Entity alignment (EA) aims to identify entities across different knowledge graphs (KGs) that refer to the same real-world object and plays a critical role in knowledge fusion and integration. Traditional EA methods mainly rely on knowledge representation learning, but their performance is often limited under noisy or sparsely supervised scenarios. Recently, large language models (LLMs) have been introduced to EA and achieved notable improvements by leveraging rich semantic knowledge. However, existing LLM-based EA approaches typically treat LLMs as black-box decision makers, resulting in limited interpretability, and the direct use of large-scale triples substantially increases inference cost. To address these challenges, we propose \textbf{EA-Agent}, a reasoning-driven agent for EA. EA-Agent formulates EA as a structured reasoning process with multi-step planning and execution, enabling interpretable alignment decisions. Within this process, it introduces attribute and relation triple selectors to filter redundant triples before feeding them into the LLM, effectively addressing efficiency challenges. Experimental results on three benchmark datasets demonstrate that EA-Agent consistently outperforms existing EA methods and achieves state-of-the-art performance. The source code is available at https://github.com/YXNan0110/EA-Agent.
The dominant paradigm for building LLM based agents is the Agent Loop, an iterative cycle where a single language model decides what to do next by reading an ever growing context window. This paradigm has three structural weaknesses: implicit dependencies between steps, unbounded recovery loops, and mutable execution history that complicates debugging. We characterize the Agent Loop as a single ready unit scheduler: at any moment, at most one executable unit is active, and the choice of which unit to activate comes from opaque LLM inference rather than an inspectable policy. This perspective places Agent Loops and graph based execution engines on a single semantic continuum. We propose SGH, Structured Graph Harness, which lifts control flow from implicit context into an explicit static DAG. SGH makes three commitments: execution plans are immutable within a plan version, planning execution and recovery are separated into three layers, and recovery follows a strict escalation protocol. These choices trade some expressiveness for controllability, verifiability, and implementability. Our contributions are fourfold: a scheduler unified framework that applies classical scheduling theory to LLM agent execution and identifies challenges introduced by non deterministic LLM nodes; a trade off analysis of controllability, expressiveness, and implementability across 70 surveyed systems; a formal specification including a node state machine with termination and soundness guarantees; and an attributable experimental framework with a seven group design for future validation. This is a position paper and design proposal. We provide a theoretical framework, design analysis, and experimental protocol, not a production implementation or empirical results.
LLM agents now perform strongly in software engineering, deep research, GUI automation, and various other applications, while recent agent scaffolds and models are increasingly integrating these capabilities into unified systems. Yet, most evaluations still test these capabilities in isolation, which leaves a gap for more diverse use cases that require agents to combine different capabilities. We introduce CocoaBench, a benchmark for unified digital agents built from human-designed, long-horizon tasks that require flexible composition of vision, search, and coding. Tasks are specified only by an instruction and an automatic evaluation function over the final output, enabling reliable and scalable evaluation across diverse agent infrastructures. We also present CocoaAgent, a lightweight shared scaffold for controlled comparison across model backbones. Experiments show that current agents remain far from reliable on CocoaBench, with the best evaluated system achieving only 45.1% success rate. Our analysis further points to substantial room for improvement in reasoning and planning, tool use and execution, and visual grounding.
Semiconductor supply chains face unprecedented resilience challenges amidst global geopolitical turbulence. Conventional Large Language Model (LLM) planners, when confronting such non-stationary "Policy Black Swan" events, frequently suffer from Decision Paralysis or a severe Grounding Gap due to the absence of physical environmental modeling. This paper introduces ReflectiChain, a cognitive agentic framework tailored for resilient macroeconomic supply chain planning. The core innovation lies in the integration of Latent Trajectory Rehearsal powered by a generative world model, which couples reflection-in-action (System 2 deliberation) with delayed reflection-on-action. Furthermore, we leverage a Retrospective Agentic RL mechanism to enable autonomous policy evolution during the deployment phase (test-time). Evaluations conducted on our high-fidelity benchmark, Semi-Sim, demonstrate that under extreme scenarios such as export bans and material shortages, ReflectiChain achieves a 250% improvement in average step rewards over the strongest LLM baselines. It successfully restores the Operability Ratio (OR) from a deficient 13.3% to over 88.5% while ensuring robust gradient convergence. Ablation studies further underscore that the synergy between physical grounding constraints and double-loop learning is fundamental to bridging the gap between semantic reasoning and physical reality for long-horizon strategic planning.
Agentic Web is an emerging paradigm where autonomous agents help users use online information. As the paradigm develops, content providers are also deploying agents to manage their data and serve it through controlled interfaces. This shift moves information access from centralized retrieval to decentralized coordination. To study this setting, we introduce AgentWebBench, a benchmark that evaluates how well a user agent synthesizes answers by interacting with website-specific content agents. We evaluate four tasks that cover common web information needs, spanning ranked retrieval (web search, web recommendation) and open-ended synthesis (question answering, deep research). Across seven advanced LLMs and three coordination strategies, multi-agent coordination generally lags behind centralized retrieval as expected, because user agent cannot directly access the corpus, but the gap shrinks with model scale and can even outperform centralized retrieval on question answering. This benchmark also enables us to study properties of the emerging paradigm of the digital world. We find that decentralized access concentrates traffic toward a small set of websites, test time scaling improves both interaction reliability and task performance, and strong results require sufficient interactions guided by careful planning. Finally, our failure analysis suggests that user agents need better planning and answer synthesis, while content agents need more reliable retrieval and evidence quality. Code, data, and APIs are released on https://github.com/cxcscmu/AgentWebBench.
Recent advances in large language models (LLMs) provide robots with contextual reasoning abilities to comprehend human instructions. Yet, current LLM-enabled robots typically depend on cloud-based models or high-performance computing infrastructure, which limit their deployment on robots under unreliable internet environments or with constrained computational resources, such as UAVs and small ground vehicles. Thus, deploying fine-tuned small language models (SLMs) that support onboard deployment offers a promising alternative. This paper introduces Ro-SLM, a framework that enables reliable SLM-driven robot operation by distilling LLMs' knowledge and reasoning. Ro-SLM starts from dataset synthesis by leveraging LLMs to generate diverse task instructions, produce corresponding ground truth code with minimal human assistance, and augment instructions into real-world application scenarios. Ro-SLM is then fine-tuned with the dataset, in which LLM serves as a reward function to guide the training. Extensive experiments on UAV operation tasks demonstrate that Ro-SLM improves the performance of SLM from being incapable of supporting robotic task planning and code generation to achieving performance that approaches LLM.
Enabling large language models to scale and reliably use hundreds of tools is critical for real-world applications, yet challenging due to the inefficiency and error accumulation inherent in flat tool-calling architectures. To address this, we propose Hybrid Toolset Agentization & Adaptation (HTAA), a hierarchical framework for scalable tool-use planning. We propose a novel toolset agentization paradigm, which encapsulates frequently co-used tools into specialized agent tools, thereby reducing the planner's action space and mitigating redundancy. To ensure effective coordination, we design Asymmetric Planner Adaptation, a trajectory-based training paradigm that aligns the high-level planner with agent tools via backward reconstruction and forward refinement. To validate the performance of HTAA, we conduct experiments on a real-world internal dataset, InfoVerify, based on the POI validation workflow of China's largest online large-scale ride-hailing platform, featuring long-horizon executable tool trajectories. Experiments on InfoVerify and widely-used benchmarks show that HTAA consistently achieves higher task success rates, requires short tool calling trajectories, and significantly reduces context overhead compared to strong baselines. Furthermore, in a production deployment, HTAA substantially reduces manual validation effort and operational cost, demonstrating its practical efficacy.
Foundation models have shown remarkable performance across diverse tasks, yet their ability to construct internal spatial world models for reasoning and planning remains unclear. We systematically evaluate the spatial understanding of large language models through maze tasks, a controlled testing context requiring multi-step planning and spatial abstraction. Across comprehensive experiments with Gemini-2.5-Flash, GPT-5-mini, Claude-Haiku-4.5, and DeepSeek-Chat, we uncover significant discrepancies in spatial reasoning that challenge assumptions about LLM planning capabilities. Using chain-of-thought prompting, Gemini achieves 80-86% accuracy on smaller mazes (5x5 to 7x7 grids) with tokenized adjacency representations, but performance collapses to 16-34% with visual grid formats, which is a 2-5x difference, suggesting representation-dependent rather than format-invariant spatial reasoning. We further probe spatial understanding through sequential proximity questions and compositional distance comparisons. Despite achieving 96-99% semantic coverage in reasoning traces, models fail to leverage this understanding for consistent spatial computations, indicating that they treat each question independently rather than building cumulative spatial knowledge. Our findings based on the maze-solving tasks suggest that LLMs do not develop robust spatial world models, but rather exhibit representation-specific and prompting-dependent reasoning that succeeds only under narrow conditions. These results have critical implications for deploying foundation models in applications requiring spatial abstraction.
Although Large Language Models (LLMs) demonstrate proficiency in knowledge-intensive tasks, current interfaces frequently precipitate cognitive misalignment by failing to externalize users' underlying reasoning structures. Existing tools typically represent intent as "flat lists," thereby disregarding the causal dependencies and revisable assumptions inherent in human decision-making. We introduce CogInstrument, a system that represents user reasoning through cognitive motifs-compositional, revisable units comprising concepts linked by causal dependencies. CogInstrument extracts these motifs from natural language interactions and renders them as editable graphical structures to facilitate bidirectional alignment. This structural externalization enables both the user and the LLM to inspect, negotiate, and reconcile reasoning processes iteratively. A within-subjects study (N=12) demonstrates that CogInstrument explicitly surfaces implicit reasoning structures, facilitating more targeted revision and reusability over conventional LLM-based dialogue interfaces. By enabling users to verify the logical grounding of LLM outputs, CogInstrument significantly enhances user agency, trust, and structural control over the collaboration. This work formalizes cognitive motifs as a fundamental unit for human-LLM alignment, providing a novel framework for achieving structured, reasoning-based human-AI collaboration.
Modeling household-level trip generation is fundamental to accurate demand forecasting, traffic flow estimation, and urban system planning. Existing studies were mostly based on classical machine learning models with limited predictive capability, while recent LLM-based approaches have yet to incorporate behavioral theory or intra-household interaction dynamics, both of which are critical for modeling realistic collective travel decisions. To address these limitations, we propose a novel LLM-based framework, named Persona-Enriched Multi-Agent Negotiation for Travel (PEMANT), which first integrates behavioral theory for individualized persona modeling and then conducts household-level trip planning negotiations via a structured multi-agent conversation. Specifically, PEMANT transforms static sociodemographic attributes into coherent narrative profiles that explicitly encode household-level attitudes, subjective norms, and perceived behavioral controls, following our proposed Household-Aware Chain-of-Planned-Behavior (HA-CoPB) framework. Building on these theory-grounded personas, PEMANT captures real-world household decision negotiation via a structured two-phase multi-agent conversation framework with a novel persona-alignment control mechanism. Evaluated on both national and regional household travel survey datasets, PEMANT consistently outperforms state-of-the-art benchmarks across datasets.
Existing multi-agent video generation systems use LLM agents to orchestrate neural video generators, producing visually impressive but semantically unreliable outputs with no ground truth annotations. We present an agentic system that inverts this paradigm: instead of generating pixels, the LLM constructs a formal Graph of Events in Space and Time (GEST) -- a structured specification of actors, actions, objects, and temporal constraints -- which is then executed deterministically in a 3D game engine. A staged LLM refinement pipeline fails entirely at this task (0 of 50 attempts produce an executable specification), motivating a fundamentally different architecture based on a separation of concerns: the LLM handles narrative planning through natural language reasoning, while a programmatic state backend enforces all simulator constraints through validated tool calls, guaranteeing that every generated specification is executable by construction. The system uses a hierarchical two-agent architecture -- a Director that plans the story and a Scene Builder that constructs individual scenes through a round-based state machine -- with dedicated Relation Subagents that populate the logical and semantic edge types of the GEST formalism that procedural generation leaves empty, making this the first approach to exercise the full expressive capacity of the representation. We evaluate in two stages: autonomous generation against procedural baselines via a 3-model LLM jury, where agentic narratives win 79% of text and 74% of video comparisons; and seeded generation where the same text is given to our system, VEO 3.1, and WAN 2.2, with human annotations showing engine-generated videos substantially outperform neural generators on physical validity (58% vs 25% and 20%) and semantic alignment (3.75/5 vs 2.33 and 1.50).
LLM-based coding agents are increasingly used to generate code, tests, and documentation. Still, their outputs can be plausible yet misaligned with developer intent and provide limited evidence for review in evolving projects. This limits our understanding of how to structure LLM pair-programming workflows so that artifacts remain reliable, auditable, and maintainable over time. To address this gap, this doctoral research proposes a systematic study of multi-agent LLM pair programming that externalizes intent and uses development tools for iterative validation. The plan includes three studies: translating informal problem statements into standards aligned requirements and formal specifications; refining tests and implementations using automated feedback, such as solver-backed counterexamples; and supporting maintenance tasks, including refactoring, API migrations, and documentation updates, while preserving validated behavior. The expected outcome is a clearer understanding of when multi-agent workflows increase trust, along with practical guidance for building reliable programming assistants for real-world development.
Large Language Model (LLM) agents are increasingly integrated into critical systems, leveraging external tools to interact with the real world. However, this capability exposes them to Indirect Prompt Injection (IPI), where attackers embed malicious instructions into retrieved content to manipulate the agent into executing unauthorized or unintended actions. Existing defenses predominantly focus on the pre-processing stage, neglecting the monitoring of the model's actual behavior. In this paper, we propose PlanGuard, a training-free defense framework based on the principle of Context Isolation. Unlike prior methods, PlanGuard introduces an isolated Planner that generates a reference set of valid actions derived solely from user instructions. In addition, we design a Hierarchical Verification Mechanism that first enforces strict hard constraints to block unauthorized tool invocations, and subsequently employs an Intent Verifier to validate whether parameter deviations are benign formatting variances or malicious hijacking. Experiments on the InjecAgent benchmark demonstrate that PlanGuard effectively neutralizes these attacks, reducing the Attack Success Rate (ASR) from 72.8% to 0%, while maintaining an acceptable False Positive Rate of 1.49%. Furthermore, our method is model-agnostic and highly compatible.
Microreboot enables fast recovery by restarting only the failing component, but in modern microservices naive restarts are unsafe: dense dependencies mean rebooting one service can disrupt many callers. Autonomous remediation agents compound this by actuating raw infrastructure commands without safety guarantees. We make microreboot practical by separating planning from actuation: a three-agent architecture (diagnosis, planning, verification) proposes typed remediation plans over a seven-action ISA with explicit side-effect semantics, and a small microkernel validates and executes each plan transactionally. Agents are explicitly untrusted; safety derives from the ISA and microkernel. To determine where restart is safe, we infer recovery boundaries online from distributed traces, computing minimal restart groups and ordering constraints. On industrial traces (Alibaba, Meta) and DeathStarBench with fault injection, recovery-group inference runs in 21 ms at P99; typed actuation reduces agent-caused harm by 95% in simulation and achieves 0% harm online. The primary value is safety, not speed: LLM inference overhead increases TTR for services with fast auto-restart.
Recent database systems have introduced semantic operators that leverage large language models (LLMs) to filter, join, and project over structured data using natural language predicates. In practice, these operators are combined with traditional relational operators, e.g., equi-joins, producing hybrid query plans whose execution cost depends on both expensive LLM calls and conventional database processing. A key optimization question is where to place each semantic operator relative to the relational operators in the plan: placing them earlier reduces the data that subsequent operators process, but requires more LLM calls; placing them later reduces LLM calls through deduplication, but forces relational operators to process larger intermediate data. Existing systems either ignore this placement question or apply simple heuristics without considering the full cost trade-off. We present Horrila, a plan-level optimizer for hybrid semantic-relational queries. Horrila reduces hybrid query planning to semantic filter placement via two equivalence-preserving rewrites. We prove that deferring all semantic filters to the latest possible position minimizes LLM invocations under function caching, but show that this can cause relational processing costs to dominate on complex multi-table queries. To balance LLM cost against relational cost, Horrila uses a dynamic-programming-based cost model that finds the placement minimizing their weighted sum. On 44 semantic SQL queries across five schemas and two benchmarks, Horrila achieves up to 1.5$\times$ speedup and 4.29$\times$ cost reduction while maintaining high output quality: an average F1 of 0.85 against the unoptimized baseline and 0.84 against human-annotated ground truth on SemBench. Overall, Horrila achieves a significant cost reduction while preserving the highest accuracy among six publicly available systems.
Large Language Models (LLMs) offer a promising interface for intent-driven control of autonomous cyber-physical systems, but their direct use in mission-critical Internet of Battlefield Things (IoBT) environments raises significant safety, reliability, and policy-compliance concerns. This paper presents a Policy-Aware Large Language Model Retrieval-Augmented Generation (referred as PA-LLM-RAG), an edge-deployed LLM orchestration framework for IoBT mission control that integrates retrieval-augmented reasoning and independent command verification. The proposed PA-LLM-RAG framework combines a lightweight retrieval module that grounds decisions in operational policies and telemetry with a locally hosted LLM for mission planning and a secondary JudgeLLM for validating user generated commands prior to execution. To evaluate PA-LLM-RAG, we implement a simulated IoBT environment using RoboDK and assess four open-source LLMs across controlled mission scenarios of increasing complexity, including baseline operations, threat detection, coverage recovery, multi-event coordination, and policy-violation requests. Experimental results demonstrate that the framework effectively detects policy-violating commands while maintaining low-latency response suitable for edge deployment. Gemma-2B achieving the highest overall reliability with 4.17 sec latency and 100% success rate. The findings highlight a clear tradeoff between reasoning capacity and responsiveness across models and show that combining deterministic safeguards with JudgeLLM verification significantly improves reliability in LLM-driven IoBT orchestration.
Ancient inscriptions, as repositories of cultural memory, have suffered from centuries of environmental and human-induced degradation. Restoring their intertwined visual and textual integrity poses one of the most demanding challenges in digital heritage preservation. However, existing AI-based approaches often rely on rigid pipelines, struggling to generalize across such complex and heterogeneous real-world degradations. Inspired by the skill-coordinated workflow of human epigraphers, we propose EpiAgent, an agent-centric system that formulates inscription restoration as a hierarchical planning problem. Following an Observe-Conceive-Execute-Reevaluate paradigm, an LLM-based central planner orchestrates collaboration among multimodal analysis, historical experience, specialized restoration tools, and iterative self-refinement. This agent-centric coordination enables a flexible and adaptive restoration process beyond conventional single-pass methods. Across real-world degraded inscriptions, EpiAgent achieves superior restoration quality and stronger generalization compared to existing methods. Our work marks an important step toward expert-level agent-driven restoration of cultural heritage. The code is available at https://github.com/blackprotoss/EpiAgent.
While Large Language Models (LLMs) excel in various general domains, they exhibit notable gaps in the highly specialized, knowledge-intensive, and legally regulated Chinese tax domain. Consequently, while tax-related benchmarks are gaining attention, many focus on isolated NLP tasks, neglecting real-world practical capabilities. To address this issue, we introduce TaxPraBen, the first dedicated benchmark for Chinese taxation practice. It combines 10 traditional application tasks, along with 3 pioneering real-world scenarios: tax risk prevention, tax inspection analysis, and tax strategy planning, sourced from 14 datasets totaling 7.3K instances. TaxPraBen features a scalable structured evaluation paradigm designed through process of "structured parsing-field alignment extraction-numerical and textual matching", enabling end-to-end tax practice assessment while being extensible to other domains. We evaluate 19 LLMs based on Bloom's taxonomy. The results indicate significant performance disparities: all closed-source large-parameter LLMs excel, and Chinese LLMs like Qwen2.5 generally exceed multilingual LLMs, while the YaYi2 LLM, fine-tuned with some tax data, shows only limited improvement. TaxPraBen serves as a vital resource for advancing evaluations of LLMs in practical applications.
Patient-clinician communication is an asymmetric-information problem: patients often do not disclose fears, misconceptions, or practical barriers unless clinicians elicit them skillfully. Effective medical dialogue therefore requires reasoning under partial observability: clinicians must elicit latent concerns, confirm them through interaction, and respond in ways that guide patients toward appropriate care. However, existing medical dialogue benchmarks largely sidestep this challenge by exposing hidden patient state, collapsing elicitation into extraction, or evaluating responses without modeling what remains hidden. We present MedConceal, a benchmark with an interactive patient simulator for evaluating hidden-concern reasoning in medical dialogue, comprising 300 curated cases and 600 clinician-LLM interactions. Built from clinician-answered online health discussions, each case pairing clinician-visible context with simulator-internal hidden concerns derived from prior literature and structured using an expert-developed taxonomy. The simulator withholds these concerns from the dialogue agent, tracks whether they have been revealed and addressed via theory-grounded turn-level communication signals, and is clinician-reviewed for clinical plausibility. This enables process-aware evaluation of both task success and the interaction process that leads to it. We study two abilities: confirmation, surfacing hidden concerns through multi-turn dialogue, and intervention, addressing the primary concern and guiding the patient toward a target plan. Results show that no single system dominates: frontier models lead on different confirmation metrics, while human clinicians (N=159) remain strongest on intervention success. Together, these results identify hidden-concern reasoning under partial observability as a key unresolved challenge for medical dialogue systems.
As large language model (LLM) agents become more prevalent in real world social settings, social intelligence will play an increasingly critical role. But social intelligence is still a poorly defined construct, for humans and artificial agents. We introduce a multiplayer arena of mixed cooperative and competitive social games to study LLM social intelligence. The controllability of LLM based agents enables systematic evaluation, which also supports broader inferences about social intelligence per se. We evaluated eight diverse LLMs (24B to 1T parameters) using a Communicate Predict Act (COMPACT) interaction protocol and fine grained probing of social dynamics. Elo style ratings reveal consistent performance differences across models, but this scalar measure provides only a partial characterization of social intelligence. To address this limitation, we analyze gameplay traces to extract sociocognitive metrics capturing action prediction, communicative influence, strategic reasoning, and tradeoffs under conflicting interests. These sociocognitive metrics exhibit strong intramodel consistency and they reliably predict pairwise agent advantage in game outcomes (AUC ROC = 0.82). Feature importance analysis indicates that surprisingly, influence, transparency, and adaptability are more predictive of success than Theory of Mind inference or deep planning. Together, our results advance a testable, multidimensional conception of social intelligence and provide empirical insights into the capacities that underpin it.
Recent years have seen remarkable progress in autonomous driving, yet generalization to long-tail and open-world scenarios remains a major bottleneck for large-scale deployment. To address this challenge, some works use LLMs and VLMs for vision-language understanding and reasoning, enabling vehicles to interpret rare and safety-critical situations when generating actions. Others study generative world models to capture the spatio-temporal evolution of driving scenes, allowing agents to imagine possible futures before acting. Inspired by human intelligence, which unifies understanding and imagination, we explore a unified model for autonomous driving. We present LMGenDrive, the first framework that combines LLM-based multimodal understanding with generative world models for end-to-end closed-loop driving. Given multi-view camera inputs and natural-language instructions, LMGenDrive generates both future driving videos and control signals. This design provides complementary benefits: video prediction improves spatio-temporal scene modeling, while the LLM contributes strong semantic priors and instruction grounding from large-scale pretraining. We further propose a progressive three-stage training strategy, from vision pretraining to multi-step long-horizon driving, to improve stability and performance. LMGenDrive supports both low-latency online planning and autoregressive offline video generation. Experiments show that it significantly outperforms prior methods on challenging closed-loop benchmarks, with clear gains in instruction following, spatio-temporal understanding, and robustness to rare scenarios. These results suggest that unifying multimodal understanding and generation is a promising direction for more generalizable and robust embodied decision-making systems.
The generation of planning domains from natural language descriptions remains an open problem even with the advent of large language models and reasoning models. Recent work suggests that while LLMs have the ability to assist with domain generation, they are still far from producing high quality domains that can be deployed in practice. To this end, we investigate the ability of an agentic language model feedback framework to generate planning domains from natural language descriptions that have been augmented with a minimal amount of symbolic information. In particular, we evaluate the quality of the generated domains under various forms of symbolic feedback, including landmarks, and output from the VAL plan validator. Using these feedback mechanisms, we experiment using heuristic search over model space to optimize domain quality.
Leveraging the general world knowledge of Large Language Models (LLMs) holds significant promise for improving the ability of autonomous driving systems to handle rare and complex scenarios. While integrating LLMs into Vision-Language-Action (VLA) models has yielded state-of-the-art performance, their massive parameter counts pose severe challenges for latency-sensitive and energy-efficient deployment. Distilling LLM knowledge into a compact driving model offers a compelling solution to retain these reasoning capabilities while maintaining a manageable computational footprint. Although previous works have demonstrated the efficacy of distillation, these efforts have primarily focused on relatively simple scenarios and open-loop evaluations. Therefore, in this work, we investigate LLM distillation in more complex, interactive scenarios under closed-loop evaluation. We demonstrate that through a combination of latent feature distillation and ground-truth trajectory supervision, an efficient vision-only student model \textbf{Orion-Lite} can even surpass the performance of its massive VLA teacher, ORION. Setting a new state-of-the-art on the rigorous Bench2Drive benchmark, with a Driving Score of 80.6. Ultimately, this reveals that vision-only architectures still possess significant, untapped potential for high-performance reactive planning.
In classical Reinforcement Learning from Human Feedback (RLHF), Reward Models (RMs) serve as the fundamental signal provider for model alignment. As Large Language Models evolve into agentic systems capable of autonomous tool invocation and complex reasoning, the paradigm of reward modeling faces unprecedented challenges--most notably, the lack of benchmarks specifically designed to assess RM capabilities within tool-integrated environments. To address this gap, we present Plan-RewardBench, a trajectory-level preference benchmark designed to evaluate how well judges distinguish preferred versus distractor agent trajectories in complex tool-using scenarios. Plan-RewardBench covers four representative task families -- (i) Safety Refusal, (ii) Tool-Irrelevance / Unavailability, (iii) Complex Planning, and (iv) Robust Error Recovery -- comprising validated positive trajectories and confusable hard negatives constructed via multi-model natural rollouts, rule-based perturbations, and minimal-edit LLM perturbations. We benchmark representative RMs (generative, discriminative, and LLM-as-Judge) under a unified pairwise protocol, reporting accuracy trends across varying trajectory lengths and task categories. Furthermore, we provide diagnostic analyses of prevalent failure modes. Our results reveal that all three evaluator families face substantial challenges, with performance degrading sharply on long-horizon trajectories, underscoring the necessity for specialized training in agentic, trajectory-level reward modeling. Ultimately, Plan-RewardBench aims to serve as both a practical evaluation suite and a reusable blueprint for constructing agentic planning preference data.
Intelligent systems powered by large-scale sensor networks are shifting from predefined monitoring to intent-driven operation, revealing a critical Semantic-to-Physical Mapping Gap. While large language models (LLMs) excel at semantic understanding, existing perception-centric pipelines operate retrospectively, overlooking the fundamental decision of what to sense and when. We formalize this proactive decision as Semantic-Spatial Sensor Scheduling (S3) and demonstrate that direct LLM planning is unreliable due to inherent gaps in representation, reasoning, and optimization. To bridge these gaps, we introduce the Spatial Trajectory Graph (STG), a neuro-symbolic paradigm governed by a verify-before-commit discipline that transforms open-ended planning into a verifiable graph optimization problem. Based on STG, we implement IoT-Brain, a concrete system embodiment, and construct TopoSense-Bench, a campus-scale benchmark with 5,250 natural-language queries across 2,510 cameras. Evaluations show that IoT-Brain boosts task success rate by 37.6% over the strongest search-intensive methods while running nearly 2 times faster and using 6.6 times fewer prompt tokens. In real-world deployment, it approaches the reliability upper bound while reducing 4.1 times network bandwidth, providing a foundational framework for LLMs to interact with the physical world with unprecedented reliability and efficiency.
Most Human-Machine Interaction (HMI) research overlooks the maneuvering needs of passengers in autonomous driving (AD). Natural language offers an intuitive interface, yet translating passenger open-ended instructions into control signals, without sacrificing interpretability and traceability, remains a challenge. This study proposes an instruction-realization framework that leverages a large language model (LLM) to interpret instructions, generates executable scripts that schedule multiple model predictive control (MPC)-based motion planners based on real-time feedback, and converts planned trajectories into control signals. This scheduling-centric design decouples semantic reasoning from vehicle control at different timescales, establishing a transparent, traceable decision-making chain from high-level instructions to low-level actions. Due to the absence of high-fidelity evaluation tools, this study introduces a benchmark for open-ended instruction realization in a closed-loop setting. Comprehensive experiments reveal that the framework significantly improves task-completion rates over instruction-realization baselines, reduces LLM query costs, achieves safety and compliance on par with specialized AD approaches, and exhibits considerable tolerance to LLM inference latency. For more qualitative illustrations and a clearer understanding.
Large language models (LLMs) have recently demonstrated strong potential for autonomous vehicle motion planning by reformulating trajectory prediction as a language generation problem. However, deploying capable LLMs in resource-constrained onboard systems remains a fundamental challenge. In this paper, we study how to effectively transfer motion planning knowledge from a large teacher LLM to a smaller, more deployable student model. We build on the GPT-Driver framework, which represents driving scenes as language prompts and generates waypoint trajectories with chain-of-thought reasoning, and investigate two student training paradigms: (i) on-policy generalized knowledge distillation (GKD), which trains the student on its own self-generated outputs using dense token-level feedback from the teacher, and (ii) a dense-feedback reinforcement learning (RL) baseline that uses the teacher's log-probabilities as per-token reward signals in a policy gradient framework. Experiments on the nuScenes benchmark show that GKD substantially outperforms the RL baseline and closely approaches teacher-level performance despite a 5$\times$ reduction in model size. These results highlight the practical value of on-policy distillation as a principled and effective approach to deploying LLM-based planners in autonomous driving systems.
Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) have demonstrated significant potential in single-turn reasoning tasks. With the paradigm shift toward self-evolving agentic learning, models are increasingly expected to learn from trajectories by synthesizing tools or accumulating explicit experiences. However, prevailing methods typically rely on large-scale LLMs or multi-agent frameworks, which hinder their deployment in resource-constrained environments. The inherent sparsity of outcome-based rewards also poses a substantial challenge, as agents typically receive feedback only upon completion of tasks. To address these limitations, we introduce a Tool-Memory based self-evolving agentic framework SEARL. Unlike approaches that directly utilize interaction experiences, our method constructs a structured experience memory that integrates planning with execution. This provides a novel state abstraction that facilitates generalization across analogous contexts, such as tool reuse. Consequently, agents extract explicit knowledge from historical data while leveraging inter-trajectory correlations to densify reward signals. We evaluate our framework on knowledge reasoning and mathematics tasks, demonstrating its effectiveness in achieving more practical and efficient learning.
Modern video games are complex, non-deterministic systems that are difficult to test automatically at scale. Although prior work shows that personality-driven Large Language Model (LLM) agents can improve behavioural diversity and test coverage, existing tools largely remain research prototypes and lack cross-game reusability. This tool paper presents MIMIC-Py, a Python-based automated game-testing tool that transforms personality-driven LLM agents into a reusable and extensible framework. MIMIC-Py exposes personality traits as configurable inputs and adopts a modular architecture that decouples planning, execution, and memory from game-specific logic. It supports multiple interaction mechanisms, enabling agents to interact with games via exposed APIs or synthesized code. We describe the design of MIMIC-Py and show how it enables deployment to new game environments with minimal engineering effort, bridging the gap between research prototypes and practical automated game testing. The source code and a demo video are available on our project webpage: https://mimic-persona.github.io/MIMIC-Py-Home-Page/.
The integration of Artificial Intelligence (AI) with High-Performance Computing (HPC) is transforming scientific workflows from human-directed pipelines into adaptive systems capable of autonomous decision-making. Large language models (LLMs) play a critical role in autonomous workflows; however, deploying LLM-based agents at scale remains a significant challenge. Single-agent architectures and sequential tool calls often become serialization bottlenecks when executing large-scale simulation campaigns, failing to utilize the massive parallelism of exascale resources. To address this, we present a scalable, hierarchical multi-agent framework for orchestrating high-throughput screening campaigns. Our planner-executor architecture employs a central planning agent to dynamically partition workloads and assign subtasks to a swarm of parallel executor agents. All executor agents interface with a shared Model Context Protocol (MCP) server that orchestrates tasks via the Parsl workflow engine. To demonstrate this framework, we employed the open-weight gpt-oss-120b model to orchestrate a high-throughput screening of the Computation-Ready Experimental (CoRE) Metal-Organic Framework (MOF) database for atmospheric water harvesting. The results demonstrate that the proposed agentic framework enables efficient and scalable execution on the Aurora supercomputer, with low orchestration overhead and high task completion rates. This work establishes a flexible paradigm for LLM-driven scientific automation on HPC systems, with broad applicability to materials discovery and beyond.