Agent 进展

Clinical education must prepare medical students to conduct safe and coherent patient interviews under conditions of uncertainty. Traditional standardized patient (SP) training is resource-intensive and difficult to scale. We developed a scaffolding-oriented multi-agent Large Language Model (LLM) AI Standardized Patient (AI-SP) training platform1. The system includes a patient agent for simulated dialog, a tutor agent providing Socratic prompts without disclosing diagnostic information, and a turn-level evaluator agent that monitors clinical progress without revealing summative scores. In a randomized controlled study (N = 100 medical students), participants were assigned to either a multi-agent (MA) scaffolding condition or a control condition. All students completed two learning sessions under their assigned condition followed by an examination conducted in a patient only environment. Performance was assessed using a standardized Objective Structured Clinical Examination (OSCE) based rubric. While no significant difference was observed in final diagnostic accuracy between groups, the multi-agent AI standardized patient system improved final examination scores compared to the control group utilizing structured progressive information disclosure; the most substantial and consistent improvements were observed in communication, the expression of empathy, and specific history-taking behaviors. These findings suggest that specialized LLM agents enhance the process quality of simulated clinical interviews without artificially inflating examination outcomes. To support future research, we release a multi-expert annotated dataset comprising transcripts, checklist annotations, turn-level evaluations, and OSCE-aligned scoring outcomes. This resource aims to facilitate the development of pedagogically grounded AI-SP systems and advance research on AI-supported clinical reasoning training.

Large Language Models (LLMs) are increasingly used to generate structured outputs, but their reliability remains unclear when those outputs must satisfy database-level constraints. We study this issue through database normalization, involving reasoning about functional dependencies, lossless join decompositions, and inter-table constraints. We introduce a Database Normalization Benchmark (DNBENCH), comprising 3,275 samples for evaluating LLM-driven database normalization from 1NF to BCNF. DNBENCH uses a three-axis protocol to measure semantic equivalence, structural accuracy, and logical validity. Across Single, Complex, and Real World levels, DNBENCH uncovers recurring failures in dependency inference, schema decomposition, and inter-table constraint reconstruction. We further propose Multi-Agent Reasoning for Schemas (MARS), which separates evidence extraction, violation diagnosis, and decomposition planning from schema generation and verification. MARS improves the DNB-SCORE by 82.0% over the single-prompt baseline. All artifacts will be released upon acceptance.

Recent advances in multimodal large language mod- els (MLLMs) have opened new opportunities for edge intelligence by enabling reasoning across heterogeneous sensor modalities, such as vision, text, and telemetry data. However, deploying these capabilities on resource-constrained edge platforms remains challenging due to the substantial computational, memory, and communication demands of modern MLLMs. Rather than transmitting raw sensor observations or partitioning neural networks at intermediate layers, Edge Multi-Modal Intelligence (EMMI) communicates a compact representation between edge devices and server resources, enabling communication-efficient edge MLLM inference. To achieve this, EMMI performs modality-specific encoding, cross-modal representation fusion, and learned compression at the edge, transmitting only a compact latent representation to server-side resources for high-capacity MLLM reasoning. This representation-centric design reduces communication overhead, preserves local data privacy, and provides a fixed-size interface between heterogeneous edge devices and server-side MLLMs. Evaluation on a representative multimodal benchmark demonstrates that EMMI can reduce the communication payload by 32x while maintaining comparable downstream accuracy, resulting in up to a 3.4x reduction in estimated end-to-end inference latency under bandwidth-constrained edge conditions.

Multimodal large language models (MLLMs) have shown strong potential in open-ended emotion understanding, yet they often generate emotion hallucinations. Evaluating such hallucinations is particularly challenging for two reasons. First, emotion understanding spans multiple cognitive facets, from multimodal perception to psychological reasoning. Second, emotional interpretations are expressed in free-form language, making existing closed-ended protocols insufficient for evaluation. To address these challenges, we introduce EHR (Emotion Hallucination Rate), an evaluator that quantifies emotion hallucinations across six facets: expression, action, audio, instinct, logic, and conclusion. Using EHR, we reveal that existing mitigation methods often reduce hallucinations in some facets while aggravating them in others, exposing the limitation of coarse-grained correction and the need for facet-aware localization and mitigation. Motivated by this finding, we propose HMER (Hallucination-aware Memory-guided Emotion Reasoning), a training-free framework for emotion hallucination mitigation. HMER maintains a Hallucination Memory that records localized hallucinated claims and enables targeted logit rectification, together with an Anchor Memory that preserves reliable intermediate reasoning states to stabilize subsequent generation. By selectively suppressing unreliable cues while preserving trustworthy reasoning context, HMER enables fine-grained mitigation across diverse hallucination facets. Extensive experiments on 19 MLLMs demonstrate the prevalence of emotion hallucinations and the effectiveness of our framework across diverse model architectures.

Quadratic Unconstrained Binary Optimization (QUBO) is a central formulation for combinatorial optimization and has gained increasing attention due to its compatibility with quantum, hybrid quantum-classical, and quantum-inspired solvers. However, translating natural-language problem descriptions into correct QUBO formulations remains difficult, requiring the identification of binary variables, constraints, objective functions, penalty terms, and suitable penalty weights. This process is time-consuming and often demands substantial domain expertise. To address this challenge, we propose an end-to-end multi-agent framework that automatically generates QUBO formulations from natural-language problem descriptions, supported by structured or unstructured test cases. To evaluate its performance, We also introduce QUBOBench, a benchmark containing 100 combinatorial optimization problems across 12 application domains, curated from peer-reviewed literature, competitions, and canonical NP-hard problems. Experimental results show that our framework achieves 68% accuracy on QUBOBench, outperforming a direct single-call baseline by 22%. Further analysis identifies iterative self-repair as the most important component contributing to improved performance. The data and code are open-sourced at https://quitttcat.github.io/QuantumQUBOAgent.

Diffusion large language models (dLLMs) achieve high decoding efficiency through block-parallel, arbitrary-order generation, making them attractive for latency-sensitive applications. GUI agents represent a natural testbed for this paradigm, as they must repeatedly perceive screen states and emit structured, spatially grounded actions in real time. However, whether dLLMs can be extended into capable multimodal GUI agents while preserving their parallel decoding advantage remains an open question. We present LLaDA-UI, a 16.7B-parameter MoE-based, block-wise diffusion vision-language GUI agent. LLaDA-UI follows a two-stage training pipeline: general multimodal pre-training aligns a native-resolution vision encoder with the LLaDA2.0-mini-base diffusion language backbone, followed by GUI-agent supervised fine-tuning on diverse mobile, desktop, web, and grounding data. Across widely adopted grounding benchmarks and navigation benchmarks spanning multiple platforms, LLaDA-UI substantially outperforms Qwen2.5-VL-7B and surpasses Qwen3-VL-8B on four of six reported GUI benchmarks. These results establish block-wise diffusion as a practical generative paradigm for multimodal GUI agents.

Before an LLM agent tackles tasks in a new environment, it can inspect available corpora and tools and construct reusable resources such as indices, scripts, or procedural guidance. Most automated adaptation methods, however, rely on task examples, trajectories, or evaluation feedback to decide what to build. Existing task-agnostic approaches avoid this supervision but commit in advance to a preparation strategy for a particular type of environment. We study a more open-ended setting: can an agent study an unfamiliar environment without a syllabus, i.e. before test time and without knowledge of the downstream task distribution, and choose how to prepare it? We formalize task-agnostic environment preprocessing, in which a studying system explores an environment under a budget and produces artifacts for a frozen solver. We compare unaided and archive-equipped meta-agents with fixed synthetic-practice and corpus-processing methods across six heterogeneous benchmarks. A meta-agent variant achieves the highest Avg@3 reward on five benchmarks, while fixed corpus processing remains best on the largest corpus benchmark. Larger study budgets do not reliably improve downstream reward. Nevertheless, studied artifacts reduce the test-time sampling needed to reach a given score, demonstrating how reusable preparation can shift computation from repeated test-time attempts to a pre-task study phase.

The Agent2Agent (A2A) protocol, now governed by the Linux Foundation, is an open standard that enables autonomous AI agents to discover, authenticate with, and delegate tasks to one another across organizational boundaries. Designed to complement the Model Context Protocol (MCP) for tool integration, A2A is rapidly emerging as the horizontal communication layer of the multi-agent ecosystem. Yet the protocol's security has received no systematic analysis. This paper presents A2ABreak, the first rigorous systematic security analysis of the A2A protocol. We introduce a novel framework that utilizes an LLM-assisted extraction of a verified finite-state machine directly from the natural-language specification, producing a unified model of 37 states and 76 transitions from 929 formalized statements, and then systematically reasons over this model to discover protocol-level vulnerabilities through adversarial verification, under a full-compliance assumption. Our analysis uncovers 11 new vulnerabilities, each exploitable by a specification-compliant adversary without requiring any implementation flaw. Among the findings are cross-client context injection through unprotected context identifiers, credential harvesting via multi-hop identity loss in delegation chains, and data exfiltration through rogue agents advertising unattested capability claims. A2ABreak achieves 73.3% precision and 84.6% F1 against independent expert review, while a zero-shot LLM baseline operating over the same specification produces zero confirmed findings, demonstrating that explicit formal grounding is essential for sound protocol security analysis.

When an indirect prompt injection succeeds against an LLM agent, the compromise is visible in the agent's own behavior: a benign prefix of tool calls, a poisoned observation, and a suffix of actions that serve the attacker. An operator needs three facts: where the attack entered, which steps it corrupted, and whether apparent poison was resisted. Existing systems return either a whole-trace verdict or a single unsafe index. We present DriftNet, a dual-head trajectory Transformer that reads a logged tool-call trajectory and answers all three questions in one forward pass: one head classifies the trajectory as compromised or not, and a second assigns every step one of four labels (benign, injection point, hijacked, failed injection). To our knowledge it is the first supervised detector to produce this joint output. A frozen sentence encoder and four identity-free world features embed each step; the trained trunk, under two million parameters and optimized with a class-weighted joint objective over both heads, needs no access to the agent's model. On the task-disjoint split of the AgentDrift benchmark (12,536 trajectories, 71,024 labeled steps), with a 20-configuration sweep bounding hyperparameter sensitivity to 0.011 F1 and the test part evaluated exactly once, DriftNet reaches trajectory-level F1 of 0.983, exact injection-point recovery on 98.7% of attacked trajectories, hijacked-span IoU of 0.979, zero flags on 218 resisted attacks, and 2.9% flags on hard negatives. A surface baseline retrained on the identical split recovers 11.1% of partial hijacks and 17.1% of delayed executions; DriftNet reaches 98.6% and 93.2% while lowering every false-alarm rate. Reading all 26 residual errors shows that most misses trace to trajectories whose labeled injection observation carries no legible instruction, and we report the benchmark's measured world-identity regularity alongside the results.

Real-world video understanding requires integrating visual, audio, textual, and temporal evidence distributed across a video. Yet many pipelines use a fixed video context and single-pass inference, limiting adaptive evidence acquisition when observations are incomplete, ambiguous, or conflicting. We present VLX-VR, an agentic-aware video reasoning model trained within a video reasoning framework defined by a Think--Memory--Observation loop. At each step, VLX-VR determines the needed evidence, invokes read_memory or write_memory, incorporates the returned Observation, and decides whether to continue or produce the task output. We train VLX-VR with multimodal data, including videos and agent trajectories, using reinforcement learning to learn evidence acquisition, memory use, and termination. On MINERVA, VLX-VR achieves state-of-the-art performance among the models included in our comparison, with 78.79% accuracy. Under the original three duration groups, its accuracies are 76.70%, 78.73%, and 80.92%, with a cross-duration accuracy variance of 2.97~$\mathrm{pp}^2$. On correctly answered samples, 96.20% of VLX-VR's reasoning traces are consistent with the MINERVA reference reasoning traces and the evidence described by them, while approximately 75.80% of all evaluated samples satisfy both answer correctness and this evidence-grounded trace criterion. These results show strong performance and broadly stable behavior across durations, while counting, state changes, causal reasoning, and spatial perception remain challenging.

We present the PccDiffuser, a conditional diffusion framework for continuum robots that learns a multimodal distribution over complete configuration-space paths and samples multiple candidate solutions in parallel, which are subsequently converted into an executable trajectory by time allocation considering actuator constraints. Under the piecewise constant-curvature model, we use exponential co-ordinates to describe the robot kinematics, and use graph neural network to encode a variable number of environment obstacles. Analytical differential kinematics is incorporated in the denoising process to improve terminal accuracy and whole-body clearance. On a mixed test set comprising workspace with zero to four obstacles, PccDiffuser achieved a success rate of 91%. Compared with existing sampling- and optimisation-based benchmarks, it delivered both a higher success rate and greater computational efficiency, with the latter advantage becoming more substantial when sampling more candidate solutions. Experiments on a three-section tendon-driven continuum robot further demonstrate consecutive planning, multi-solution planning, and whole-body obstacle avoidance.

Large Language Models (LLMs) have shown promise for translating Natural Language (NL) planning descriptions into PDDL problem instances. However, standard evaluation criteria such as syntactic validity or planner success can substantially overestimate faithfulness to the described task: a generated problem may be parseable and solvable while misrepresenting the intended initial state, goal, object structure, or optimization target. This paper studies an end-to-end NL-to-PDDL pipeline that combines LLM generation, checks in terms of PDDL parsing, planning and validation, a domain-conformance checker, an LLM critic, and iterative repair. Fine-grained repair feedback is constructed from the domain description, the generated problem, the natural language problem description, and operational diagnostics. Reference-based comparisons against curated benchmark PDDL problem descriptions are used for post-hoc benchmark analysis, and these offline checks include renaming-invariant structural matching and semantic equivalence, where domain support is available. Across Planetarium, AutoPlanBench, and curated PDDL~2.1 problems, results show that operational success and benchmark-reference reconstruction can diverge substantially. Results also show that structured repair can be useful, and that PDDL~2.1 remains challenging for reference reconstruction, even when operational success improves.

Large language models (LLMs) increasingly act as research agents, yet their ability to track shifts in research attention is difficult to evaluate because reviews and research ideas lack uniquely verifiable outcomes. We introduce Research Attention Prediction (RAP), a rolling benchmark covering 278 AI/ML fields and 1,390 episodes. At each cut-off, an LLM agent searches a temporally restricted arXiv corpus and predicts the next six months' paper shares across eight frozen research directions. Search generally helps, but all four diagnostic models perform worse than an exact-count exponentially weighted moving average (EWMA) baseline in compositional accuracy. We identify two linked bottlenecks. Under cumulative-history access, State carry-forward outperforms direct Forecast for all four diagnostic models; frozen-evidence replay links a shared component of this reversal to Forecast-oriented policies retrieving a smaller share of recent evidence. Even with exact historical activity, future-specific updating remains limited, with only GPT-5.5 plus reopened Search slightly surpassing EWMA. Fine-tuning on realised outcomes improves Qwen3-4B's forecast Spearman correlation by 0.105 on held-out fields at later origins, with gains also on change-rich episodes.

Scientific workflow management (WMSs) systems automate execution, yet orchestrate using fixed, hand-tuned rules. LLM agents promise more autonomous orchestration, but it remains unclear where to introduce agentic reasoning, how to bound its risk, and when it actually helps. We present Avatar, an actor-based architecture comprising an orchestrator, an executor, and a provenance monitor. Each actor's decision policy is pluggable (rule-based or LLM-backed) via a single adapter-validated action catalog, so conventional and agentic control run on the same core across different WMSs. We present an implementation using the Academy framework and evaluate Avatar across three workloads. We observe that Avatar's rule mode reproduces native execution, with a single unchanged core running all three. Moreover, LLM-backed Avatar reports a reduction of compute wastage by $55%$ and cuts GPU-busy time by $40%$. Overall, we envision Avatar as a step toward workflow systems that reason about their own orchestration rather than follow pre-fixed rules.

Large language model agents produce fluent action sequences across a wide range of tasks, yet they fail in characteristic ways once the environment becomes partially observable. Ambiguous feedback pushes them into premature commitments. A single informative observation can collapse their uncertainty onto the wrong hypothesis. Policies drift as the history grows. We trace these symptoms to a common structural cause. An LLM agent, as commonly deployed, is a history-conditioned policy with no explicit belief over hidden state. We propose an architectural fix. The Belief-State Engine (BSE) is an inference module placed outside the LLM. It maintains a Bayesian posterior over the latent states of a given POMDP (Partially Observable Markov Decision Process) model, and at each decision step it exposes only that posterior to the LLM. The raw action-observation log is not shown. We set out a minimal four-axiom specification of what a belief-consistent internal state must satisfy, and prove that the LLM paired with the BSE is a sound Markov policy on the belief MDP induced by the underlying POMDP. It therefore inherits the Bellman optimality guarantees of classical POMDP theory, provided the LLM is never exposed to the raw history. We evaluate the architecture on the Tiger POMDP and a red-team attack-graph task, against six baselines: a reactive LLM, Chain-of-Thought, ReAct, a natural-language belief tracker, QMDP, and POMCP. Across both domains, the BSE-augmented agent improves task return, belief calibration, and decision consistency. Ten targeted ablations isolate the contribution of each architectural choice confirms that the effect is not specific to any one model. Code, environment specifications, prompt templates, and seed logs accompany this paper.

Large language models (LLMs) have demonstrated remarkable capabilities in reasoning and code generation, raising the prospect that they could assist in developing and optimizing the very infrastructure that powers them. However, existing benchmarks mainly focus on isolated kernels, predefined operators, or pre-specified optimization targets, and therefore fail to evaluate the ability of LLMs to perform open-ended, long-horizon LLM infrastructure engineering. To address this gap, we present $Φ$-Bench, a benchmark for systematically evaluating LLMs on engineering the LLM infrastructure stack. Derived from optimization problems studied in frontier research and grounded in real-world code repositories, $Φ$-Bench provides broad coverage of the LLM infrastructure stack and spans tasks of varying complexity, ranging from localized kernel-level function completion to long-horizon implementation and end-to-end system optimization. Extensive experiments on frontier LLMs reveal their current capabilities and limitations in engineering complex LLM infrastructure, offering insights into the challenges that remain on the path toward autonomous optimization of future AI infrastructure.

Plane geometry remains a significant challenge in AI, requiring the integration of visual perception and mathematical reasoning. While Large Multimodal Models (LMMs) naturally handle visuo-linguistic inputs, they are often computationally intensive and opaque. We demonstrate that a pure Large Language Model (LLM), when equipped with specialized modules, can rival state-of-the-art LMMs on complex geometry problems. Our framework integrates a Geometric Vision Parser, which translates diagrams into symbolic form, with a Symbolic Solver that performs formal deductions, thereby mitigating hallucinations and promoting interpretable reasoning. To enable rigorous evaluation, we curate a benchmark of challenging problems from the 2025 Chinese Zhongkao examinations, ensuring data novelty and testing deeper deductive skills. Experiments demonstrate that our approach achieves performance comparable to Gemini 2.5 Pro while delivering clearer, human-like solutions.

Persistent language agents need stored experience to remain available across time, while each answer requires evidence suited to a particular question. A superseded fact can mislead a current-state answer and still be essential for a historical query. We present RD-Forget, a training-free framework that separates what an agent stores from what it uses. A retained source archive preserves observations, and a query-conditioned memory view controls their influence on the current answer. A frozen language-model curator extracts relevant evidence, groups facts into semantic slots, and preserves the relations needed for multi-hop reasoning. Same-slot replacement links suppress superseded values in current-state contexts, while intent-aware retrieval makes earlier evidence eligible again. A rate-distortion formulation guides construction of the answer-time view within a memory budget. Experiments span conversational memory, knowledge updating, fact consolidation, long-context reasoning, and personalization under a shared answering pipeline. The results associate accurate answers with both query-relevant evidence construction and control over obsolete alternatives. Configurations without forgetting or query conditioning have the largest score deficits, while slot grouping, historical access, and relation preservation contribute complementary functions. Retaining history while selectively controlling its use offers a practical way to accommodate changing facts and future questions.

GUI agents accumulate high-resolution screenshots as the trajectory unfolds, increasing inference latency and memory usage. Training-free visual token pruning can reduce this cost, but cache reuse introduces a fundamental constraint. Once tokens are discarded, the corresponding visual evidence cannot be recovered without re-encoding. Pruning therefore becomes an irreversible admission decision that must remain useful for unknown future targets while preserving coverage of operable regions under tight budgets. To address these challenges, we propose \textbf{\method{}}, a training-free framework for Trajectory-robust Admission and Coverage-aware Evidence ordering. Specifically, we combine a query-independent layout-derived interaction prior with instruction relevance and feature novelty to rank visual evidence according to both potential future utility and diversity. Then, we reserve part of the budget for native visual tokens distributed across the screen, repairing missing spatial coverage without breaking the ordering. Together, these mechanisms produce a nested token order, allowing retained visual evidence to shrink monotonically across budgets while remaining reusable throughout the trajectory. Finally, our monotone KV contraction incrementally contracts retired frames into compact session state, avoiding repeated visual encoding or pruning. Extensive experiments across six GUI benchmarks and diverse models verify the effectiveness of our proposed \method{} under tight budgets. The source code will be released.

Video-language models and video agents can produce hallucinations that conflict with spatiotemporal evidence. Existing benchmarks mainly evaluate model hallucinations, and heterogeneous mechanisms make detector reliability difficult to compare. We introduce VidHalLoc, a benchmark that evaluates hallucination detection methods under a unified diagnostic evaluation protocol using 2,000 adversarial hallucination samples across Video Question Answering and Video Captioning tasks, spanning Ontology and Dynamic hallucination categories. To construct VidHalLoc efficiently, we introduce VideoHALO, a Harness Engineering-informed multi-agent workflow that decomposes data construction into four executable stages supported by a memory system and a communication protocol. Evaluation of fifteen methods reveals that the four dedicated detectors peak at an Overall accuracy of only 34.63%, indicating limited reliability across video hallucination types [Dataset Repository: https://huggingface.co/datasets/wesfggfd/VidHalLoc].

Large language models are increasingly composed into agent loops that plan, call tools, and resume the same task after each action. These loops press a shared memory hierarchy harder than conventional multi-turn chat, because they hold a growing key-value (KV) prefix across tool waits and place many sessions on one SRAM/HBM pool, so that eviction and hierarchical placement become a session-level efficiency problem orthogonal to compute-mode optimization. Existing proxies based on recency, timeout, or identity miss the mechanism information of the loop and therefore treat a live wait as a cold, discardable unit. We present Unified Native Inter-turn Session Orchestration Nexus (UNISON), an event-driven near-memory scheduler in which Survival-Penalty Eviction for Agent Return-gap (SPEAR) and Tiering in Idle-window DMA Events (TIDE) share one live ranking. SPEAR selects who leaves from a gap average and a turn-indexed hazard, while TIDE spends the observed wait as a DMA budget for who sits in the fast tier. On coding and general-mission benchmarks with three model families, totaling 1,415 sessions and 33,596 turns, the joint policy is the best non-oracle entry on every trace, raising hit rate by 0.3% to 23.1%, reducing AMAT by 22% to 51%, and lowering TTFT by 58% to 89% on long-horizon traces. A structural necessity analysis shows that the unified near-memory design cannot be decomposed into independent IPs or realized in software without re-introducing documented failure modes. The 28-nm CMOS scheduling core occupies 0.169 mm^2 at 13.6 mW and 150 MHz, a negligible overhead relative to the KV hierarchy it manages, reproducing the floating-point ranking at Kendall tau exceeding 0.998.

Large language models (LLMs) are increasingly deployed as personalized assistants that interact with users over extended periods of time. As conversations grow longer, relying on full interaction histories becomes increasingly inefficient and unreliable: long contexts introduce substantial computational overhead, making it difficult for models to consistently identify and utilize the most relevant information for the current request. These challenges have motivated memory systems that structure and retrieve user-specific information. In realistic interactions, users often seek practical guidance such as recommendations, planning, and decision support. Unlike factual recall tasks, personalized guidance requires models to integrate information across multiple past conversations and reason about changing user preferences and experiences. However, existing conversational memory evaluations mainly focus on retrieval and factual recall. To study this challenge, we introduce PRAGMA, a benchmark for evaluating personalized guidance in long-term conversations. PRGAMA contains curated longitudinal conversation histories, evidence annotations, and guidance scenarios grounded in evolving user contexts and incorrect user assumptions. Experiments across retrieval systems, memory systems, and long-context models reveal that current systems struggle both to recover the appropriate conversational evidence and to effectively use it for personalized guidance. Our results highlight the need for memory architectures that support robust conversational retrieval and memory-grounded reasoning beyond evidence recall.

Real-world GUI usage frequently involves workflows that span multiple devices and platforms, requiring the transfer of intermediate results, maintenance of shared state, and coordination across heterogeneous environments. However, existing GUI benchmarks overwhelmingly evaluate agents on single-device, statically defined tasks, thus leaving such cross-device capabilities largely unexamined, resulting in an overly optimistic assessment of agents' readiness for real-world usage. We introduce JarvisGUI, a dynamic benchmark that evaluates GUI agents on cross-device workflows requiring coordinated interaction across heterogeneous platforms, including Android, Windows, and Ubuntu. Specifically, JarvisGUI formulates GUI tasks as input-output transformations under a lightweight type system, which allows us to automatically compose multi-step, cross-device workflows and dynamically evaluate agent performance within a unified framework. By evaluating agents in virtual environments spanning multiple operating systems, JarvisGUI reveals that state-of-the-art open-source GUI agents struggle with the state-transfer awareness, cross-platform contextual reasoning, and long-horizon dependency management required for real-world workflows, exposing a critical capability gap invisible to existing benchmarks.

As large language models are increasingly deployed as tool-augmented legal agents, they introduce agentic hallucinations where tool-call and reasoning errors cascade into fabricated holdings and miscited authority. However, existing legal benchmarks evaluate only single-turn QA with outcome-level metrics, while agentic hallucination benchmarks lack legal-specific diagnostic capability. Neither answers to what extent and how a legal agent hallucinates along its trajectory. To address these limitations, we introduce LexAgentHallu, a legal agentic hallucination benchmark designed to evaluate to what extent and how legal agents fail along multi-step trajectories. Built through a four-stage expert-in-the-loop pipeline, LexAgentHallu contains 3414 instances across 17 legal categories and 6 task types. Each instance is annotated under a dual-layer hallucination taxonomy of 7 high-level categories and 27 fine-grained subclasses, covering both substantive errors and agent-procedural failures. We further design fine-grained metrics that quantify to what extent and localize how each failure occurs along an agent's execution path. Our evaluation across 18 proprietary and open-source agents uncovers a Right-Answer-Wrong-Reason effect and reveals that hallucination subclasses cluster rather than scatter, forming distinct agentic framework, legal task, and category profiles. These findings, invisible to outcome-level evaluation, validate the diagnostic power of LexAgentHallu for evaluating agentic hallucination in law.

This study develops a deep reinforcement learning framework for training Unmanned Aerial Vehicle (UAV) agents to navigate and monitor simulated wildfire environments. Results show that agents learn increasingly stable and effective behaviors over time, as demonstrated by converging loss trends, improved reward signals, and more consistent navigation patterns such as fire-boundary tracking. Overall, these findings highlight the potential of deep reinforcement learning (DRL) based UAV systems for autonomous wildfire monitoring and suggest that environmental structure and reward design influence policy effectiveness.

Urban planning is a real-world spatial optimization problem that requires selecting feasible actions from large candidate spaces under practical objectives such as cost and service quality. Existing optimization and reinforcement learning methods are effective for fixed formulations, but often depend on task-specific representations and constraint handling. We propose CityPlanner, a sandbox-agent framework for executable urban planning. CityPlanner introduces UrbanSandbox, a unified file-based environment where agents inspect task files, generate plans, run evaluators, and revise decisions based on executable feedback. To make learning tractable, we further propose atomic-task reinforcement learning, which decomposes long sandbox trajectories into BuildPlan for initial construction and ImprovePlan for feedback-based refinement. Experiments on a real-world benchmark show that CityPlanner consistently outperforms heuristic, task-specific RL, and general LLM-agent baselines. Ablations verify the contributions of UrbanSandbox, atomic-task RL, and iterative deployment. We release the code and dataset at https://anonymous.4open.science/r/co-agent-C1C8

Inferring speaker relationships from spoken conversations is an important step towards socially aware speech understanding. However, this task remains underexplored, and supervised modeling is costly to train and scale. At the same time, existing inference-time LLM approaches provide limited structure for handling subtle, distributed, and multimodal relational cues that may support multiple plausible interpretations. To address these limitations, we introduce a training-free multi-agent reasoning framework that organizes inference through structured interaction among LLM agents, allowing relationship judgments to be proposed, challenged, and adjudicated without task-specific training. We instantiate this framework with two complementary designs. We propose Multi-Role Multi-Agent Debate as a task-specific adaptation of standard multi-agent debate for speaker relationship inference, assigning agents complementary roles or social-theory-grounded perspectives rather than a single undifferentiated viewpoint. In contrast, we introduce Multi-Agent Compete, a competition-based protocol that compares agent judgments through pairwise adjudication, eliminates weaker candidates, and retains the most defensible one. We evaluate these methods on the Seamless Interaction dataset across different modality settings, covering both binary classification and fine-grained relationship-detail prediction. Results suggest that they improve over zero-shot and existing multi-agent baselines in most cases. Human evaluation further suggests that this task is challenging even for people. LLM methods can sometimes outperform human annotators in text-included settings but are less competitive in the audio setting. Together, these findings suggest that relationship inference benefits from structured inference-time interaction among agents, while acoustic cues are not yet fully captured by current models.

Existing evaluation frameworks mostly assess only one part of AI agents, such as task completion (AgentBench) or security robustness (AgentDojo, ASB), rather than the complete pipeline of planning, tool selection, tool execution, memory and reasoning. Failures can occur at any stage, yet existing benchmarks rarely identify their precise source. AgentAudit evaluates the entire execution trace across ten capability, grounding, security and behavioural dimensions, namely instruction integrity, planner, memory, tool selection, tool invocation, tool correctness, alignment, tool faithfulness, security and execution integrity, combined with behavioural classification and failure attribution to pinpoint the exact stage responsible for an observed failure. AgentAudit can evaluate any LLM-based AI agent, since it attaches to the agent instead of replacing it. It reads only the recorded execution trace and does not interfere with how the agent runs, so it places no constraint on the agent's internal implementation. We evaluate five language models (OpenAI GPT-5, Claude Sonnet 5, Sarvam 105B, Llama 3.3 70B and Gemini 2.5 Flash) across nine capability and adversarial tasks. Claude Sonnet 5 and GPT-5 obtain the highest mean Composite Trust Scores (95.1 and 80.6 out of 100, respectively), while Sarvam 105B, Llama 3.3 70B and Gemini 2.5 Flash trail substantially (57.6, 45.7 and 22.6). All traces were scored by a single fixed judge model, which was itself one of the evaluated models, a limitation discussed in Section VII.E. More importantly, models with similar task-completion behaviour can diverge sharply in trustworthiness, as several non-frontier models are repeatedly classified Unsafe_Compliance on adversarial tasks rather than merely failing them, a distinction that pass/fail benchmarks cannot surface.

Agentic graph learning (AGL) has recently achieved promising results on graph reasoning tasks, where an agent powered by a large language model (LLM) sequentially samples the graph as evidence to support its final prediction. Existing methods either employ a single agent or orchestrate multiple role-based agents to reason and learn over the entire graph, but both essentially rely on a shared reasoning policy across different graph regions, which can be suboptimal for graphs with heterogeneous structural and semantic patterns. Inspired by the progress of multi-agent collaboration on complex reasoning tasks, a natural remedy is to let multiple agents own different memory and collaborate; however, applying this paradigm to graphs directly faces two challenges. First, existing AGL methods typically verbalize graph structures into natural-language descriptions for LLM agents, making the reasoning process sensitive to the ordering of structural information and thereby breaking the permutation-invariant nature of graphs. Second, incorporating increasingly large sampled neighborhoods leads to rapidly growing contexts. To address these challenges, this paper introduces a multi-agent agentic graph learning (i.e., MAAGL) framework. MAAGL partitions the graph into communities and assigns an independent agent to each community for region-specific specialization. MAAGL represents structural and semantic evidence separately. Structural evidence is summarized by a dynamically updated structural signature that is permutation-invariant and fixed in size, while semantic evidence is filtered to the top-k nodes ranked by relevance. Based on historical trajectories with similar signatures, agents estimate their confidence and trigger debate-style collaboration when needed. Extensive experiments on four benchmark datasets show that MAAGL outperforms SOTA AGL methods.

While Large Language Models (LLMs) have demonstrated impressive capabilities, they often struggle with extremely long contexts due to fixed context limits. To address this, sequential approaches like MemAgent extend the effective context by reading text in segments and iteratively updating a fixed-size memory. However, this sequential paradigm suffers from high latency and requires costly reinforcement learning (RL) training, which can lead to overfitting on specific datasets. To overcome these limitations, we propose ConvMem, a training-free, highly parallelizable framework that reformulates long-context reasoning as a hierarchical convolution. Inspired by CNNs, ConvMem treats an LLM prompted with a specific query as a convolutional kernel. This kernel summarizes text segments hierarchically, shortening the reasoning path from a linear chain into a logarithmic tree. Specifically, ConvMem integrates Configurable Strides and Skip Connections to ensure robust evidence capture and propagation, while employing Multi-Kernel Convolution to decompose complex queries into disentangled semantic channels. This design not only mitigates error accumulation but also enables massive parallelization across both text segments and reasoning threads. Experiments on RULER-HotpotQA and RULER-2WikiMultiHopQA demonstrate that ConvMem outperforms training-free baselines and avoids the risk of overfitting to parametric priors often observed in RL-trained models on out-of-distribution tasks.