Recent advances in multimodal LLMs and systems that use tools for long-video QA point to the promise of reasoning over hour-long episodes. However, many methods still compress content into lossy summaries or rely on limited toolsets, weakening temporal grounding and missing fine-grained cues. We propose a multi-agent framework in which a master LLM coordinates a grounding agent to localize question-relevant segments and a vision agent to extract targeted textual observations. The master agent plans with a step limit, and is trained with reinforcement learning to encourage concise, correct, and efficient multi-agent cooperation. This design helps the master agent focus on relevant clips via grounding, complements subtitles with visual detail, and yields interpretable trajectories. On our proposed LongTVQA and LongTVQA+ which are episode-level datasets aggregated from TVQA/TVQA+, our multi-agent system significantly outperforms strong non-agent baselines. Experiments also show reinforcement learning further strengthens reasoning and planning for the trained agent. Code and data will be shared at https://longvideoagent.github.io/.
Stereotactic radiosurgery (SRS) demands precise dose shaping around critical structures, yet black-box AI systems have limited clinical adoption due to opacity concerns. We tested whether chain-of-thought reasoning improves agentic planning in a retrospective cohort of 41 patients with brain metastases treated with 18 Gy single-fraction SRS. We developed SAGE (Secure Agent for Generative Dose Expertise), an LLM-based planning agent for automated SRS treatment planning. Two variants generated plans for each case: one using a non-reasoning model, one using a reasoning model. The reasoning variant showed comparable plan dosimetry relative to human planners on primary endpoints (PTV coverage, maximum dose, conformity index, gradient index; all p > 0.21) while reducing cochlear dose below human baselines (p = 0.022). When prompted to improve conformity, the reasoning model demonstrated systematic planning behaviors including prospective constraint verification (457 instances) and trade-off deliberation (609 instances), while the standard model exhibited none of these deliberative processes (0 and 7 instances, respectively). Content analysis revealed that constraint verification and causal explanation concentrated in the reasoning agent. The optimization traces serve as auditable logs, offering a path toward transparent automated planning.
As LLMs shift toward autonomous agents, Deep Research has emerged as a pivotal metric. However, existing academic benchmarks like BrowseComp often fail to meet real-world demands for open-ended research, which requires robust skills in intent recognition, long-horizon decision-making, and cross-source verification. To address this, we introduce Step-DeepResearch, a cost-effective, end-to-end agent. We propose a Data Synthesis Strategy Based on Atomic Capabilities to reinforce planning and report writing, combined with a progressive training path from agentic mid-training to SFT and RL. Enhanced by a Checklist-style Judger, this approach significantly improves robustness. Furthermore, to bridge the evaluation gap in the Chinese domain, we establish ADR-Bench for realistic deep research scenarios. Experimental results show that Step-DeepResearch (32B) scores 61.4% on Scale AI Research Rubrics. On ADR-Bench, it significantly outperforms comparable models and rivals SOTA closed-source models like OpenAI and Gemini DeepResearch. These findings prove that refined training enables medium-sized models to achieve expert-level capabilities at industry-leading cost-efficiency.
Recent advances in Large Language Models (LLMs) and Large Reasoning Models (LRMs) have enabled agentic search systems that interleave multi-step reasoning with external tool use. However, existing frameworks largely rely on unstructured natural-language reasoning and accumulate raw intermediate traces in the context, which often leads to unstable reasoning trajectories, context overflow, and degraded performance on complex multi-hop queries. In this study, we introduce Laser, a general framework for stabilizing and scaling agentic search. Laser defines a symbolic action protocol that organizes agent behaviors into three spaces: planning, task-solving, and retrospection. Each action is specified with explicit semantics and a deterministic execution format, enabling structured and logical reasoning processes and reliable action parsing. This design makes intermediate decisions interpretable and traceable, enhancing explicit retrospection and fine-grained control over reasoning trajectories. In coordination with parsable actions, Laser further maintains a compact context register that stores only essential states of the reasoning process, allowing the agent to reason over long horizons without uncontrolled context expansion. Experiments on Qwen2.5/3-series models across challenging multi-hop QA datasets show that Laser consistently outperforms existing agentic search baselines under both prompting-only and fine-tuning settings, demonstrating that Laser provides a principled and effective foundation for robust, scalable agentic search.
Visual-language reasoning, driving knowledge, and value alignment are essential for advanced autonomous driving systems. However, existing approaches largely rely on data-driven learning, making it difficult to capture the complex logic underlying decision-making through imitation or limited reinforcement rewards. To address this, we propose KnowVal, a new autonomous driving system that enables visual-language reasoning through the synergistic integration of open-world perception and knowledge retrieval. Specifically, we construct a comprehensive driving knowledge graph that encodes traffic laws, defensive driving principles, and ethical norms, complemented by an efficient LLM-based retrieval mechanism tailored for driving scenarios. Furthermore, we develop a human-preference dataset and train a Value Model to guide interpretable, value-aligned trajectory assessment. Experimental results show that our method substantially improves planning performance while remaining compatible with existing architectures. Notably, KnowVal achieves the lowest collision rate on nuScenes and state-of-the-art results on Bench2Drive.
As networks evolve toward 5G Standalone and 6G, operators face orchestration challenges that exceed the limits of static automation and Deep Reinforcement Learning. Although Large Language Model (LLM) agents offer a path toward intent-based networking, they introduce stochastic risks, including topology hallucinations and policy non-compliance. To mitigate this, we propose Graph-Symbolic Policy Enforcement and Control (G-SPEC), a neuro-symbolic framework that constrains probabilistic planning with deterministic verification. The architecture relies on a Governance Triad - a telecom-adapted agent (TSLAM-4B), a Network Knowledge Graph (NKG), and SHACL constraints. We evaluated G-SPEC on a simulated 450-node 5G Core, achieving zero safety violations and a 94.1% remediation success rate, significantly outperforming the 82.4% baseline. Ablation analysis indicates that NKG validation drives the majority of safety gains (68%), followed by SHACL policies (24%). Scalability tests on topologies ranging from 10K to 100K nodes demonstrate that validation latency scales as $O(k^{1.2})$ where $k$ is subgraph size. With a processing overhead of 142ms, G-SPEC is viable for SMO-layer operations.
Retrieval-Augmented Generation (RAG) has emerged as a powerful paradigm for Large Language Models (LLMs) to address knowledge-intensive queries requiring domain-specific or up-to-date information. To handle complex multi-hop questions that are challenging for single-step retrieval, iterative RAG approaches incorporating reinforcement learning have been proposed. However, existing iterative RAG systems typically plan to decompose questions without leveraging information about the available retrieval corpus, leading to inefficient retrieval and reasoning chains that cascade into suboptimal performance. In this paper, we introduce Early Knowledge Alignment (EKA), a simple but effective module that aligns LLMs with retrieval set before planning in iterative RAG systems with contextually relevant retrieved knowledge. Extensive experiments on six standard RAG datasets demonstrate that by establishing a stronger reasoning foundation, EKA significantly improves retrieval precision, reduces cascading errors, and enhances both performance and efficiency. Our analysis from an entropy perspective demonstrate that incorporating early knowledge reduces unnecessary exploration during the reasoning process, enabling the model to focus more effectively on relevant information subsets. Moreover, EKA proves effective as a versatile, training-free inference strategy that scales seamlessly to large models. Generalization tests across diverse datasets and retrieval corpora confirm the robustness of our approach. Overall, EKA advances the state-of-the-art in iterative RAG systems while illuminating the critical interplay between structured reasoning and efficient exploration in reinforcement learning-augmented frameworks. The code is released at \href{https://github.com/yxzwang/EarlyKnowledgeAlignment}{Github}.
Spatio-temporal graph neural networks (ST-GNNs) have achieved notable success in structured domains such as road traffic and public transportation, where spatial entities can be naturally represented as fixed nodes. In contrast, many real-world systems including maritime traffic lack such fixed anchors, making the construction of spatio-temporal graphs a fundamental challenge. Anomaly detection in these non-grid environments is particularly difficult due to the absence of canonical reference points, the sparsity and irregularity of trajectories, and the fact that anomalies may manifest at multiple granularities. In this work, we introduce a novel benchmark dataset for anomaly detection in the maritime domain, extending the Open Maritime Traffic Analysis Dataset (OMTAD) into a benchmark tailored for graph-based anomaly detection. Our dataset enables systematic evaluation across three different granularities: node-level, edge-level, and graph-level anomalies. We plan to employ two specialized LLM-based agents: \emph{Trajectory Synthesizer} and \emph{Anomaly Injector} to construct richer interaction contexts and generate semantically meaningful anomalies. We expect this benchmark to promote reproducibility and to foster methodological advances in anomaly detection for non-grid spatio-temporal systems.
Embodied robotic AI systems designed to manage complex daily tasks rely on a task planner to understand and decompose high-level tasks. While most research focuses on enhancing the task-understanding abilities of LLMs/VLMs through fine-tuning or chain-of-thought prompting, this paper argues that defining the planned skill set is equally crucial. To handle the complexity of daily environments, the skill set should possess a high degree of generalization ability. Empirically, more abstract expressions tend to be more generalizable. Therefore, we propose to abstract the planned result as a set of meta-actions. Each meta-action comprises three components: {move/rotate, end-effector status change, relationship with the environment}. This abstraction replaces human-centric concepts, such as grasping or pushing, with the robot's intrinsic functionalities. As a result, the planned outcomes align seamlessly with the complete range of actions that the robot is capable of performing. Furthermore, to ensure that the LLM/VLM accurately produces the desired meta-action format, we employ the Retrieval-Augmented Generation (RAG) technique, which leverages a database of human-annotated planning demonstrations to facilitate in-context learning. As the system successfully completes more tasks, the database will self-augment to continue supporting diversity. The meta-action set and its integration with RAG are two novel contributions of our planner, denoted as MaP-AVR, the meta-action planner for agents composed of VLM and RAG. To validate its efficacy, we design experiments using GPT-4o as the pre-trained LLM/VLM model and OmniGibson as our robotic platform. Our approach demonstrates promising performance compared to the current state-of-the-art method. Project page: https://map-avr.github.io/.
LLMs and VLMs are increasingly deployed as embodied agents, yet existing benchmarks largely revolve around simple short-term tasks and struggle to capture rich realistic constraints that shape real-world decision making. To close this gap, we propose DeliveryBench, a city-scale embodied benchmark grounded in the real-world profession of food delivery. Food couriers naturally operate under long-horizon objectives (maximizing net profit over hours) while managing diverse constraints, e.g., delivery deadline, transportation expense, vehicle battery, and necessary interactions with other couriers and customers. DeliveryBench instantiates this setting in procedurally generated 3D cities with diverse road networks, buildings, functional locations, transportation modes, and realistic resource dynamics, enabling systematic evaluation of constraint-aware, long-horizon planning. We benchmark a range of VLM-based agents across nine cities and compare them with human players. Our results reveal a substantial performance gap to humans, and find that these agents are short-sighted and frequently break basic commonsense constraints. Additionally, we observe distinct personalities across models (e.g., adventurous GPT-5 vs. conservative Claude), highlighting both the brittleness and the diversity of current VLM-based embodied agents in realistic, constraint-dense environments. Our code, data, and benchmark are available at https://deliverybench.github.io.
Planning for an upcoming project iteration (sprint) is one of the key activities in Scrum planning. In this paper, we present our work in progress on exploring the applicability of Large Language Models (LLMs) for solving this problem. We conducted case studies with manually created data sets to investigate the applicability of OpenAI models for supporting the sprint planning activities. In our experiments, we applied three models provided OpenAI: GPT-3.5 Turbo, GPT-4.0 Turbo, and Val. The experiments demonstrated that the results produced by the models aren't of acceptable quality for direct use in Scrum projects.
We present ChronoDreamer, an action-conditioned world model for contact-rich robotic manipulation. Given a history of egocentric RGB frames, contact maps, actions, and joint states, ChronoDreamer predicts future video frames, contact distributions, and joint angles via a spatial-temporal transformer trained with MaskGIT-style masked prediction. Contact is encoded as depth-weighted Gaussian splat images that render 3D forces into a camera-aligned format suitable for vision backbones. At inference, predicted rollouts are evaluated by a vision-language model that reasons about collision likelihood, enabling rejection sampling of unsafe actions before execution. We train and evaluate on DreamerBench, a simulation dataset generated with Project Chrono that provides synchronized RGB, contact splat, proprioception, and physics annotations across rigid and deformable object scenarios. Qualitative results demonstrate that the model preserves spatial coherence during non-contact motion and generates plausible contact predictions, while the LLM-based judge distinguishes collision from non-collision trajectories.
Mixture-of-experts (MoE) architectures used in large language models (LLMs) achieve state-of-the-art performance across diverse tasks yet face practical challenges such as deployment complexity and low activation efficiency. Expert pruning has thus emerged as a promising solution to reduce computational overhead and simplify the deployment of MoE models. However, existing expert pruning approaches conventionally rely on local importance metrics and often apply uniform layer-wise pruning, leveraging only partial evaluation signals and overlooking the heterogeneous contributions of experts across layers. To address these limitations, we propose an expert pruning approach based on the trajectory of activated experts across layers, which treats MoE as a weighted computation graph and casts expert selection as a global optimal path planning problem. Within this framework, we integrate complementary importance signals from reconstruction error, routing probabilities, and activation strength at the trajectory level, which naturally yields non-uniform expert retention across layers. Experiments show that our approach achieves superior pruning performance on nearly all tasks compared with most existing approaches.
Manufacturing planners face complex operational challenges that require seamless collaboration between human expertise and intelligent systems to achieve optimal performance in modern production environments. Traditional approaches to analyzing simulation-based manufacturing data often create barriers between human decision-makers and critical operational insights, limiting effective partnership in manufacturing planning. Our framework establishes a collaborative intelligence system integrating Knowledge Graphs and Large Language Model-based agents to bridge this gap, empowering manufacturing professionals through natural language interfaces for complex operational analysis. The system transforms simulation data into semantically rich representations, enabling planners to interact naturally with operational insights without specialized expertise. A collaborative LLM agent works alongside human decision-makers, employing iterative reasoning that mirrors human analytical thinking while generating precise queries for knowledge extraction and providing transparent validation. This partnership approach to manufacturing bottleneck identification, validated through operational scenarios, demonstrates enhanced performance while maintaining human oversight and decision authority. For operational inquiries, the system achieves near-perfect accuracy through natural language interaction. For investigative scenarios requiring collaborative analysis, we demonstrate the framework's effectiveness in supporting human experts to uncover interconnected operational issues that enhance understanding and decision-making. This work advances collaborative manufacturing by creating intuitive methods for actionable insights, reducing cognitive load while amplifying human analytical capabilities in evolving manufacturing ecosystems.
Trajectory planning is a fundamental yet challenging component of autonomous driving. End-to-end planners frequently falter under adverse weather, unpredictable human behavior, or complex road layouts, primarily because they lack strong generalization or few-shot capabilities beyond their training data. We propose LLaViDA, a Large Language Vision Driving Assistant that leverages a Vision-Language Model (VLM) for object motion prediction, semantic grounding, and chain-of-thought reasoning for trajectory planning in autonomous driving. A two-stage training pipeline--supervised fine-tuning followed by Trajectory Preference Optimization (TPO)--enhances scene understanding and trajectory planning by injecting regression-based supervision, produces a powerful "VLM Trajectory Planner for Autonomous Driving." On the NuScenes benchmark, LLaViDA surpasses state-of-the-art end-to-end and other recent VLM/LLM-based baselines in open-loop trajectory planning task, achieving an average L2 trajectory error of 0.31 m and a collision rate of 0.10% on the NuScenes test set. The code for this paper is available at GitHub.
Generalist robot learning remains constrained by data: large-scale, diverse, and high-quality interaction data are expensive to collect in the real world. While simulation has become a promising way for scaling up data collection, the related tasks, including simulation task design, task-aware scene generation, expert demonstration synthesis, and sim-to-real transfer, still demand substantial human effort. We present AnyTask, an automated framework that pairs massively parallel GPU simulation with foundation models to design diverse manipulation tasks and synthesize robot data. We introduce three AnyTask agents for generating expert demonstrations aiming to solve as many tasks as possible: 1) ViPR, a novel task and motion planning agent with VLM-in-the-loop Parallel Refinement; 2) ViPR-Eureka, a reinforcement learning agent with generated dense rewards and LLM-guided contact sampling; 3) ViPR-RL, a hybrid planning and learning approach that jointly produces high-quality demonstrations with only sparse rewards. We train behavior cloning policies on generated data, validate them in simulation, and deploy them directly on real robot hardware. The policies generalize to novel object poses, achieving 44% average success across a suite of real-world pick-and-place, drawer opening, contact-rich pushing, and long-horizon manipulation tasks. Our project website is at https://anytask.rai-inst.com .
Visual navigation is a fundamental capability for autonomous home-assistance robots, enabling long-horizon tasks such as object search. While recent methods have leveraged Large Language Models (LLMs) to incorporate commonsense reasoning and improve exploration efficiency, their planning remains constrained by textual representations, which cannot adequately capture spatial occupancy or scene geometry--critical factors for navigation decisions. We explore whether Vision-Language Models (VLMs) can achieve mapless visual navigation using only onboard RGB/RGB-D streams, unlocking their potential for spatial perception and planning. We achieve this through an imagination-powered navigation framework, ImagineNav++, which imagines future observation images from candidate robot views and translates navigation planning into a simple best-view image selection problem for VLMs. First, a future-view imagination module distills human navigation preferences to generate semantically meaningful viewpoints with high exploration potential. These imagined views then serve as visual prompts for the VLM to identify the most informative viewpoint. To maintain spatial consistency, we develop a selective foveation memory mechanism, which hierarchically integrates keyframe observations via a sparse-to-dense framework, constructing a compact yet comprehensive memory for long-term spatial reasoning. This approach transforms goal-oriented navigation into a series of tractable point-goal navigation tasks. Extensive experiments on open-vocabulary object and instance navigation benchmarks show that ImagineNav++ achieves SOTA performance in mapless settings, even surpassing most map-based methods, highlighting the importance of scene imagination and memory in VLM-based spatial reasoning.
Evaluating user-facing AI applications remains a central challenge, especially in open-ended domains such as travel planning, clinical note generation, or dialogue. The gold standard is user feedback (e.g., thumbs up/down) or behavioral signals (e.g., retention), but these are often scarce in prototypes and research projects, or too-slow to use for system optimization. We present AutoMetrics, a framework for synthesizing evaluation metrics under low-data constraints. AutoMetrics combines retrieval from MetricBank, a collection of 48 metrics we curate, with automatically generated LLM-as-a-Judge criteria informed by lightweight human feedback. These metrics are composed via regression to maximize correlation with human signal. AutoMetrics takes you from expensive measures to interpretable automatic metrics. Across 5 diverse tasks, AutoMetrics improves Kendall correlation with human ratings by up to 33.4% over LLM-as-a-Judge while requiring fewer than 100 feedback points. We show that AutoMetrics can be used as a proxy reward to equal effect as a verifiable reward. We release the full AutoMetrics toolkit and MetricBank to accelerate adaptive evaluation of LLM applications.
Real-time sequential control agents are often bottlenecked by inference latency. Even modest per-step planning delays can destabilize control and degrade overall performance. We propose a speculation-and-correction framework that adapts the predict-then-verify philosophy of speculative execution to model-based control with TD-MPC2. At each step, a pretrained world model and latent-space MPC planner generate a short-horizon action queue together with predicted latent rollouts, allowing the agent to execute multiple planned actions without immediate replanning. When a new observation arrives, the system measures the mismatch between the encoded real latent state and the queued predicted latent. For small to moderate mismatch, a lightweight learned corrector applies a residual update to the speculative action, distilled offline from a replanning teacher. For large mismatch, the agent safely falls back to full replanning and clears stale action queues. We study both a gated two-tower MLP corrector and a temporal Transformer corrector to address local errors and systematic drift. Experiments on the DMC Humanoid-Walk task show that our method reduces the number of planning inferences from 500 to 282, improves end-to-end step latency by 25 percent, and maintains strong control performance with only a 7.1 percent return reduction. Ablation results demonstrate that speculative execution without correction is unreliable over longer horizons, highlighting the necessity of mismatch-aware correction for robust latency reduction.
Structured generation for LLM tool use highlights the value of compact DSL intermediate representations (IRs) that can be emitted directly and parsed deterministically. This paper introduces axial grammar: linear token sequences that recover multi-dimensional structure from the placement of rank-specific separator tokens. A single left-to-right pass assigns each token a coordinate in an n-dimensional grid, enabling deterministic parsing without parentheses or clause-heavy surface syntax. This grammar is instantiated in Memelang, a compact query language intended as an LLM-emittable IR whose fixed coordinate roles map directly to table/column/value slots. Memelang supports coordinate-stable relative references, parse-time variable binding, and implicit context carry-forward to reduce repetition in LLM-produced queries. It also encodes grouping, aggregation, and ordering via inline tags on value terms, allowing grouped execution plans to be derived in one streaming pass over the coordinate-indexed representation. Provided are a reference lexer/parser and a compiler that emits parameterized PostgreSQL SQL (optionally using pgvector operators).
Simulation is essential for developing robotic manipulation systems, particularly for task and motion planning (TAMP), where symbolic reasoning interfaces with geometric, kinematic, and physics-based execution. Recent advances in Large Language Models (LLMs) enable robots to generate symbolic plans from natural language, yet executing these plans in simulation often requires robot-specific engineering or planner-dependent integration. In this work, we present a unified pipeline that connects an LLM-based symbolic planner with the Kautham motion planning framework to achieve generalizable, robot-agnostic symbolic-to-geometric manipulation. Kautham provides ROS-compatible support for a wide range of industrial manipulators and offers geometric, kinodynamic, physics-driven, and constraint-based motion planning under a single interface. Our system converts language instructions into symbolic actions and computes and executes collision-free trajectories using any of Kautham's planners without additional coding. The result is a flexible and scalable tool for language-driven TAMP that is generalized across robots, planning modalities, and manipulation tasks.
Deploying accurate Text-to-SQL systems at the enterprise level faces a difficult trilemma involving cost, security and performance. Current solutions force enterprises to choose between expensive, proprietary Large Language Models (LLMs) and low-performing Small Language Models (SLMs). Efforts to improve SLMs often rely on distilling reasoning from large LLMs using unstructured Chain-of-Thought (CoT) traces, a process that remains inherently ambiguous. Instead, we hypothesize that a formal, structured reasoning representation provides a clearer, more reliable teaching signal, as the Text-to-SQL task requires explicit and precise logical steps. To evaluate this hypothesis, we propose Struct-SQL, a novel Knowledge Distillation (KD) framework that trains an SLM to emulate a powerful large LLM. Consequently, we adopt a query execution plan as a formal blueprint to derive this structured reasoning. Our SLM, distilled with structured CoT, achieves an absolute improvement of 8.1% over an unstructured CoT distillation baseline. A detailed error analysis reveals that a key factor in this gain is a marked reduction in syntactic errors. This demonstrates that teaching a model to reason using a structured logical blueprint is beneficial for reliable SQL generation in SLMs.
Function calling agents powered by Large Language Models (LLMs) select external tools to automate complex tasks. On-device agents typically use a retrieval module to select relevant tools, improving performance and reducing context length. However, existing retrieval methods rely on static and limited inputs, failing to capture multi-step tool dependencies and evolving task context. This limitation often introduces irrelevant tools that mislead the agent, degrading efficiency and accuracy. We propose Dynamic Tool Dependency Retrieval (DTDR), a lightweight retrieval method that conditions on both the initial query and the evolving execution context. DTDR models tool dependencies from function calling demonstrations, enabling adaptive retrieval as plans unfold. We benchmark DTDR against state-of-the-art retrieval methods across multiple datasets and LLM backbones, evaluating retrieval precision, downstream task accuracy, and computational efficiency. Additionally, we explore strategies to integrate retrieved tools into prompts. Our results show that dynamic tool retrieval improves function calling success rates between $23\%$ and $104\%$ compared to state-of-the-art static retrievers.
Autonomous driving has long relied on modular "Perception-Decision-Action" pipelines, where hand-crafted interfaces and rule-based components often break down in complex or long-tailed scenarios. Their cascaded design further propagates perception errors, degrading downstream planning and control. Vision-Action (VA) models address some limitations by learning direct mappings from visual inputs to actions, but they remain opaque, sensitive to distribution shifts, and lack structured reasoning or instruction-following capabilities. Recent progress in Large Language Models (LLMs) and multimodal learning has motivated the emergence of Vision-Language-Action (VLA) frameworks, which integrate perception with language-grounded decision making. By unifying visual understanding, linguistic reasoning, and actionable outputs, VLAs offer a pathway toward more interpretable, generalizable, and human-aligned driving policies. This work provides a structured characterization of the emerging VLA landscape for autonomous driving. We trace the evolution from early VA approaches to modern VLA frameworks and organize existing methods into two principal paradigms: End-to-End VLA, which integrates perception, reasoning, and planning within a single model, and Dual-System VLA, which separates slow deliberation (via VLMs) from fast, safety-critical execution (via planners). Within these paradigms, we further distinguish subclasses such as textual vs. numerical action generators and explicit vs. implicit guidance mechanisms. We also summarize representative datasets and benchmarks for evaluating VLA-based driving systems and highlight key challenges and open directions, including robustness, interpretability, and instruction fidelity. Overall, this work aims to establish a coherent foundation for advancing human-compatible autonomous driving systems.
The rapidly growing demand for high-quality data in Large Language Models (LLMs) has intensified the need for scalable, reliable, and semantically rich data preparation pipelines. However, current practices remain dominated by ad-hoc scripts and loosely specified workflows, which lack principled abstractions, hinder reproducibility, and offer limited support for model-in-the-loop data generation. To address these challenges, we present DataFlow, a unified and extensible LLM-driven data preparation framework. DataFlow is designed with system-level abstractions that enable modular, reusable, and composable data transformations, and provides a PyTorch-style pipeline construction API for building debuggable and optimizable dataflows. The framework consists of nearly 200 reusable operators and six domain-general pipelines spanning text, mathematical reasoning, code, Text-to-SQL, agentic RAG, and large-scale knowledge extraction. To further improve usability, we introduce DataFlow-Agent, which automatically translates natural-language specifications into executable pipelines via operator synthesis, pipeline planning, and iterative verification. Across six representative use cases, DataFlow consistently improves downstream LLM performance. Our math, code, and text pipelines outperform curated human datasets and specialized synthetic baselines, achieving up to +3\% execution accuracy in Text-to-SQL over SynSQL, +7\% average improvements on code benchmarks, and 1--3 point gains on MATH, GSM8K, and AIME. Moreover, a unified 10K-sample dataset produced by DataFlow enables base models to surpass counterparts trained on 1M Infinity-Instruct data. These results demonstrate that DataFlow provides a practical and high-performance substrate for reliable, reproducible, and scalable LLM data preparation, and establishes a system-level foundation for future data-centric AI development.
Large Language Model (LLM) agents are increasingly deployed in complex, multi-step workflows involving planning, tool use, reflection, and interaction with external knowledge systems. These workflows generate rapidly expanding contexts that must be curated, transformed, and compressed to maintain fidelity, avoid attention dilution, and reduce inference cost. Prior work on summarization and query-aware compression largely ignores the multi-step, plan-aware nature of agentic reasoning. In this work, we introduce PAACE (Plan-Aware Automated Context Engineering), a unified framework for optimizing the evolving state of LLM agents through next-k-task relevance modeling, plan-structure analysis, instruction co-refinement, and function-preserving compression. PAACE comprises (1) PAACE-Syn, a large-scale generator of synthetic agent workflows annotated with stepwise compression supervision, and (2) PAACE-FT, a family of distilled, plan-aware compressors trained from successful teacher demonstrations. Experiments on long-horizon benchmarks (AppWorld, OfficeBench, and 8-Objective QA) demonstrate that PAACE consistently improves agent correctness while substantially reducing context load. On AppWorld, PAACE achieves higher accuracy than all baselines while lowering peak context and cumulative dependency. On OfficeBench and multi-hop QA, PAACE improves both accuracy and F1, achieving fewer steps, lower peak tokens, and reduced attention dependency. Distilled PAACE-FT retains 97 percent of the teacher's performance while reducing inference cost by over an order of magnitude, enabling practical deployment of plan-aware compression with compact models.
Computer-aided synthesis planning (CASP) has long been envisioned as a complementary tool for synthetic chemists. However, existing frameworks often lack mechanisms to allow interaction with human experts, limiting their ability to integrate chemists' insights. In this work, we introduce Synthelite, a synthesis planning framework that uses large language models (LLMs) to directly propose retrosynthetic transformations. Synthelite can generate end-to-end synthesis routes by harnessing the intrinsic chemical knowledge and reasoning capabilities of LLMs, while allowing expert intervention through natural language prompts. Our experiments demonstrate that Synthelite can flexibly adapt its planning trajectory to diverse user-specified constraints, achieving up to 95\% success rates in both strategy-constrained and starting-material-constrained synthesis tasks. Additionally, Synthelite exhibits the ability to account for chemical feasibility during route design. We envision Synthelite to be both a useful tool and a step toward a paradigm where LLMs are the central orchestrators of synthesis planning.
Recent multimodal large language models (MLLMs) such as GPT-4o and Qwen3-Omni show strong perception but struggle in multi-speaker, dialogue-centric settings that demand agentic reasoning tracking who speaks, maintaining roles, and grounding events across time. These scenarios are central to multimodal audio-video understanding, where models must jointly reason over audio and visual streams in applications such as conversational video assistants and meeting analytics. We introduce AMUSE, a benchmark designed around tasks that are inherently agentic, requiring models to decompose complex audio-visual interactions into planning, grounding, and reflection steps. It evaluates MLLMs across three modes zero-shot, guided, and agentic and six task families, including spatio-temporal speaker grounding and multimodal dialogue summarization. Across all modes, current models exhibit weak multi-speaker reasoning and inconsistent behavior under both non-agentic and agentic evaluation. Motivated by the inherently agentic nature of these tasks and recent advances in LLM agents, we propose RAFT, a data-efficient agentic alignment framework that integrates reward optimization with intrinsic multimodal self-evaluation as reward and selective parameter adaptation for data and parameter efficient updates. Using RAFT, we achieve up to 39.52\% relative improvement in accuracy on our benchmark. Together, AMUSE and RAFT provide a practical platform for examining agentic reasoning in multimodal models and improving their capabilities.
Solving Partial Differential Equations (PDEs) is a cornerstone of engineering and scientific research. Traditional methods for PDE solving are cumbersome, relying on manual setup and domain expertise. While Physics-Informed Neural Network (PINNs) introduced end-to-end neural network-based solutions, and frameworks like DeepXDE further enhanced automation, these approaches still depend on expert knowledge and lack full autonomy. In this work, we frame PDE solving as tool invocation via LLM-driven agents and introduce PDE-Agent, the first toolchain-augmented multi-agent collaboration framework, inheriting the reasoning capacity of LLMs and the controllability of external tools and enabling automated PDE solving from natural language descriptions. PDE-Agent leverages the strengths of multi-agent and multi-tool collaboration through two key innovations: (1) A Prog-Act framework with graph memory for multi-agent collaboration, which enables effective dynamic planning and error correction via dual-loop mechanisms (localized fixes and global revisions). (2) A Resource-Pool integrated with a tool-parameter separation mechanism for multi-tool collaboration. This centralizes the management of runtime artifacts and resolves inter-tool dependency gaps in existing frameworks. To validate and evaluate this new paradigm for PDE solving , we develop PDE-Bench, a multi-type PDE Benchmark for agent-based tool collaborative solving, and propose multi-level metrics for assessing tool coordination. Evaluations verify that PDE-Agent exhibits superior applicability and performance in complex multi-step, cross-step dependent tasks. This new paradigm of toolchain-augmented multi-agent PDE solving will further advance future developments in automated scientific computing. Our source code and dataset will be made publicly available.
The rapid evolution of the Web toward an agent-centric paradigm, driven by large language models (LLMs), has enabled autonomous agents to reason, plan, and interact in complex decentralized environments. However, the openness and heterogeneity of LLM-based multi-agent systems also amplify the risks of deception, fraud, and misinformation, posing severe challenges to trust establishment and system robustness. To address this issue, we propose Ev-Trust, a strategy-equilibrium trust mechanism grounded in evolutionary game theory. This mechanism integrates direct trust, indirect trust, and expected revenue into a dynamic feedback structure that guides agents' behavioral evolution toward equilibria. Within a decentralized "Request-Response-Payment-Evaluation" service framework, Ev-Trust enables agents to adaptively adjust strategies, naturally excluding malicious participants while reinforcing high-quality collaboration. Furthermore, our theoretical derivation based on replicator dynamics equations proves the existence and stability of local evolutionary equilibria. Experimental results indicate that our approach effectively reflects agent trustworthiness in LLM-driven open service interaction scenarios, reduces malicious strategies, and increases collective revenue. We hope Ev-Trust can provide a new perspective on trust modeling for the agentic service web in group evolutionary game scenarios.