Searcharxiv⌕ Search

arXiv subjects

Shimin Di

Publications and source records attributed to Shimin Di.

At least 19 recordsLinked to original sources
arXiv2026

FactReview: Evidence-Grounded Peer Review with Execution-Based Claim Verification

AI is accelerating scientific research, but providing timely and trustworthy feedback remains challenging. Such feedback requires evaluating specific claims against verified evidence, helping researchers and autonomous research systems determine which findings can guide subsequent work. Thorough verification is time-consuming, and reviewers under time pressure may overlook or misjudge critical issues. Existing AI reviewers have yet to fill this gap because they often assess claims without adequately verifying the supporting evidence. We introduce FactReview, a framework that verifies claims in papers to provide more trustworthy feedback. It checks claims against the literature and examines derivations, while also executing the paper's code to test empirical claims. Across 300 papers, FactReview ranks best among all evaluated systems on five of seven metrics, achieving 6.8% false support and 79.2% classification accuracy. In a study of 36 papers, reviewers using FactReview detect 9.4 issues per paper compared with 5.6 independently, while spending 74.1% less time. FactReview thus supports more reliable peer review, with the potential to accelerate research iteration. The code is public at https://github.com/DEFENSE-SEU/FactReview.

cs.AI↗
arXiv2026

TokenCast: Forecasting Token Consumption During LLM Agent Execution

When a large language model (LLM) agent executes the same task, token consumption can vary by over an order of magnitude across runs. The agent chooses its next steps based on tool feedback and intermediate results, while the growing context steadily inflates the input size of every subsequent call. The total consumption of a task is therefore hard to predict before execution and the prediction must be revised as the run unfolds. In this paper, we propose TokenCast, which learns a composable cost representation for each execution segment, recording its own consumption and the context growth it introduces. Composing adjacent segments yields a cumulative estimate that captures the extra input cost incurred when context from earlier segments is re-read by every later call. As execution unfolds, newly observed evidence refreshes the forecast, requiring no additional LLM calls and incurring a mean cumulative prediction time of 32.8 ms per run on SWE-bench Verified. Across 4 task suites and 6 agent models, TokenCast's mean absolute error reduction against the strongest comparator averages 14.5% over 96 evaluated combinations. In offline budget-control replay, TokenCast uses 21.3% fewer tokens on average than a fixed-budget policy at matched trace completion. The code is available at https://github.com/DEFENSE-SEU/TokenCast.

cs.LG↗
arXiv2026

CoRe-VLA: Preserving Cross-View Coordination in VLAs under Camera Shifts

VLAs combine pretrained vision-language representations with action generation to enable language-guided control across diverse tasks, becoming a mainstream paradigm in embodied intelligence. However, multiple studies have reported VLA's substantial declines in task success under camera shifts, revealing a key vulnerability that limits reliable deployment. To address this vulnerability, existing methods collect paired observations of the same scene from different viewpoints to fine-tune the VLA or train visual adaptation modules. Unfortunately, they require additional data collection and VLA training costs. In this paper, we first identify \emph{cross-view coordination breakdown} under external camera shifts: the robot may rely too heavily on wrist-view cues and consequently execute subtasks in the wrong order when losing global view. Motivated by this, we propose CoRe-VLA, a plug-and-play framework requiring neither additional multi-view data collection nor VLA fine-tuning, which can incorporate with exsiting VLAs. It reconstructs a scene point cloud and renders the observation from the VLA's training viewpoint to restore cross-view coordination. In CoRe-VLA, Render-to-Camera (R2C) Restoration reduces rendering-induced visual degradation, while Execution-Trajectory-Conditioned Alignment (ETCA) reduces robot idle time and mitigates motion conflicts during asynchronous execution. Experiments on 5 real-robot tasks, LIBERO-100 and LIBERO-Plus demonstrate CoRe-VLA substantially improves task success across mainstream VLAs under camera shifts. For example, CoRe-VLA raises PI0.5's success rate from 13.3% to 83.3% at a 1.6m camera shift in real-robot environment.

cs.RO↗
arXiv2026

MuPlon: Multi-Path Causal Optimization for Claim Verification through Controlling Confounding

As a critical task in data quality control, claim verification aims to curb the spread of misinformation by assessing the truthfulness of claims based on a wide range of evidence. However, traditional methods often overlook the complex interactions between evidence, leading to unreliable verification results. A straightforward solution represents the claim and evidence as a fully connected graph, which we define as the Claim-Evidence Graph (C-E Graph). Nevertheless, claim verification methods based on fully connected graphs face two primary confounding challenges, Data Noise and Data Biases. To address these challenges, we propose a novel framework, Multi-Path Causal Optimization (MuPlon). MuPlon integrates a dual causal intervention strategy, consisting of the back-door path and front-door path. In the back-door path, MuPlon dilutes noisy node interference by optimizing node probability weights, while simultaneously strengthening the connections between relevant evidence nodes. In the front-door path, MuPlon extracts highly relevant subgraphs and constructs reasoning paths, further applying counterfactual reasoning to eliminate data biases within these paths. The experimental results demonstrate that MuPlon outperforms existing methods and achieves state-of-the-art performance.

cs.LG↗
arXiv2026

Beyond Final Decisions: A Process-Centric Benchmark for Transparent AI-Assisted Peer Review

Peer review is central to quality control in science. However, existing evaluations of AI-assisted peer review mainly focus on the overall quality of generated reviews or the accuracy of final decisions. They therefore provide limited evidence about whether model decisions are supported by sufficient and reliable review evidence. We introduce a process-centric diagnostic benchmark for AI-assisted peer review. It uses (x,$z_s$,$z_c$,$z_r$,y) to represent the paper content, summary, critique, suggestion, and decision. We convert heterogeneous review records from PeerRead, NLPeer ARR-22, and OpenReview-ICLR into process-aligned data. Our benchmark uses direct decision prediction from the paper content (Direct) as its baseline. It compares the decision value of Gold-process variables and Predicted-process variables, and conducts stage-level evaluation, chain-consistency evaluation, and interventional sensitivity analysis. Experiments across three datasets and six models show that Gold-process variables generally have higher decision value. For the main analysis model, the Gold--Predicted gap remains stable across datasets and random seeds. This gap is also reproduced in most model--dataset combinations. Although model-generated intermediate review texts show relatively high local consistency across adjacent stages, the final decisions are not consistently supported by the preceding review evidence. Our benchmark targets AI systems designed to assist rather than replace human reviewers. It provides a transparent and auditable diagnostic tool for evaluating the reliability of their review processes.

cs.AI↗
arXiv2026

PeroMAS: A Multi-agent System of Perovskite Material Discovery

As a pioneer of the third-generation photovoltaic revolution, Perovskite Solar Cells (PSCs) are renowned for their superior optoelectronic performance and cost potential. The development process of PSCs is precise and complex, involving a series of closed-loop workflows such as literature retrieval, data integration, experimental design, and synthesis. However, existing AI perovskite approaches focus predominantly on discrete models, including material design, process optimization,and property prediction. These models fail to propagate physical constraints across the workflow, hindering end-to-end optimization. In this paper, we propose a multi-agent system for perovskite material discovery, named PeroMAS. We first encapsulated a series of perovskite-specific tools into Model Context Protocols (MCPs). By planning and invoking these tools, PeroMAS can design perovskite materials under multi-objective constraints, covering the entire process from literature retrieval and data extraction to property prediction and mechanism analysis. Furthermore, we construct an evaluation benchmark by perovskite human experts to assess this multi-agent system. Results demonstrate that, compared to single Large Language Model (LLM) or traditional search strategies, our system significantly enhances discovery efficiency. It successfully identified candidate materials satisfying multi-objective constraints. Notably, we verify PeroMAS's effectiveness in the physical world through real synthesis experiments.

cs.MA↗
arXiv2026

FlowEvo: Self-Evolving Agents through the Co-Evolution of Workflows and Executable Skills

Large language model agents can adapt to complex tasks by constructing workflows at inference time, but procedures discovered in one episode are usually discarded after execution. Existing skill libraries provide reusable executable routines, but are typically assembled offline and do not grow from the agent's own workflows. We introduce FlowEvo, a training-free framework in which workflows and skills co-evolve at inference time. FlowEvo compiles successful workflows into callable skills, stores them in a persistent bank, and uses retrieved skills either through direct execution or as context for constructing new workflows. It also tracks each skill's downstream utility and suppresses skills that cause negative transfer. Using a shared GPT-4o-mini backbone, FlowEvo achieves the highest accuracy among 8 baselines on the full standard splits of ALFWorld, HumanEval, MBPP, GSM8K, and MATH-500. On ALFWorld, it reaches 85.6%, 26.4 points above the strongest baseline, while using roughly one third as many tokens. Across 10 base models spanning 7B to 671B parameters, FlowEvo outperforms ExpeL in 49 of 50 model-dataset comparisons. Code is available at https://github.com/DEFENSE-SEU/FlowEvo.

cs.AI↗
arXiv2026

RobustFlow: Towards Robust Agentic Workflow Generation

The automated generation of agentic workflows is a promising frontier for enabling large language models (LLMs) to solve complex tasks. However, the empirical study reveals that existing agentic workflow generation methods are not robust. They often generate inconsistent workflows when provided with instructions that are semantically equivalent but phrased differently. This brittleness severely undermines their reliability in real-world applications. To tackle this challenge, we propose RobustFlow, a robust agentic workflow generation system that leverages preference optimization to learn invariance across instruction variations. We also introduce a benchmark of semantically equivalent instruction variants with node-level and graph-level metrics for evaluating workflow generation robustness. By training on these instruction variants, RobustFlow achieves workflow generation robustness scores of 70\%--90\% across diverse perturbations, outperforming existing approaches including AFlow and ScoreFlow. The code is publicly available at https://github.com/DEFENSE-SEU/RobustFlow.

cs.MA↗
arXiv2026

AtomBridge: Agentic VLA Inference Plugin for Long-Horizon Tasks in Scientific Experiments

Robotic laboratories play a critical role in autonomous scientific discovery by enabling scalable, continuous experimental execution. Recent vision-language-action (VLA) models offer a promising foundation for robotic laboratories. However, scientific experiments typically involve long-horizon tasks composed of multiple atomic tasks. Existing VLA models may fail to perform composed tasks formed by reordering and composing these known atomic actions. This limitation can arise from a skill-chaining gap caused by robot-state mismatch: the terminal robot state of one skill can fall outside the valid initial-state distribution of the next. To address this challenge, we propose AtomBridge, an Agentic VLA Inference Plugin for Long-Horizon Tasks in Scientific Experiments. AtomBridge attaches at inference time to a VLA policy already fine-tuned on atomic tasks, while keeping its weights fixed. At each task boundary, it uses LLM-based transition reasoning and robotic-action code generation to insert transitional actions between consecutive tasks. This plug-and-play design mitigates the skill-chaining gap caused by robot-state mismatch without additional VLA fine-tuning or demonstrations of composed long-horizon sequences. Across scientific manipulation sequences in simulation and a real-world experimental environment, AtomBridge improves execution continuity and per-step atomic-task success. On 8-step composed tasks, AtomBridge improves full-sequence success by 10%~25%.

cs.RO↗
arXiv2026

Foam-Agent: A Large Language Model-Based Multi-Agent Framework for Automating Computational Fluid Dynamics Workflows

Computational fluid dynamics (CFD) has been the main workhorse of computational physics, yet its steep learning curve and fragmented, multi-stage workflow create significant barriers to entry. We present Foam-Agent, a multi-agent framework that leverages large language models (LLMs) to automate the end-to-end CFD workflow in OpenFOAM from a single natural-language prompt. Foam-Agent rests on three methodological contributions. First, a multi-index retrieval scheme organizes domain knowledge along four complementary structural dimensions and selects indices by workflow stage, sharpening retrieval precision over conventional single-index retrieval-augmented generation. Second, dependency-aware file generation is formulated as a topological traversal of the OpenFOAM case dependency graph, so that each configuration file is synthesized in the context of its already-generated predecessors, enforcing cross-file consistency. Third, a trajectory-conditioned reviewer loop iteratively repairs failed runs by conditioning each correction on the accumulated error-and-diagnosis trajectory of its own previous attempts, applying a minimal configuration edit that targets a reduced solver-error set. Around these contributions, six specialist agents span planning, meshing, file writing, execution, review, and visualization; Foam-Agent additionally exposes its capabilities through the Model Context Protocol as a deployment surface for external orchestrators. On FoamBench, Foam-Agent achieves an 88.2% execution success rate on the 110 Basic-tier tasks and 62.5% on the out-of-distribution Advanced tier, all without expert intervention. These results show how strategic harnessing of specialized multi-agent systems can reduce expertise barriers while preserving the rigor of solver-based simulation workflows.

cs.AI↗
arXiv2026

DREvo: Distilling Recalibrated Historical Experience for Harness Self-Evolution

Harness plays a critical role in large language model agent performance, and building a high-performing harness requires substantial expert effort. Therefore, recent research has increasingly explored harness self-evolution, which iteratively proposes, evaluates, and improves harnesses using historical trial experience. However, accumulated historical experience does not always translate into stable search guidance, and performance often fluctuates substantially across evolution iterations, making it difficult to reliably discover high-performing harnesses under a limited evolution budget. We identify two limitations in how existing harness self-evolution methods leverage historical experience: (1) Lack of dynamic reassessment of whether historical experience remains valid for the current harness, and (2) Lack of explicit mechanisms for translating valid historical experience into actionable search directions. To address these limitations, we propose a new harness self-evolution method, named DREvo, which integrates function-level evidence anchoring, state-dependent evidence recalibration, and role-conditioned search intent distillation to determine which historical evidence remains valid and where the harness should evolve next. Under limited evolution budgets, DREvo exhibits smoother evolution trajectories, achieves the highest accuracy on all five benchmarks, and delivers average gains of 16.2% and 14.2% over the evaluated baselines on domain reasoning and agentic tasks, respectively.

cs.MA↗
arXiv2026

RemoteZero: Geospatial Reasoning with Zero Labels

Geospatial reasoning requires models to identify image regions that satisfy complex and often implicit user intents. Recent reinforcement learning approaches improve reasoning without manually annotated reasoning traces, but still require human-provided target labels to construct rewards, limiting their use on large-scale unlabeled Earth observation data. We introduce RemoteZero, a label-free framework for reinforcement-based geospatial reasoning. Our key observation is twofold: MLLMs are often more reliable at evaluating candidates than generating solutions, while aerial imagery reduces interference in region-level verification. Therefore, RemoteZero converts each predicted region into a visual crop and uses its semantic consistency with the query as an intrinsic reward for GRPO optimization. This formulation removes the need for human-provided solution labels and further supports iterative self-evolution by reusing previous-round models as verifiers. Experiments show that RemoteZero outperforms strong supervised baselines, applies effectively to other Earth observation tasks, and continues to improve through self-evolution as the training data expand. We hope this direction can broadly benefit the Earth observation community.

cs.CV↗
arXiv2026

UrbanAgent: A Tool-Augmented Agent for Cross-System Urban Tasks

Modern cities rely on an increasing number of digital services to operate, but residents' daily needs are still difficult to meet. Services are fragmented and have little interoperability, placing a heavy operational burden on users. Existing digital platforms, urban foundation models, and intelligent assistants each address only isolated aspects of an urban task. But they struggle to reliably convert complex natural-language requests into executable cross-system workflows. We propose Urban-Agent, a tool-augmented agent framework for cross-system urban tasks. It couples the cognitive and reasoning capabilities of a large language model with a tool-set supporting code execution, API calls, and Model Context Protocol. Through one adaptive closed loop, it clarifies missing information before acting, grounds tool use in live observations, and aligns the final response with observed evidence and task constraints. To address the evaluation gap, we introduce Urban-Eval, a benchmark specifically designed for cross-system urban request. Unlike prior benchmarks that assess either general tool use or urban knowledge and reasoning, Urban-Eval evaluates both task results and execution quality, including required tool coverage, dependency validity, and evidence traceability. Experimental results indicate that Urban-Agent reaches a 71% task success rate, 10 points above the strongest baseline. This lead holds across GPT-5-mini, Gemini-2.5-flash, DeepSeek-V4-flash, and Qwen3-235B-A22B.

cs.AI↗
arXiv2026

AI-generated Images Challenge Visual Trust in High-risk Scenarios

Rapid advances in image generation are eroding the evidentiary value of visual content in settings where authenticity can affect public safety and personal reputation. Yet existing detection benchmarks rarely examine synthetic images in public- and individual-safety contexts, where misleading visual content may carry substantial risks. Here we introduce SafeIMG, a safety-oriented benchmark spanning 12 public- and individual-safety scenarios generated using GPT Image 2. Unlike benchmarks centred on generic imagery and image-level labels, SafeIMG evaluates not only whether detectors recognise synthetic images, but also whether their decisions reflect human-identified anomalies. To this end, SafeIMG provides human annotations that localise suspicious regions and explain local artefacts and higher-level commonsense or physical inconsistencies. We evaluate specialized synthetic-image detectors and vision-language models (VLMs), and find that neither provides reliable detection. The strongest VLM identifies only 49.5% of generated images, whereas the best specialised detector identifies 33.1%, compared with 81.7% accuracy for human evaluators. Model explanations cover only 29.8\% of human-annotated anomalies and predominantly capture local defects in text, faces and hands. Their coverage falls to 15.0% for commonsense conflicts and 12.0% for physical inconsistencies, while detection performance deteriorates further after dissemination-induced image degradation. These findings show that current detectors lack the accuracy, explanatory alignment and robustness needed to evaluate AI-generated images reliably across public- and individual-safety settings.

cs.CV↗
arXiv2026

ToolRosella: Translating Code Repositories into Standardized Tools for Scientific Agents

Large Language Model (LLM)-based agent systems are increasingly used for scientific tasks, yet their practical capability remains constrained by the narrow scope of manually curated tools they can invoke. Much scientific computational functionality already exists in open-source code repositories, but these resources remain difficult to standardize, operationalize, and invoke reliably for agent use. Here we present ToolRosella, a framework that automatically transforms heterogeneous scientific code repositories into standardized, agent-invocable tools. ToolRosella combines repository analysis, tool interface construction, execution testing, and iterative repair to address the problem of repository-to-tool standardization. Across 122 GitHub repositories spanning 35 subdisciplines in six domains, ToolRosella reaches a 61.5\% repository conversion success rate after iterative repair, with a 4.4 speedup over human engineers. The resulting 1,580 callable tools support a downstream task success rate of 84.0\% and improve performance when integrated into other agent frameworks, particularly on tasks whose required tools are absent from fixed, curated inventories.

cs.SE↗
arXiv2026

Beyond Model Base Retrieval: Weaving Knowledge to Master Fine-grained Neural Network Design

Designing high-performance neural networks for new tasks requires balancing optimization quality with search efficiency. Current methods fail to achieve this balance: neural architectural search is computationally expensive, while model retrieval often yields suboptimal static checkpoints. To resolve this dilemma, we model the performance gains induced by fine-grained architectural modifications as edit-effect evidence and build evidence graphs from prior tasks. By constructing a retrieval-augmented model refinement framework, our proposed M-DESIGN dynamically weaves historical evidence to discover near-optimal modification paths. M-DESIGN features an adaptive retrieval mechanism that quickly calibrates the evolving transferability of edit-effect evidence from different sources. To handle out-of-distribution shifts, we introduce predictive task planners that extrapolate gains from multi-hop evidence, thereby reducing reliance on an exhaustive repository. Based on our model knowledge base of 67,760 graph neural networks across 22 datasets, extensive experiments demonstrate that M-DESIGN consistently outperforms baselines, achieving the search-space best performance in 26 out of 33 cases under a strict budget.

cs.LG↗
arXiv2026

TravelEval: A Comprehensive Benchmarking Framework for Evaluating LLM-Powered Travel Planning Agents

The development of Large Language Models (LLMs) has significantly improved travel planning applications, yet evaluating such models is limited by existing benchmarks' limitations: 1) overemphasis on constraint compliance, neglecting multi-dimensional qualities like spatio-temporal cost; 2) datasets lacking real-world authenticity and coverage in key areas (e.g., lodging, transport); and 3) isolated daily plan assessments that miss critical details (e.g., the impact of daily accommodation and visit pacing) needed for entire plan's evaluation. To address this gap, we introduce TravelEval, a realistic and comprehensive benchmark. TravelEval features 1) a novel six-dimensional evaluation framework to holistically assess plans across accuracy, compliance, temporality, spatiality, economy, and utility dimensions; 2) a highly realistic data sandbox with precise accommodation pricing and authentic intercity transportation data; and 3) a simulation-based global evaluation method that emulates complete travel plans with API-integrated geographic information and fine-grained queuing time. Evaluating 12 mainstream approaches with TravelEval reveals several valuable insights, such that LLMs struggle with globally-optimized multi-dimensional planning (especially in spatio-temporal reasoning and budget compliance), and agentic reasoning strategies offer no consistent improvement. Concisely, TravelEval facilitates travel plan evaluation via grounded spatio-temporal emulation and comprehensive metrics, providing a robust foundation for advancing LLM-powered travel planning research and applications.

cs.AI↗
arXiv2026

When AI reviews science: Can we trust the referee?

The volume of scientific submissions continues to climb, outpacing the capacity of qualified human referees and stretching editorial timelines. At the same time, modern large language models (LLMs) offer impressive capabilities in summarization, fact checking, and literature triage, making the integration of AI into peer review increasingly attractive -- and, in practice, unavoidable. Yet early deployments and informal adoption have exposed acute failure modes. Recent incidents have revealed that hidden prompt injections embedded in manuscripts can steer LLM-generated reviews toward unjustifiably positive judgments. Complementary studies have also demonstrated brittleness to adversarial phrasing, authority and length biases, and hallucinated claims. These episodes raise a central question for scholarly communication: when AI reviews science, can we trust the AI referee? This paper provides a security- and reliability-centered analysis of AI peer review. We map attacks across the review lifecycle -- training and data retrieval, desk review, deep review, rebuttal, and system-level. We instantiate this taxonomy with four treatment-control probes on a stratified set of ICLR 2025 submissions, using two advanced LLM-based referees to isolate the causal effects of prestige framing, assertion strength, rebuttal sycophancy, and contextual poisoning on review scores. Together, this taxonomy and experimental audit provide an evidence-based baseline for assessing and tracking the reliability of AI peer review and highlight concrete failure points to guide targeted, testable mitigations.

cs.AI↗