arXiv subjects

Shuo Ren

Publications and source records attributed to Shuo Ren.

At least 19 recordsLinked to original sources

arXiv2026

SkillAlign: Aligning Skill Interfaces for LLM-based Agents

Language-model agents increasingly rely on skills: reusable procedural knowledge for reasoning, tool use, and interaction. Existing work studies how skills are acquired, retrieved, compressed, or composed, but often assumes that once a skill is selected, its interface to the agent is fixed. We argue that this overlooks a key source of skill utility: the same skill can help, distract, or mislead depending on how it is exposed. We propose SkillAlign, a provider-agnostic framework that represents candidate skills as multi-view procedural cards and renders them through alternative exposure interfaces, including full instructions, hints, compressed summaries, workflows, or no exposure. This enables counterfactual evaluation where the task, agent, and candidate skills are fixed while only the exposure interface varies. Across ALFWorld and SkillsBench, we show that exposure form substantially affects task success and rendered context cost, and that compact top-k exposure can outperform full-library injection. We further conduct a replay-based policy-learning analysis on ALFWorld, showing that adaptive exposure contains learnable signal but remains far from oracle selection. Our results suggest that skill-augmented agents should optimize not only which skills to use, but also how those skills are presented.

cs.AI↗

arXiv2026

EDGE: Experience-Distillation for Guided Exploration in Agentic Reinforcement Learning

Reinforcement learning with outcome-based objectives such as GRPO enables LLM-based agents to solve complex, long-horizon tasks, yet the reusable exploration patterns embedded in interaction trajectories are largely discarded after a single policy update. Existing experience-augmented approaches retrieve historical guidance at inference time, but they apply experiences without accounting for the policy's evolving capability and create persistent dependencies on external retrieval. We propose EDGE (Experience-Distillation for Guided Exploration), a framework that treats retrieved experiences as temporary training-time scaffolds and progressively internalizes their benefits into the parametric policy. Concretely, EDGE partitions each rollout group into experience-conditioned and experience-free trajectories to estimate and admit only positive marginal gains without extra sampling, then distills the induced behavior into the base policy via a reverse-KL objective on its own empirical support. A co-evolutionary experience bank further synthesizes guidance from emerging failure modes and prunes obsolete entries as the policy evolves. Across embodied, web, and search-based QA tasks, EDGE improves over strong RL baselines by up to 12.5 points and remains effective without inference-time scaffolds or a proprietary reflector. The code is available at https://github.com/xvolcano02/EDGE.

cs.CL↗

arXiv2026

EviGraph: Evidence-Guided Autonomous Research Agents

Autonomous research agents can generate hypotheses, execute experiments, and draft manuscripts, yet their outputs often contain unsupported claims and inconsistencies between research questions, experiments, results, and conclusions. We argue that this problem is partly architectural: existing systems organize research as sequential pipelines but do not explicitly maintain or validate the evolving claim-evidence structure across stages. In this paper, we introduce EviGraph, an autonomous research framework that represents the research process as a typed evidence graph containing Problem, Gap, Hypothesis, Experiment, Finding, and Claim nodes. The graph serves as the operational state of the agent rather than a post-hoc record. EviGraph inspects evidence chains for missing dependencies, semantic misalignment, and result-claim inconsistencies, localizes the earliest weak node, and regenerates its affected downstream subgraph. Graph checkpointing prevents unsuccessful repairs from corrupting previously validated evidence. Manuscripts are generated only after every retained claim is grounded in a validated evidence chain. Experiments on ARC-Bench-ML and NanoResearch-20 show that EviGraph outperforms the compared end-to-end research-agent baselines in overall research performance, improves Claim Support Rate by 40.19% over the strongest baseline, and achieves 87.73% Experimental Data Consistency. These results demonstrate the value of explicit evidence-state maintenance for reliable autonomous research.

cs.AI↗

arXiv2026

Project2Task: Graph-Guided Project-Level Planning for Autonomous Research

Research agents can increasingly search literature, propose hypotheses, generate code, run experiments, and draft manuscripts from a single topic. However, a research project is not merely a larger task: it is a long-horizon agenda that must be advanced through multiple bounded tasks with distinct but related objectives, parallel alternatives, and dependency-aware sequences. Existing single-task systems often treat the project as one oversized task, produce a flat set of vague or overlapping tasks, or leave task boundaries and execution order to manual coordination. We introduce Project2Task, a graph-guided project-level planning layer for autonomous research. Given a project brief, it represents candidate contributions as innovation atoms and organizes them in a directed lineage graph. A lightweight Bernoulli block-model objective selects among horizontal, vertical, and hybrid portfolio decompositions. Project2Task then generates bounded tasks with explicit contribution ownership, repairs overlaps and missing execution fields, and emits dependency-aware task contracts that specify objectives, inputs, expected artifacts, evaluation requirements, boundary constraints, dependencies, and execution order. The contracts are independent of any particular downstream research executor and support integration of task outputs into a coherent project-level result. On a benchmark of ten project briefs yielding roughly 30 tasks, manuscript-based portfolio evaluation gives Project2Task an average quality score of 7.15, compared with 4.58 for the Brief Baseline and 5.31 for the Topic-only Setting. Integrating its contracts with AutoResearchClaw increases average downstream task accuracy from 0.536 to 0.759. These results demonstrate the value of explicit project-to-task planning for producing coherent, non-redundant, and executable research-task portfolios.

cs.AI↗

arXiv2026

AgenticECO: An Agentic Framework for ECO on 3D Integrated Circuits

As Moore's law slows, the industry is turning to three-dimensional integration; yet in merged 3D-IC flows, routed designs expose bond-level defects with no 2D analogue, and post-route engineering change orders (ECO) remain manual, expertise-bound work. Worse, the standard edit-then-fully-reroute practice entangles a repair with router churn, so a signoff number cannot be attributed to the edit that motivated it. We present AgenticECO, an evidence-gated tool-using agent workflow for 3D-IC ECO on the open-source TaiWei flow, paired with EcoRoute, a minimal-disturbance ECO-routing layer that drives the unmodified pinned router so a repair is attributable to its edit. Across nine matched natural defect cases under identical budgets, AgenticECO clears seven versus two for both full reroute and stock repair, at 0.66\% mean disturbance over cleared cases and zero clock nets touched, and a cross-backbone rerun under the same sealed contract clears all nine. Controlled studies show that the repair moves are necessary under preservation, that occupancy-aware choice buys legal landings rather than repair success, and that under tightened clocks minimal disturbance flips accept versus reject. Three preregistered visual studies localize the pixel instrument's edge to contested landing sites, and a preregistered blind diagnostic exactly restores every held-out injected defect, the only arm with zero wrong edits. Every accepted result passes routing, fresh extraction, max/min timing, DRC, and structural-equivalence gates. Code, environment, and per-episode audit artifacts are released as supplementary material.

cs.AI↗

arXiv2026

CLIP-3D: Closed-Loop Evaluation of Performance and Physical Constraints for 3D ICs

3D integration packs more power into a smaller footprint, so a candidate design's actual throughput depends on its layout: which macro sits on which tier, where the hot spot lands, and how cache geometry maps to access cycles. Architectural simulators like gem5 report IPC under idealized timing. They do not produce the per-block power map, the cache cycle counts, or the 3D layout that decide the realized billion-instructions-per-second (BIPS), so early-stage 3D-IC exploration selects designs without accounting for the effects that decide whether they throttle on silicon. We present CLIP-3D, a shift-left flow that exposes 3D layout-driven thermal, wire, and cache effects to early-stage architectural exploration before any sign-off tool is invoked. The first stage lifts an architectural configuration into a physical block representation: McPAT for per-block dynamic and leakage power, CACTI for cache geometry and access cycles, and a HotSpot-compatible 3D stack discretization. The second stage runs an analytical 3D thermal-aware floorplanner over that representation. The floorplanner objective embeds a closed-form sustained-frequency expression derived from the linearity of HotSpot's steady-state operator and the standard CMOS power-frequency decomposition. Cross-tier macro assignment and in-plane placement are co-optimized for the realized BIPS rather than for a half-perimeter wirelength (HPWL)-plus-temperature surrogate with hand-tuned weights.

cs.AR↗

arXiv2026

AgenticPD: A Stage-Aware Agentic Framework for Physical Design QoR Optimization

Physical design quality-of-results~(QoR) optimization is hard and expensive. Choices made at one stage can help or hurt later stages. Each evaluation requires a costly EDA run through the full flow. While existing methods still treat optimization as flat parameter tuning or a LLM-based script generation task, we present AgenticPD, a stage-aware agentic framework for physical design QoR optimization. Instead of re-running the full flow after every trial, AgenticPD is organized around the stage boundaries of the physical design flow, where a Judge Agent navigates the search and stage-specialized agents make local decisions within their own stage using stage-local tools. Additionally, the agent harness in AgenticPD provides structured observations, execution history, and agent context management. As a result, the system can branch from prior intermediate states and reuse checkpoints to continue the optimization procedure, and every candidate is evaluated at the post-route signoff. Across these baselines, AgenticPD achieves strong post-route timing while remaining competitive in power and area.

cs.AI↗

arXiv2026

Chiplet3D: Pin- and Thermal-Aware 3D Chiplet Floorplanning via Convolution-Embedded MILP

As traditional Moore's Law scaling slows down, 3D-ICs stack multiple active dies vertically to sustain performance scaling. However, this vertical stacking traps heat inside, making temperature a design concern. Although we can fix thermal issues at different design steps, floorplanning is the earliest and most cost-effective stage to solve it. Previous methods handle this by assuming wires connect to block centers and estimating temperature through simplistic power-based calculations, but these assumptions mislead their wirelength optimization and leave hotspots unresolved. To address these limitations, we present Chiplet3D, a pin- and thermal-aware floorplanner for two-die 3D-ICs. To achieve pin-awareness, it supports all four rotations and two flips, measuring wirelength from exact pin locations so the solver can flip or rotate blocks to pull connected pins closer. On the thermal side, Chiplet3D replaces the inaccurate power-based metrics of prior work with a fast, coarse convolution field embedded directly in a mixed-integer linear program (MILP) to accurately track the true 3D heat spread. We evaluate Chiplet3D on the ICCAD'24 ATPlace benchmarks, validating every temperature with a golden 3D-ICE simulation. Chiplet3D reduces wirelength by 39\%--43\% on average (and up to 62\% in the best case), while lowering peak temperatures by up to 45.9$^\circ$C and reducing thermal non-uniformity by up to 56\% compared to the SOTA baselines. Overall, these results demonstrate that by co-optimizing pin alignment and thermal fields, Chiplet3D establishes a stronger Pareto frontier between thermal-aware layout and interconnect efficiency.

cs.AR↗

arXiv2026

A$^{2}$utoLPBench: An Auto-Generated, Agent-Friendly LP Benchmark via Inverse-KKT Construction

Most LP-from-text benchmarks are static datasets of word problems written and labeled by hand. Once such a dataset is released, its size is fixed, its difficulty is fixed, and every problem can leak into the training data of future LLMs. We present \textbf{A$^{2}$utoLPBench}, a benchmark for testing LLM-driven agents on linear programming problems written in plain text. We first pick a feasible point and dual, then write down a problem for which that point is optimal and the objective value is known. The answer is known by construction, with no solver call and no human annotator. The evaluation environment bundles a reference solver-critic baseline and a Docker image whose usage instructions are written for an LLM-driven agent to read. With these in place, any agent can run the benchmark and get a calibrated score with one command. Because the benchmark is a generator rather than a fixed dataset, it has properties no fixed dataset can match: an unlimited supply of fresh problems, a difficulty knob set by $(n,m)$, ground-truth answers correct by construction, low LLM-side cost per problem relative to human authoring, repeatable scores across independent batches, and resistance to training-data leakage when fresh post-cutoff seed ranges are used.

cs.AI↗

arXiv2026

World2VLM: Distilling World Model Imagination into VLMs for Dynamic Spatial Reasoning

Vision-language models (VLMs) have shown strong performance on static visual understanding, yet they still struggle with dynamic spatial reasoning that requires imagining how scenes evolve under egocentric motion. Recent efforts address this limitation either by scaling spatial supervision with synthetic data or by coupling VLMs with world models at inference time. However, the former often lacks explicit modeling of motion-conditioned state transitions, while the latter incurs substantial computational overhead. In this work, we propose World2VLM, a training framework that distills spatial imagination from a generative world model into a vision-language model. Given an initial observation and a parameterized camera trajectory, we use a view-consistent world model to synthesize geometrically aligned future views and derive structured supervision for both forward (action-to-outcome) and inverse (outcome-to-action) spatial reasoning. We post-train the VLM with a two-stage recipe on a compact dataset generated by this pipeline and evaluate it on multiple spatial reasoning benchmarks. World2VLM delivers consistent improvements over the base model across diverse benchmarks, including SAT-Real, SAT-Synthesized, VSI-Bench, and MindCube. It also outperforms the test-time world-model-coupled methods while eliminating the need for expensive inference-time generation. Our results suggest that world models can serve not only as inference-time tools, but also as effective training-time teachers, enabling VLMs to internalize spatial imagination in a scalable and efficient manner.

cs.CV↗

arXiv2026

Cloud-native and Distributed Systems for Efficient and Scalable Large Language Models -- A Research Agenda

The rapid rise of Large Language Models (LLMs) has revolutionized various artificial intelligence (AI) applications, from natural language processing to code generation. However, the computational demands of these models, particularly in training and inference, present significant challenges. Traditional systems are often unable to meet these requirements, necessitating the integration of cloud-native and distributed architectures. This paper explores the role of cloud platforms and distributed systems in supporting the scalability, efficiency, and optimization of LLMs. We discuss the complexities of LLM deployment, including data management, resource optimization, and the need for microservices, autoscaling, and hybrid cloud-edge solutions. Additionally, we examine emerging research trends, such as serverless inference, quantum computing, and federated learning, and their potential to drive the next phase of LLM innovation. The paper concludes with a roadmap for future developments, emphasizing the need for continued research, standardization, and cross-sector collaboration to sustain the growth of LLMs in both research and enterprise applications.

cs.DC↗

arXiv2026

AstroVLM: Expert Multi-agent Collaborative Reasoning for Astronomical Imaging Quality Diagnosis

Vision Language Models (VLMs) have been applied to several specific domains and have shown strong problem-solving capabilities. However, astronomical imaging, a quite complex problem involving multidisciplinary knowledge and several subtasks, has not been adequately studied. Due to the complexity of the astronomical imaging process, both world-class astronomical organizations, such as NASA, and expert enthusiasts devote a great deal of time and effort. This is because the processes in astronomical imaging have complex underlying correlations that significantly influence one another, making the quality diagnosis and error localization of astronomical images challenging. To address this problem, we propose AstroVLM, a collaborative multi-agent system for diagnosing the quality of astronomical images. Experiment results show that AstroVLM outperforms all baselines on real-world astronomical imaging quality diagnosis tasks, providing a reference for language models to handle complicated multi-process tasks.

cs.MA↗

arXiv2026

Coherent Spin-Photon Interface of single PL6 Color Centers in Silicon Carbide

The PL6 color center in silicon carbide has recently emerged as a promising platform for quantum information processing, yet its coherent spin--photon interface has remained largely unexplored. Here we present a comprehensive investigation of single PL6 centers, combining spectroscopy with theoretical analysis. The excited-state fine structure is fully resolved using group-theoretical modeling and strain-dependent measurements. Under resonant excitation, we achieve a spin initialization fidelity of $99.69 \pm 0.03\%$ and a readout contrast of $98.31 \pm 1.03\%$. The spin--photon--entangled $A_2$ transition exhibits narrow optical linewidths ($\sim 180$~MHz) and a polarization visibility of $\sim 82\%$. Coherent optical driving enables Rabi frequencies up to $2.895$~GHz, while dynamical decoupling extends the spin coherence time from $0.5$~ms to $5.70$~ms. Our results establish PL6 as a competitive solid-state spin--photon interface hosted in a commercially available semiconductor platform.

quant-ph↗

arXiv2026

Decoherence-protected entangling gates in a silicon carbide quantum node

Solid-state color centers are promising candidates for nodes in quantum network architectures. However, realizing scalable and fully functional quantum nodes, comprising both processor and memory qubits with high-fidelity universal gate operations, remains a central challenge in this field. Here, we demonstrate a fully functional quantum node in silicon carbide, where electron spins act as quantum processors and nuclear spins serve as quantum memory. Specifically, we design a pulse sequence that combines dynamical decoupling with hyperfine interactions to realize decoherence-protected universal gate operations between the processor and memory qubits. Leveraging this gate, we deterministically prepare entangled states within the quantum node, achieving a fidelity of 90%, which exceeds the fault-tolerance threshold of certain quantum network architectures. These results open a pathway toward scalable and fully functional quantum nodes based on silicon carbide.

quant-ph↗

arXiv2025

High-yield engineering and identification of oxygen-related modified divacancies in 4H-SiC

Modified divacancies in the 4H polytype of silicon carbide (SiC) exhibit enhanced charge stability and spin addressability at room temperature, making them attractive for quantum applications. However, their low formation yield and lack of direct structural identification have hindered progress. Here, we demonstrate a controllable method for high-yield engineering and identification of oxygen-related modified divacancy color centers in 4H-SiC via oxygen-ion implantation. Based on their distinct optical and spin-resonance characteristics, we experimentally resolve four types of modified divacancies. Furthermore, by measuring isotope-resolved 17O hyperfine interactions, we identify them as the four crystallographic configurations of oxygen-vacancy (OV) complexes. Remarkably, single OV centers account for over 90% of the total defect population and exhibit superior optical properties and spin coherence compared with defects created by conventional carbon or nitrogen implantation. We characterize the zero-phonon lines of these OV centers and reveal distinct temperature-dependent behavior in spin-readout contrast. By optimizing implantation dose and annealing temperature, we achieve high-density ensembles and observe Rabi-oscillation beating patterns associated with different orientations of basal-type defects. These results establish a high-yield route for scalable engineering of these four oxygen-related modified divacancies in 4H-SiC and clarify their atomic structure, opening new opportunities for solid-state quantum technologies.

quant-ph↗

arXiv2025

SWITCH: Benchmarking Modeling and Handling of Tangible Interfaces in Long-horizon Embodied Scenarios

Tangible control interfaces (TCIs), such as appliance panels, remotes, elevators, and embedded GUIs, are a fundamental component of everyday human-built environments. Interacting with these interfaces requires agents not only to ground language in visual observations,but also to execute actions, track temporally evolving state changes, and verify whether intended outcomes have been achieved. However, existing benchmarks predominantly evaluate open-loop perception or single-step action execution, failing to capture this continuous cycle of interaction, feedback, and correction. We introduce SWITCH, a benchmark for closed-loop interactive reasoning with TCIs in realistic egocentric environments1. SWITCH comprises 1,170 temporally interactive videos across diverse functional categories, providing structured annotations of instructions, actions, state transitions, outcomes, and recovery behaviors over time. To probe generative world modeling, SWITCH also evaluates video generation models on interaction-centered tasks using both LLM-as-judge and human evaluation2.Experiments with frontier proprietary and opensource multimodal models reveal persistent weaknesses in fine-grained visual-temporal perception, outcome verification, and error recovery, highlighting SWITCH as a testbed for closed-loop embodied intelligence.

cs.CV↗

arXiv2025

Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models

Recent advances in text-only "slow-thinking" reasoning have prompted efforts to transfer this capability to vision-language models (VLMs), for training visual reasoning models (\textbf{VRMs}). owever, such transfer faces critical challenges: Effective "slow thinking" in VRMs requires \textbf{visual reflection}, the ability to check the reasoning process based on visual information. Through quantitative analysis, we observe that current VRMs exhibit limited visual reflection, as their attention to visual information diminishes rapidly with longer generated responses. To address this challenge, we propose a new VRM \textbf{Reflection-V}, which enhances visual reflection based on reasoning data construction for cold-start and reward design for reinforcement learning (RL). Firstly, we construct vision-centered reasoning data by leveraging an agent that interacts between VLMs and reasoning LLMs, enabling cold-start learning of visual reflection patterns. Secondly, a visual attention based reward model is employed during RL to encourage reasoning based on visual information. Therefore, \textbf{Reflection-V} demonstrates significant improvements across multiple visual reasoning benchmarks. Furthermore, \textbf{Reflection-V} maintains a stronger and more consistent reliance on visual information during visual reasoning, indicating effective enhancement in visual reflection capabilities.

cs.CV↗

arXiv2025

Why Do MLLMs Struggle with Spatial Understanding? A Systematic Analysis from Data to Architecture

Spatial understanding is essential for Multimodal Large Language Models (MLLMs) to support perception, reasoning, and planning in embodied environments. Despite recent progress, existing studies reveal that MLLMs still struggle with spatial understanding. However, existing research lacks a comprehensive and systematic evaluation of these limitations, often restricted to isolated scenarios, such as single-view or video. In this work, we present a systematic analysis of spatial understanding from both data and architectural perspectives across three representative scenarios: single-view, multi-view, and video. We propose a benchmark named MulSeT (Multi-view Spatial Understanding Tasks), and design a series of experiments to analyze the spatial reasoning capabilities of MLLMs. From the data perspective, the performance of spatial understanding converges quickly as the training data increases, and the upper bound is relatively low, especially for tasks that require spatial imagination. This indicates that merely expanding training data is insufficient to achieve satisfactory performance. From the architectural perspective, we find that spatial understanding relies more heavily on the positional encoding within the visual encoder than within the language model, in both cascaded and native MLLMs. Moreover, we explore reasoning injection and envision future improvements through architectural design to optimize spatial understanding. These insights shed light on the limitations of current MLLMs and suggest new directions for improving spatial reasoning capabilities through data scaling and architectural tuning.

cs.CV↗