Search arXiv⌕ Search

arXiv subjects

Yifan Yang

Publications and source records attributed to Yifan Yang.

At least 19 recordsLinked to original sources
arXiv2026

HEMO: Harness Self-Evolution for Multi-Objective Combinatorial Optimization

Automatic operator design (AOD) has increasingly adopted large language models (LLMs) to generate problem-specific search and variation operators for multi-objective combinatorial optimization (MOCO). Yet most methods evolve the operators while leaving the process that discovers them fixed. This limits adaptation as new Pareto trade-offs and operator interactions change where and how the search should proceed. We introduce HEMO, which makes the AOD harness itself a self-evolving optimization target. HEMO maintains a persistent harness state and updates one module at a time, revising the logic that determines which experience to retrieve, which operators to improve, which parents to select, and how to formulate the orchestration of search steps. Downstream solution quality and runtime guide these updates, while a discounted UCB scheduler directs adaptation toward promising modules as their utility changes. A persistent memory filesystem preserves candidate outcomes and diagnostic feedback across harness states, enabling successive states to build on accumulated optimization experience. Experiments across eight MOCO tasks and two structurally distinct evolutionary backbones demonstrate strong performance against conventional evolutionary, neural, and LLM-based AOD baselines, together with effective transfer to related tasks. HEMO extends automatic operator design beyond evolving individual operators to improving the search process that discovers them.

cs.NE↗
arXiv2026

Cinematize from Unreal: Agentic Choreography for Controllable World Simulation

Controllable world simulation requires more than visually plausible frames: scenes must retain persistent state, coordinated actions, and editable temporal structure. Generative world models offer flexible visual synthesis, but their outputs do not always expose the objects and transitions needed for precise revision. Graphics engines provide executable state and direct control, yet translating language into valid operations requires specialized knowledge of assets, geometry, and interdependent APIs. We present CineU (Cinematize from Unreal), an agentic system for language-driven world orchestration and cinematic choreography within Unreal Engine. From a code-based world modeling perspective, an Unreal project serves as a persistent, inspectable world representation, while agent-generated code specifies operations whose effects can be executed and verified. CineU combines hierarchical orchestration, cascaded asset retrieval and geometry-constrained placement, capability-aligned code synthesis, and multi-stage verification with localized repair. Shared scene and timeline context coordinates entities, actions, camera trajectories, and shot boundaries while supporting dependency-aware revisions. Experiments on scene construction, selective editing, multi-shot cinematography, and component ablations show how specialized execution knowledge and engine feedback improve task completion and targeted recovery. CineU illustrates how executable world state can complement learned visual generation to support controllable and revisable simulated worlds.

cs.MA↗
arXiv2026

Omni-InteractScope: Benchmarking Proactive and Agentic Interaction in Continuous Omnimodal Streams

Omnimodal large language models (Omni-LLMs) are increasingly expected to assist users while observing continuous audiovisual streams. However, existing evaluations provide limited insight into how reliably these models connect stream evidence and user needs to timely, sustained interventions. We introduce \textbf{Omni-InteractScope}, a benchmark of 1,479 human-annotated, cross-reviewed interactions with 1,790 temporal targets across eight task groups. It links input modalities, event triggers, intervention types, and user needs, covering event-timed tool invocation and query-free assistance alongside notifications, warnings, state tracking, and continuous responses. Our experimental results on the proposed benchmark reveal three critical limitations of current Omni-LLMs: (1) \textbf{Timely tool invocation remains unreliable}: all 12 evaluated models produce an on-time first response for at most 40\% of tool-invocation targets, and joint timing-and-tool accuracy reaches at most 32.0\%. (2) \textbf{Query-free reminders remain poorly covered}: all evaluated models achieve lower timely reference-target recall on query-free reminders than on explicit questions, measured on their respective target sets. Reminder recall never exceeds 23.0\%. (3) \textbf{End-to-end guidance coverage remains limited}: nine models cover none of the 26 guidance sequences in full, and the remaining three cover only one to three sequences each. Targeted controls further show that tool-invocation scores alone do not establish event grounding and that reminder coverage depends on response history and frequency. These findings motivate developing and evaluating streaming assistants for timely action, initiative under general user needs, and coverage of entire response sequences.

cs.AI↗
arXiv2026

PS-DLO: Property- and Spatially Aware Deformable Linear Object Manipulation Policy

Deformable linear objects (DLO) pose a coupled perception and control challenge: their slender geometry makes precise localization difficult, while their deformations depend on object-specific physical properties. To address this challenge, we propose PS-DLO, a property- and spatially aware DLO manipulation policy. First, contrastive image-text learning maps the initial observation to categorical descriptions of DLO properties, providing explicit physical and structural priors for action generation. Second, SAM3 extracts mask-guided features from future observations, which are distilled into the policy's action expert to encode task-relevant DLO regions and their subsequent configurations. We evaluate PS-DLO on nine real-world tasks across single-arm and bimanual platforms, training a shared multi-task policy for each embodiment. PS-DLO achieves an average success rate of 68.9%, exceeding the strongest baseline by 20.0 percentage points. In generalization experiments, PS-DLO achieves higher success rates than the baseline in six of seven visual-shift conditions on butterfly-knot untying. These results demonstrate that combining object-property priors with future spatial supervision improves multi-task DLO manipulation and robustness to visual variation.

cs.RO↗
arXiv2026

Allocation Before the Clock: Graph, Set and Game Theory of Professional League of Legends Objective Setups

Before every neutral objective in professional League of Legends, each team decides which of its five players walk to the pit, which hold a lane, and when to commit. The leading analysis of such setups, TAGNet for Counter-Strike 2, clusters graph-network embeddings of player positions and reads cluster win rates as tactical quality. We treat a setup as an allocation on a walled map: formations are set partitions on the lattice $Π_5$, control is a geodesic Voronoi split of a navigation graph, and commitment is an allocation game solved as a quantal response equilibrium priced in win probability. On all 164 games of MSI and Worlds 2025 (2,994 team-setups, minimap tracks validated against Riot positions), trailing teams leave the pit empty far more often than leading teams, by +34.8 percentage points at the first baron and +30.4 percentage points at Atakhan. Our model, HASSE-QRE, finds six setup patterns that whole-model series-bootstrap refits reproduce (ARI 0.819, comparable to 0.813 for TAGNet's $K$-Means step alone) and indicates that teams price fights, travel and committed players, not the objective itself (weight 0.018; fixing it to one costs 59.9 log-likelihood points). The equilibrium reproduces a quarter of the commitment gap, almost all of it through state variables rather than its strategic channels. Weighting a team-level contrast by exposure moves it across $p=0.05$ (0.046 against 0.052). We release the tracks, setups and code.

cs.CV↗
arXiv2026

An Adaptive-Horizon Graph Neural Operator for coupled surrogate morphodynamic modelling

Morphodynamic simulations require repeated coupling between hydrodynamic solvers, sediment transport modules, and bed updating. For long duration, multi-scenario simulations on large unstructured meshes, such coupling is computationally demanding. This study proposes an Adaptive-Horizon Graph Neural Operator (AH-GNO) that formulates bed evolution as a graph operator learning problem from recent hydrodynamic and topographic states to predict future bed elevation increments. The model operates directly on the native unstructured meshes. The approach integrates area-weighted graph learning, historical state selection, and forecast horizon estimation, allowing the effective history length (K) and update interval (B) to vary with the evolving flow and bed state. Using Telemac2D/GAIA solutions as supervised numerical references, the framework is evaluated on the official Bump and Yen bend benchmarks and on a field-scale application (Waiho River, New Zealand). Results show that the AH-GNO reproduces the main patterns of bedform migration, bend-scale erosion and deposition, and localized bed adjustment. Across the three cases, the tested CPU-GPU deployment reduced post-training bed-update workflow time from 12~1204 s with GAIA to 0.08~3.34 s with AH-GNO. This improvement corresponds to deployment-specific accelerations of approximately 150~360 times relative to 4-core GAIA CPU configurations, and with 105~186 times gains for 20-core CPU configurations. These results suggest that, while retaining hydrodynamic feedback from TELEMAC-2D, a learned operator for bed updating can provide an efficient acceleration component for morphodynamic scenario analysis and rapid coupled simulation.

physics.comp-ph↗
arXiv2026

FilmFlow: Agentic System for 3D Virtual Film Cinematography

Complex camera motion is central to visual storytelling, yet translating cinematographic intent into controllable, executable camera trajectories remains challenging. We introduce FilmFlow, an agentic framework that converts natural-language instructions or reference videos into explicit camera trajectories for dynamic 3D environments. To generate these trajectories, a Director agent constructs executable camera plans by composing high-level motions from concurrent atomic operations that jointly control translation, rotation, and framing. The Director is supported by three specialized agents: an Interpreter that extracts scene-grounded cinematographic intent, a Scout that selects initial viewpoints, and a Critic that evaluates rendered results and provides visual feedback for iterative plan refinement. We also introduce CinemaBench, comprising 150 Blender scenes from self-created and licensed sources, with five camera instructions per scene for 750 text-directed tasks and 60 reference videos associated with a subset of scenes. CinemaBench supports evaluation of both text-directed camera generation and video reference-directed camera generation. Across a diverse set of evaluated baselines, FilmFlow achieves the strongest benchmark performance and the highest user preference, demonstrating effective spatial reasoning, temporal coordination, and visual composition for executable 3D cinematography.

cs.CV↗
arXiv2026

SPARE: Sparsity Allocation via Routing Entropy for Efficient MoEs

Mixture-of-Experts (MoE) architectures scale model capacity efficiently, yet their substantial memory footprint poses a major barrier to deployment. Expert pruning reduces this footprint, but most methods focus on which experts to remove and prune every layer equally. We propose SPARE (Sparsity Allocation via Routing Entropy), a training-free, selector-agnostic method that decides how many experts to remove from each layer using routing entropy, the entropy of tokens' normalized Top-K gate weights on calibration data. When a token's gate weight is spread evenly, removing one active expert discards little of it, so SPARE prunes layers with more diffuse routing more aggressively. A perturbation bound under random pruning formalizes this intuition, and controlled interventions with a fixed selector link concentrated routing to larger output changes. With the same selector and budget, SPARE improves average accuracy over uniform allocation on Mixtral, Qwen3, and DeepSeek models, especially at high pruning ratios. At 50% expert pruning, it raises the eight-task average of Qwen3-30B-A3B from 57.2% to 63.8%, and the math, code, and science average of DeepSeek-R1 from 80.1 to 82.8.

cs.LG↗
arXiv2026

ZOMP: Zeroth-Order Multi-Modal Prompt Tuning for Vision-Language Models

Prompt tuning adapts vision--language models with few trainable parameters, but computing their gradients still requires backpropagation through frozen encoders. We introduce ZOMP, a forward-only method for deep multimodal prompt tuning under a limited loss-query budget. ZOMP combines shared prompt factors with a budget-indexed rank schedule and gradient-correction momentum. Early updates search a rank-one subspace; later updates activate additional components without discarding the existing optimizer state. With 5,000 training-loss queries, ZOMP achieves 68.2\% average 16-shot accuracy across 13 datasets, improving on ZIP by 6.0 points, alongside gains in base-to-new and distribution-shift generalization. On five image--text retrieval datasets, it outperforms four derivative-free baselines at both training sizes, improving average bidirectional Recall@1 over BPT-VLM by 2.63 points. An exploratory five-benchmark language diagnostic comparison examines caption discrimination beyond the retrieval galleries. Component, modality, depth, and budget studies characterize the method's benefits. ZOMP requires an internal-prompt inference interface and reduces allocated training memory relative to a matched-architecture first-order reference.

cs.CV↗
arXiv2026

OfficeTown: Generative Organizations for Evolving Agent Intelligence

AI agents increasingly use files and software tools to produce professional deliverables. Such work draws on materials, decisions, and feedback accumulated across assignments. We introduce OfficeTown, a generative simulation framework for professional organizations in which tasks and their context arise from continuing organizational work. From a natural-language description of an organization's purpose and activities, OfficeTown initializes an organization whose members coordinate work, delegate bounded assignments to assistant agents, and review their deliverables. Artifacts, decisions, and unresolved matters persist and shape subsequent work, while responsibilities and permissions determine what each member can see and do. We curate work requests, their context, and review feedback into executable resources for evaluation and learning. We construct OfficeTown Bench with 406 tasks and 4,836 evaluation criteria from 23 simulated organizations across eight professional domains, incorporating domain-expert feedback. Frontier-model evaluations reveal substantial remaining headroom. Supervised fine-tuning and on-policy distillation on OfficeTown data substantially improve Qwen3.5-9B on external professional-work benchmarks, including GDPval. Supplementary evaluations show that the principal--assistant harness achieves higher scores than the single- and multi-agent baselines tested. These results highlight the value of organizational simulation in generating work-grounded data and environments for the continued development of generalist agents.

cs.AI↗
arXiv2026

Spacecraft Pose Tracking via Kinematic Prediction and Selective Event Correction

In initialized spacecraft tracking, a short-horizon motion prediction remains available as event support changes. Observation-Aligned Event Innovation (OA-EI) uses events to correct selected components of this prediction. A constant-body-twist model propagates the complete pose; the event encoder proposes rotational and normalized image-plane translation corrections, retaining propagated axial depth. Candidate magnitudes come from a bounded Scale Gate and a deterministic activity factor, with empty windows returning the prediction unchanged. Evaluation uses four FRESH physical-event trajectories, twenty rollout starts, and three training seeds. Each rollout starts from two reference poses and then uses self-estimates. At 7.7 seconds, rotation and translation errors fall from 41.63°/57.28 mm for prediction alone to 15.73°/22.41 mm for OA-EI, reductions of 62.2% and 60.9%. Failure rates fall from 20.0% to 1.67%. Matched ablations favor the rotation-bearing interface for overall pose accuracy; combining scaling with activity support gives the lowest errors at every tested event-retention level. On Jetson Orin Nano, the measured in-memory update takes 44.56 milliseconds at the median and 58.77 milliseconds at P95.

cs.RO↗
arXiv2026

Holi-Spatial 360: Generative Reconstruction from Sparse Panoramas for Spatial Rendering and Intelligence

Spatial intelligence requires scalable 3D environments that are both photorealistic and semantically grounded, yet existing indoor datasets are dominated by room-scale captures and costly LiDAR acquisition. Online real-estate platforms offer abundant panoramas of diverse multi-room homes, but sparse viewpoints and texture-poor regions make reconstruction severely under-constrained. We introduce Holi-Spatial 360, a generative reconstruction and data curation framework for converting these panoramas into annotated multi-room 3D environments. Because reconstruction quality bounds subsequent generation, our Correspondence-Guided Geometric Optimization converts feed-forward reconstruction priors into reliable cross-view constraints and builds a coherent 3D Gaussian Splatting representation as 3D spatial memory. Adapted single-image and video priors then restore appearance and complete continuous trajectories while preserving observed content. The reconstructed scenes support arbitrary RGB-D rendering and an automated curation pipeline that combines end-to-end 3D grounding with VLM-based verification. Holi360 contains over 1K multi-room 3DGS scenes, more than 100K instance annotations, and 2M spatial question-answer pairs. We also introduce the Holi360 benchmark to evaluate the spatial understanding of VLMs in real-world, multi-room indoor environments. Experiments demonstrate superior reconstruction and curation quality under sparse panoramic inputs, while fine-tuning VLMs on Holi360 substantially improves spatial reasoning capabilities.

cs.CV↗
arXiv2026

From Agents to Edges: Paired Optimization for Multi-Agent Collaboration

Strong individual agents do not guarantee effective collaboration. Communication must align what one agent conveys with how another interprets and uses it. This dependency makes the communication edge a natural unit of optimization. We introduce Paired Automated Communication Optimization (PACO), which jointly optimizes the instructions at both ends of each edge and their shared communication convention in systems built on black-box language models. PACO keeps model weights, agent roles, and workflow topology fixed. A state-aware discounted bandit selects edges for refinement, while execution feedback guides paired revisions evaluated through staged end-to-end execution. The optimized instructions integrate into existing agent prompts without additional model calls at deployment. On a four-agent workflow evaluated across diverse multi-agent benchmarks, PACO consistently outperforms leading prompt-optimization and communication baselines. Configurations learned on HotpotQA retain their advantage in cross-dataset transfer without target-specific optimization. These results demonstrate that optimizing how agents communicate can substantially improve collaboration within an otherwise fixed system.

cs.CL↗
arXiv2026

AesCode: Aesthetic Code Generation with Decoupled Cross-Modal Rewards

Generating information-rich visual artifacts such as slides, posters, and dashboards as code is appealing because the outputs are structured, editable, and verifiable. Yet code models cannot see how their choices of layout and color come together on the canvas, often limiting spatial planning and aesthetic quality. Image generators excel at visual design but can misrender requested content, making their outputs unreliable targets for direct reproduction. We therefore introduce AesCode, which generates code grounded in the content prompt while using an image generated from the same prompt as an aesthetic guidance. To do so, AesCode represents the target as a design graph that describes the whole canvas and makes each property attributable. From this graph, we derive complementary cross-modal rewards: deterministic verifiers score properties parsable from code and rendering, while a VLM judge assesses the non-parsable ones with a sample-specific Visual Graph Rubric (VGR) tied to graph elements and relations. We optimize these decoupled rewards through reinforcement learning with per-channel normalization to jointly improve spatial planning, aesthetic quality, and verifiable correctness. To evaluate this setting, we build a benchmark that scores verifiable correctness and visual quality separately, with visual scores highly consistent with human judgments. We find that reference images substantially improve the visual quality of code generated by existing models, and ablations show that AesCode benefits from references both as model input and as a source of visual rewards. Relative to same-scale Qwen3-VL baselines given the same references, AesCode-8B and AesCode-32B improve visual quality by 31.1 and 22.4 percentage points, reaching scores comparable to those of closed-source frontier models such as GPT-5.5 and Claude Opus 4.8.

cs.AI↗
arXiv2026

Memento: Communicating Sensor Observations Through Shared Memory

Wireless sensing systems often transmit highly redundant observations, making communication a bottleneck for low-power devices. We present Memento, a communication system that exploits recurring content by transmitting observations by reference. The sender embeds each observation and searches a shared vector table stored in persistent memory. When it finds a sufficiently similar prior observation, it sends a compact reference; otherwise, it sends the observation itself and adds it to the table. This design shifts work from wireless communication to local computation and storage, without requiring a fixed task-specific model. We implement Memento on a microcontroller with an SD card and evaluate it on three image datasets and one radar dataset. Memento provides favorable accuracy-communication and accuracy-energy tradeoffs against compression-based and task-oriented baselines. At high-accuracy operating points, it matches cloud classification accuracy on three workloads while using 5.5 to 27.1 times less energy, and comes within 0.14 percentage points on a fourth while using 14.7 times less energy. These results show that retrieval over persistent local memory can reduce communication costs in recurrent sensing workloads.

cs.NI↗
arXiv2026

When Satellite and Street Views Disagree: Cross-View Complementarity in Disaster Damage Assessment

Satellite and street-view imagery see different parts of a damaged building: roofs from above, facades and debris from the ground. Average accuracy hides whether fusion methods use this complementary evidence. We study the conflict cases, the samples on which independently trained single-view models disagree, as a diagnostic subset. On paired collections from the 2025 Eaton wildfire and Hurricanes Ian and Milton, conflicts make up 9.6-33.2% of the test data. Fusion improves conflict accuracy over either view, yet an oracle that selects the correct single view per conflict remains 0.19-0.32 above the best evaluated fusion method. A linear fusion gate over building-visibility features, calibrated confidences, and disagreement recovers part of this headroom where ground photographs are aimed at the building: on Eaton it beats end-to-end fusion by +0.072 conflict accuracy p < 10^-4 and calibrated averaging by +0.051 p = 0.0001; on the panoramic hurricane datasets it is indistinguishable from end-to-end fusion. Cropping panoramas toward the building raises the conflict gain of fusion, whereas random crops of the same size do not. The spatial density of conflicts, computed without labels, correlates with tile-level wildfire damage Spearman r = 0.615, 25 tiles. Conflict cases thus show how much complementary evidence fusion uses, which view it carries under each hazard and capture setting, and where current methods fall short.

cs.CV↗
arXiv2026

Beyond Fault Localization: A Trajectory-Level Study of LLM Agents for Microservice Root Cause Analysis

Automated microservice root cause analysis (RCA) is usually evaluated by whether the final answer localizes the fault source. This is insufficient for on-call site reliability engineers (SREs), who need the evidence and reasoning behind the fault. Evaluating the process is hard because agent trajectories interleave free-form reasoning with heterogeneous tool calls and telemetry results, making it difficult to assess agents' behavior. To assess how well RCA agents ground diagnoses in evidence, we propose a trajectory-analysis methodology that characterizes evidence navigation and utilization, SRE-oriented diagnostic intent, and recurring failure modes. Our key insight is that fault-propagation paths give a causal reference for where agents investigate and how they use evidence. With it, we analyze 5,000 trajectories from ten framework-backbone configurations (nine agent frameworks, two backbone models) on RCABench. Correct localization can hide deficiencies in causal reconstruction. Successful investigations use retrieved evidence to guide later queries, consider broader diagnostic intents, and investigate more deeply. Failed investigations drift toward unrelated services or repeat shallow queries; recurring failures arise from omitted evidence, misinterpreted evidence, and unsupported reasoning. To test whether these patterns can guide improvement, we build a lightweight defense prototype targeting the three failure families. Across two held-out benchmarks, two backbone models, and six diagnostic frameworks, the failure patterns recur; the prototype reduces their prevalence and raises Acc@1 by 3.5-35.1 percentage points in every configuration, suggesting that the mined failures generalize and are actionable. Our findings motivate a process-level view of automated RCA, in which trajectories reveal whether a diagnosis is correct, well-grounded, and open to improvement.

cs.SE↗
arXiv2026

V-ICAL Bench: Evaluating Video In-Context Learning for Multimodal Agents in Interactive Environments

While In-Context Learning (ICL) enables models to adapt from exemplars without parameter updates, multimodal ICL remains largely underexplored, particularly regarding video demonstrations in interactive environments. For multimodal agents, learning from videos presents unique challenges: they must translate in-context demonstrations into executable policies, ground these policies in novel visual states, and iteratively refine actions based on environmental feedback. We introduce V-ICAL, a novel benchmark designed to evaluate video-based ICL for multimodal agents. Comprising 342 interactive tasks across 37 environments, V-ICAL utilizes human-curated demonstration videos as task-specific behavioral exemplars, evaluating agents through sustained interaction from a target initialization. The benchmark seamlessly connects in-context knowledge induction with core agentic capabilities, including state grounding, temporal memory, planning, and adaptation in dynamic environments. Extensive evaluations across 19 state-of-the-art multimodal agents reveal significant limitations: the best-performing model, Seed-2.1-Pro, achieves a score of only 54.4/100, while other leading models (e.g., Gemini-3.1-Pro, GPT-5.6) fail to surpass 50, far below the human baseline of 83.6. Controlled comparisons further demonstrate that current agents struggle to reliably translate video exemplars into effective policies, failing to yield consistent performance gains. Ultimately, V-ICAL exposes a critical gap in the ICL capabilities of multimodal agents, underscoring an urgent need for future research.

cs.CV↗