evaluated each response according to a rigorous scoring rubric emphasizing remediation (quality of the code fix, 50%), explanation (20%), and classification and test plan (30%) according to a standardized rubric. Our results show that current state-of-the-art LLMs achieve only moderate success on VADER - OpenAI's o3 attained 54.7% accuracy overall, with others in the 49-54% range, indicating ample room for improvement. Notably, remediation quality is strongly correlated (Pearson r > 0.97) with accurate classification and test plans, suggesting that models that effectively categorize vulnerabilities also tend to fix them well. VADER's comprehensive dataset, detailed evaluation rubrics, scoring tools, and visualized results with confidence intervals are publicly released, providing the community with an interpretable, reproducible benchmark to advance vulnerability-aware LLMs. All code and data are available at: https://github.com/AfterQuery/vader
Querying tables with unstructured data is challenging due to the presence of text (or image), either embedded in the table or in external paragraphs, which traditional SQL struggles to process, especially for tasks requiring semantic reasoning. While Large Language Models (LLMs) excel at understanding context, they face limitations with long input sequences. Existing approaches that combine SQL and LLMs typically rely on rigid, predefined work-flows, limiting their adaptability to complex queries. To address these issues, we introduce Weaver , a modular pipeline that dynamically integrates SQL and LLMs for table-based question answering (TableQA). Weaver generates a flexible, step-by-step plan that combines SQL for structured data retrieval with LLMs for semantic processing. By decomposing complex queries into manageable subtasks, Weaver improves accuracy and generalization. Our experiments show that Weaver consistently outperforms state-of-the-art methods across four TableQA datasets, reducing both API calls and error rates.
Large language models (LLMs) typically generate identical or similar responses for all users given the same prompt, posing serious safety risks in high-stakes applications where user vulnerabilities differ widely. Existing safety evaluations primarily rely on context-independent metrics - such as factuality, bias, or toxicity - overlooking the fact that the same response may carry divergent risks depending on the user's background or condition. We introduce personalized safety to fill this gap and present PENGUIN - a benchmark comprising 14,000 scenarios across seven sensitive domains with both context-rich and context-free variants. Evaluating six leading LLMs, we demonstrate that personalized user information significantly improves safety scores by 43.2%, confirming the effectiveness of personalization in safety alignment. However, not all context attributes contribute equally to safety enhancement. To address this, we develop RAISE - a training-free, two-stage agent framework that strategically acquires user-specific background. RAISE improves safety scores by up to 31.6% over six vanilla LLMs, while maintaining a low interaction cost of just 2.7 user queries on average. Our findings highlight the importance of selective information gathering in safety-critical domains and offer a practical solution for personalizing LLM responses without model retraining. This work establishes a foundation for safety research that adapts to individual user contexts rather than assuming a universal harm standard.
We introduce the Exemplar-Based Expository Text Generation task, aiming to generate an expository text on a new topic using an exemplar on a similar topic. Current methods fall short due to their reliance on extensive exemplar data, difficulty in adapting topic-specific content, and issues with long-text coherence. To address these challenges, we propose the concept of Adaptive Imitation and present a novel Recurrent Plan-then-Adapt (RePA) framework. RePA leverages large language models (LLMs) for effective adaptive imitation through a fine-grained plan-then-adapt process. RePA also enables recurrent segment-by-segment imitation, supported by two memory structures that enhance input clarity and output coherence. We also develop task-specific evaluation metrics--imitativeness, adaptiveness, and adaptive-imitativeness--using LLMs as evaluators. Experimental results across our collected three diverse datasets demonstrate that RePA surpasses existing baselines in producing factual, consistent, and relevant texts for this task.
Recent advances have increasingly applied large language models (LLMs) to electrocardiogram (ECG) interpretation, giving rise to Electrocardiogram-Language Models (ELMs). Conditioned on an ECG and a textual query, an ELM autoregressively generates a free-form textual response. Unlike traditional classification-based systems, ELMs emulate expert cardiac electrophysiologists by issuing diagnoses, analyzing waveform morphology, identifying contributing factors, and proposing patient-specific action plans. To realize this potential, researchers are curating instruction-tuning datasets that pair ECGs with textual dialogues and are training ELMs on these resources. Yet before scaling ELMs further, there is a fundamental question yet to be explored: What is the most effective ECG input representation? In recent works, three candidate representations have emerged-raw time-series signals, rendered images, and discretized symbolic sequences. We present the first comprehensive benchmark of these modalities across 6 public datasets and 5 evaluation metrics. We find symbolic representations achieve the greatest number of statistically significant wins over both signal and image inputs. We further ablate the LLM backbone, ECG duration, and token budget, and we evaluate robustness to signal perturbations. We hope that our findings offer clear guidance for selecting input representations when developing the next generation of ELMs.
Existing large language models (LLMs) driven search agents typically rely on prompt engineering to decouple the user queries into search plans, limiting their effectiveness in complex scenarios requiring reasoning. Furthermore, they suffer from excessive token consumption due to Python-based search plan representations and inadequate integration of multimedia elements for both input processing and response generation. To address these challenges, we introduce SearchExpert, a training method for LLMs to improve their multimedia search capabilities in response to complex search queries. Firstly, we reformulate the search plan in an efficient natural language representation to reduce token consumption. Then, we propose the supervised fine-tuning for searching (SFTS) to fine-tune LLM to adapt to these representations, together with an automated dataset construction pipeline. Secondly, to improve reasoning-intensive search capabilities, we propose the reinforcement learning from search feedback (RLSF) that takes the search results planned by LLM as the reward signals. Thirdly, we propose a multimedia understanding and generation agent that enables the fine-tuned LLM to process visual input and produce visual output during inference. Finally, we establish an automated benchmark construction pipeline and a human evaluation framework. Our resulting benchmark, SearchExpertBench-25, comprises 200 multiple-choice questions spanning financial and international news scenarios that require reasoning in searching. Experiments demonstrate that SearchExpert outperforms the commercial LLM search method (Perplexity Pro) by 36.60% on the existing FinSearchBench-24 benchmark and 54.54% on our proposed SearchExpertBench-25. Human evaluations further confirm the superior readability.
Climate policy scenario generation and evaluation have traditionally relied on integrated assessment models (IAMs) and expert-driven qualitative analysis. These methods enable stakeholders, such as policymakers and researchers, to anticipate impacts, plan governance strategies, and develop mitigation measures. However, traditional methods are often time-intensive, reliant on simple extrapolations of past trends, and limited in capturing the complex and interconnected nature of energy and climate issues. With the advent of artificial intelligence (AI), particularly generative AI models trained on vast datasets, these limitations can be addressed, ensuring robustness even under limited data conditions. In this work, we explore the novel method that employs generative AI, specifically large language models (LLMs), to simulate climate policy scenarios for Sub-Saharan Africa. These scenarios focus on energy transition themes derived from the historical United Nations Climate Change Conference (COP) documents. By leveraging generative models, the project aims to create plausible and diverse policy scenarios that align with regional climate goals and energy challenges. Given limited access to human evaluators, automated techniques were employed for scenario evaluation. We generated policy scenarios using the llama3.2-3B model. Of the 34 generated responses, 30 (88%) passed expert validation, accurately reflecting the intended impacts provided in the corresponding prompts. We compared these validated responses against assessments from a human climate expert and two additional LLMs (gemma2-2B and mistral-7B). Our structured, embedding-based evaluation framework shows that generative AI effectively generate scenarios that are coherent, relevant, plausible, and diverse. This approach offers a transformative tool for climate policy planning in data-constrained regions.
Hardware accelerators, especially those designed for tensor processing, have become ubiquitous in today's computing landscape. However, even with significant efforts in building compilers, programming these tensor accelerators remains challenging, leaving much of their potential underutilized. Recently, large language models (LLMs), trained on large amounts of code, have shown significant promise in code generation and optimization tasks, but generating low-resource languages like specialized tensor accelerator code still poses a significant challenge. We tackle this challenge with Autocomp, an approach that empowers accelerator programmers to leverage domain knowledge and hardware feedback to optimize code via an automated LLM-driven search. We accomplish this by: 1) formulating each optimization pass as a structured two-phase prompt, divided into planning and code generation phases, 2) inserting domain knowledge during planning via a concise and adaptable optimization menu, and 3) integrating correctness and performance metrics from hardware as feedback at each search iteration. Across three categories of representative workloads and two different accelerators, we demonstrate that Autocomp-optimized code runs 5.6x (GEMM) and 2.7x (convolution) faster than the vendor-provided library, and outperforms expert-level hand-tuned code by 1.4x (GEMM), 1.1x (convolution), and 1.3x (fine-grained linear algebra). Additionally, we demonstrate that optimization schedules generated from Autocomp can be reused across similar tensor operations, improving speedups by up to 24% under a fixed sample budget.
Large Language Models (LLMs)-based Multi-Agent Systems (MAS) exhibit remarkable problem-solving and task planning capabilities across diverse domains due to their specialized agentic roles and collaborative interactions. However, this also amplifies the severity of security risks under MAS attacks. To address this, we introduce MASTER, a novel security research framework for MAS, focusing on diverse Role configurations and Topological structures across various scenarios. MASTER offers an automated construction process for different MAS setups and an information-flow-based interaction paradigm. To tackle MAS security challenges in varied scenarios, we design a scenario-adaptive, extensible attack strategy utilizing role and topological information, which dynamically allocates targeted, domain-specific attack tasks for collaborative agent execution. Our experiments demonstrate that such an attack, leveraging role and topological information, exhibits significant destructive potential across most models. Additionally, we propose corresponding defense strategies, substantially enhancing MAS resilience across diverse scenarios. We anticipate that our framework and findings will provide valuable insights for future research into MAS security challenges.
Various industries have produced a large number of documents such as industrial plans, technical guidelines, and regulations that are structurally complex and content-wise fragmented. This poses significant challenges for experts and decision-makers in terms of retrieval and understanding. Although existing LLM-based Retrieval-Augmented Generation methods can provide context-related suggestions, they lack quantitative weighting and traceable reasoning paths, making it difficult to offer multi-level and transparent decision support. To address this issue, this paper proposes the RAD method, which integrates Multi-Criteria Decision Making with the semantic understanding capabilities of LLMs. The method automatically extracts key criteria from industry documents, builds a weighted hierarchical decision model, and generates structured reports under model guidance. The RAD framework introduces explicit weight assignment and reasoning chains in decision generation to ensure accuracy, completeness, and traceability. Experiments show that in various decision-making tasks, the decision reports generated by RAD significantly outperform existing methods in terms of detail, rationality, and structure, demonstrating its application value and potential in complex decision support scenarios.
Multi-agent AI systems (MAS) offer a promising framework for distributed intelligence, enabling collaborative reasoning, planning, and decision-making across autonomous agents. This paper provides a systematic outlook on the current opportunities and challenges of MAS, drawing insights from recent advances in large language models (LLMs), federated optimization, and human-AI interaction. We formalize key concepts including agent topology, coordination protocols, and shared objectives, and identify major risks such as dependency, misalignment, and vulnerabilities arising from training data overlap. Through a biologically inspired simulation and comprehensive theoretical framing, we highlight critical pathways for developing robust, scalable, and secure MAS in real-world settings.
Pre-trained Large Language Models (LLMs) have shown promise in solving planning problems but often struggle to ensure plan correctness, especially for long-horizon tasks. Meanwhile, traditional robotic task and motion planning (TAMP) frameworks address these challenges more reliably by combining high-level symbolic search with low-level motion planning. At the core of TAMP is the planning domain, an abstract world representation defined through symbolic predicates and actions. However, creating these domains typically involves substantial manual effort and domain expertise, limiting generalizability. We introduce Planning Domain Derivation with LLMs (PDDLLM), a novel approach that combines simulated physical interaction with LLM reasoning to improve planning performance. The method reduces reliance on humans by inferring planning domains from a single annotated task-execution demonstration. Unlike prior domain-inference methods that rely on partially predefined or language descriptions of planning domains, PDDLLM constructs domains entirely from scratch and automatically integrates them with low-level motion planning skills, enabling fully automated long-horizon planning. PDDLLM is evaluated on over 1,200 diverse tasks spanning nine environments and benchmarked against six LLM-based planning baselines, demonstrating superior long-horizon planning performance, lower token costs, and successful deployment on multiple physical robot platforms.
Recent advances in web-augmented large language models (LLMs) have exhibited strong performance in complex reasoning tasks, yet these capabilities are mostly locked in proprietary systems with opaque architectures. In this work, we propose \textbf{ManuSearch}, a transparent and modular multi-agent framework designed to democratize deep search for LLMs. ManuSearch decomposes the search and reasoning process into three collaborative agents: (1) a solution planning agent that iteratively formulates sub-queries, (2) an Internet search agent that retrieves relevant documents via real-time web search, and (3) a structured webpage reading agent that extracts key evidence from raw web content. To rigorously evaluate deep reasoning abilities, we introduce \textbf{ORION}, a challenging benchmark focused on open-web reasoning over long-tail entities, covering both English and Chinese. Experimental results show that ManuSearch substantially outperforms prior open-source baselines and even surpasses leading closed-source systems. Our work paves the way for reproducible, extensible research in open deep search systems. We release the data and code in https://github.com/RUCAIBox/ManuSearch
Large language models (LLMs) excel in tasks like question answering and dialogue, but complex tasks requiring interaction, such as negotiation and persuasion, require additional long-horizon reasoning and planning. Reinforcement learning (RL) fine-tuning can enable such planning in principle, but suffers from drawbacks that hinder scalability. In particular, multi-turn RL training incurs high memory and computational costs, which are exacerbated when training LLMs as policies. Furthermore, the largest LLMs do not expose the APIs necessary to be trained in such manner. As a result, modern methods to improve the reasoning of LLMs rely on sophisticated prompting mechanisms rather than RL fine-tuning. To remedy this, we propose a novel approach that uses goal-conditioned value functions to guide the reasoning of LLM agents, that scales even to large API-based models. These value functions predict how a task will unfold given an action, allowing the LLM agent to evaluate multiple possible outcomes, both positive and negative, to plan effectively. In addition, these value functions are trained over reasoning steps rather than full actions, to be a concise and light-weight module that facilitates decision-making in multi-turn interactions. We validate our method on tasks requiring interaction, including tool use, social deduction, and dialogue, demonstrating superior performance over both RL fine-tuning and prompting methods while maintaining efficiency and scalability.
Long-form video understanding presents significant challenges due to extensive temporal-spatial complexity and the difficulty of question answering under such extended contexts. While Large Language Models (LLMs) have demonstrated considerable advancements in video analysis capabilities and long context handling, they continue to exhibit limitations when processing information-dense hour-long videos. To overcome such limitations, we propose the Deep Video Discovery agent to leverage an agentic search strategy over segmented video clips. Different from previous video agents manually designing a rigid workflow, our approach emphasizes the autonomous nature of agents. By providing a set of search-centric tools on multi-granular video database, our DVD agent leverages the advanced reasoning capability of LLM to plan on its current observation state, strategically selects tools, formulates appropriate parameters for actions, and iteratively refines its internal reasoning in light of the gathered information. We perform comprehensive evaluation on multiple long video understanding benchmarks that demonstrates the advantage of the entire system design. Our DVD agent achieves SOTA performance, significantly surpassing prior works by a large margin on the challenging LVBench dataset. Comprehensive ablation studies and in-depth tool analyses are also provided, yielding insights to further advance intelligent agents tailored for long-form video understanding tasks. The code will be released later.
Large-language-model (LLM) agents excel at reactive dialogue but struggle with proactive, goal-driven interactions due to myopic decoding and costly planning. We introduce DialogXpert, which leverages a frozen LLM to propose a small, high-quality set of candidate actions per turn and employs a compact Q-network over fixed BERT embeddings trained via temporal-difference learning to select optimal moves within this reduced space. By tracking the user's emotions, DialogXpert tailors each decision to advance the task while nurturing a genuine, empathetic connection. Across negotiation, emotional support, and tutoring benchmarks, DialogXpert drives conversations to under $3$ turns with success rates exceeding 94\% and, with a larger LLM prior, pushes success above 97\% while markedly improving negotiation outcomes. This framework delivers real-time, strategic, and emotionally intelligent dialogue planning at scale. Code available at https://github.com/declare-lab/dialogxpert/
Large Language Model (LLM) agents represent a promising shift in human-AI interaction, moving beyond passive prompt-response systems to autonomous agents capable of reasoning, planning, and goal-directed action. Despite the widespread application in specialized, high-effort tasks like coding and scientific research, we highlight a critical usability gap in high-demand, mass-market applications. This position paper argues that the limited real-world adoption of LLM agents stems not only from gaps in model capabilities, but also from a fundamental tradeoff between the value an agent can provide and the costs incurred during real-world use. Hence, we call for a shift from solely optimizing model performance to a broader, utility-driven perspective: evaluating agents through the lens of the overall agentic return on investment (Agent ROI). By identifying key factors that determine Agentic ROI--information quality, agent time, and cost--we posit a zigzag development trajectory in optimizing agentic ROI: first scaling up to improve the information quality, then scaling down to minimize the time and cost. We outline the roadmap across different development stages to bridge the current usability gaps, aiming to make LLM agents truly scalable, accessible, and effective in real-world contexts.
Agents powered by large language models (LLMs) have demonstrated strong planning and decision-making capabilities in complex embodied environments. However, such agents often suffer from inefficiencies in multi-turn interactions, frequently trapped in repetitive loops or issuing ineffective commands, leading to redundant computational overhead. Instead of relying solely on learning from trajectories, we take a first step toward exploring the early-exit behavior for LLM-based agents. We propose two complementary approaches: 1. an $\textbf{intrinsic}$ method that injects exit instructions during generation, and 2. an $\textbf{extrinsic}$ method that verifies task completion to determine when to halt an agent's trial. To evaluate early-exit mechanisms, we introduce two metrics: one measures the reduction of $\textbf{redundant steps}$ as a positive effect, and the other evaluates $\textbf{progress degradation}$ as a negative effect. Experiments with 4 different LLMs across 5 embodied environments show significant efficiency improvements, with only minor drops in agent performance. We also validate a practical strategy where a stronger agent assists after an early-exit agent, achieving better performance with the same total steps. We will release our code to support further research.
This work presents a dual-agent Large Language Model (LLM)-based reasoning method for mechanism synthesis, capable of reasoning at both linguistic and symbolic levels to generate geometrical and dynamic outcomes. The model consists of a composition of well-defined functions that, starting from a natural language specification, references abstract properties through supporting equations, generates and parametrizes simulation code, and elicits feedback anchor points using symbolic regression and distance functions. This process closes an actionable refinement loop at the linguistic and symbolic layers. The approach is shown to be both effective and convergent in the context of planar mechanisms. Additionally, we introduce MSynth, a novel benchmark for planar mechanism synthesis, and perform a comprehensive analysis of the impact of the model components. We further demonstrate that symbolic regression prompts unlock mechanistic insights only when applied to sufficiently large architectures.