arXiv subjects

Jiawei Liu

Publications and source records attributed to Jiawei Liu.

At least 19 recordsLinked to original sources

arXiv2026

Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills

Autonomous agents are beginning to carry out machine-learning (ML) research end to end. These agents combine a model backbone with a harness for planning, execution, memory, and verification, but this architecture still leaves domain-specific know-how outside the agent. We call this missing layer operational knowledge, the know-how that separates knowing a method from making it work. That knowledge is not absent from the field. It appears in repositories and papers, but in forms written for human readers and too large to load during a task. Once distilled into compact, verified skills, this knowledge can be reused across tasks rather than rediscovered during each run. We present DisCo, a skill-powered research agent that creates skills and uses them during research. Its distillation runs in two complementary forms: task-agnostic, condensing the field's widely used repositories into reusable skills, and task-oriented, producing the skills a concrete task calls for. The former, applied across the open ecosystem, yields the AREX-Skill Library, with 5,000+ verified skills distilled from 1,000 widely used ML repositories and organized into 20 areas and 178 capability families. With the GPT-5.5 backbone, research harness, and downstream execution budget held fixed, the skill-equipped research agent scores 134.3% higher on MLE-bench, 34.4% higher on PaperBench, 9.2% higher on FrontierCS, and 14.0% higher on PassNet than the same agent without skills. These gains come from adding distilled operating context under that fixed setup.

cs.AI↗

arXiv2026

ARISE-RL: Agentic Rubric-Grounded Iterative Self-Evolution with Reinforcement Learning

Training open-ended agents via reinforcement learning (RL) is hindered by the lack of verifiable gold answers and scalable rubrics. Moreover, even near the model's capability boundary, long-horizon open-ended agentic tasks often yield brittle and unstable rewards, resulting in weak or noisy rollout contrast that obscures fine-grained optimization signals for group-based policy learning. To address these challenges, we propose ARISE-RL, a novel full-cycle self-evolution framework that couples a task/rubric Generator and a reasoning Solver through rubric-mediated co-evolution. The Generator grounds tool-related rubric criteria in real tool observations and is rewarded for producing valid, intermediate-difficulty tasks aligned with the Solver's evolving capability boundary. The Solver, in turn, learns from fine-grained rubric satisfaction signals through multi-step reasoning and tool use. We further introduce Reward-Gated Self-Evolution Distillation (RG-SED), which selectively distills a memory-augmented variant of the same policy back into itself only when the memory yields empirical reward improvement, thereby reducing distribution mismatch and avoiding blind imitation of noisy guidance. Finally, to support rigorous evaluation, we present ECR-Bench, an expert-calibrated rubric benchmark suite covering single-tool deep research and multi-tool travel planning. Extensive experiments demonstrate that ARISE-RL consistently achieves robust and stable overall state-of-the-art performance across all evaluated benchmarks.

cs.AI↗

arXiv2026

Discrete Diffusion Bridges for Spatiotemporally Aligned Image Translation and Generation

We propose Discrete Diffusion Bridges (DDB), a novel framework designed to resolve the fundamental spatiotemporal misalignment of standard discrete diffusion in image translation and generation. By corrupting data into a pure mask state via a random schedule, the conventional forward process induces a twofold misalignment: spatially, this pure-mask destination entirely discards the rich structural priors of the source image; temporally, the random masking order inherently contradicts the ``easy-first, hard-last'' decoding mechanism used during inference. To address this, DDB constructs a direct and efficient trajectory between domains. Spatially, we introduce a hybrid absorption mechanism that redefines the absorbing state to a stochastic mixture of mask and source tokens, effectively injecting source prior as spatial anchors into the latent space. Temporally, we design an information-guided noise schedule that quantifies semantic variation to prioritize the corruption of high-information regions at earlier timesteps. This ensures the model learns to resolve difficult semantic changes using robust context from invariant regions. Extensive experiments validate the versatility and robustness of our framework across diverse generative paradigms. DDB effectively balances edit alignment with structural fidelity across both text-guided semantic manipulation and pure structural image translation, while inherently complementing text-to-image generation and guaranteeing robust high-quality decoding under extremely low sampling steps. Code and models are available at \href{https://github.com/HKU-HealthAI/DDB}{https://github.com/HKU-HealthAI/DDB}.

cs.CV↗

arXiv2026

ALOHA IRDCs Molecular Line Follow-up: I. Gas properties and kinematics

Infrared Dark Clouds are ideal sites for investigating the initial conditions of massive star and cluster formation. The A Lei Of the Habitat and Assembly of Infrared Dark Clouds (ALOHA IRDCs), a James Clerk Maxwell Telescope (JCMT) Large Program, has mapped nearby IRDCs with SCUBA-2. Complementary molecular line observations are needed to characterise the physical, kinematic, and chemical properties of the dense gas. We aim to determine the thermal, kinematic, and chemical properties of clumps identified in the ALOHA IRDCs, and to assess their evolutionary status and level of star-forming activity. We performed single-pointing K-band and W-band observations towards 56 ALOHA IRDCs clumps using the Effelsberg 100-m and Yebes 40-m telescopes, respectively. We derived NH3 kinetic temperatures using the hyperfine group ratio (HFGR) method and identified infall and shock signatures from HCO+, H13CO+, SiO, and HNCO profiles. Water masers and NH2D emission were used as complementary tracers of chemical evolution and star formation. The clumps exhibit kinetic temperatures of 15-29 K. We detect NH2D emission towards 18 sources, with NH2D centroid velocities consistent with NH3, indicating both species trace the same dense gas component. More than half of the clumps display blue-asymmetric HCO+ profiles, identifying them as infall candidates. Water masers are detected in 22 sources, with prominent velocity ranges and variability. Broad SiO emission (>~20 km/s) indicates strong shocks, while narrower extents (<~6km/s) likely trace large-scale interactions or low-velocity shocks. The widespread infall signatures, shock tracers, masers, and NH2D emission suggest that relatively quiescent, chemically young material can coexist with dynamically active gas affected by early protostellar feedback, providing insight into the coupled physical and chemical evolution of massive IRDC clumps.

astro-ph.GA↗

arXiv2026

Enhancement-Mode Vertical $\beta$-Ga$_2$O$_3$ U-Trench MOSFET with MOCVD Regrown n$^+$ Contact Layers and Nitrogen-Implanted Current Blocking Layer

In this work, an implantation-free ohmic contact technology based on selectively MOCVD-regrown Si-doped n$^+$ layers is demonstrated for enhancement-mode vertical $\beta$-Ga$_2$O$_3$ U-trench MOSFETs. The regrown n$^+$ contact structure eliminates the need for implantation-based ohmic contact formation while maintaining excellent electrical characteristics. A multi-energy nitrogen-ion-implanted current blocking layer (CBL) followed by 1100~$^\circ$C activation annealing in N$_2$ ambient for 30 min was employed to achieve normally-OFF operation. Transmission line model measurements yielded a low specific contact resistivity of $2.65 \times 10^{-7}~\Omega\cdot$cm$^2$. The fabricated devices exhibited a threshold voltage of approximately 5~V, an ON/OFF current ratio of $1.15\times10^{6}$, a peak current density of 158A/cm$^2$, and a specific ON-resistance of 120.9~m$\Omega\cdot$cm$^2$. Three-terminal OFF-state breakdown voltages ranging from 920 to 980~V were achieved at $V_{GS}=0$~V. Multi-finger MOSFETs show current scaling to 0.25 A. These results demonstrate that selectively MOCVD-regrown n$^+$ contact layers provide a promising implantation-free approach for realizing high-performance vertical $\beta$-Ga$_2$O$_3$ power MOSFETs.

cond-mat.mtrl-sci↗

arXiv2026

Breaking Planner Integrity Boundary: Enviroment State-Text Injection Attack on LLM-Driven Embodied Agents

Large language model (LLM)-driven embodied agents rely on environment states to interpret scenes, generate high-level plans, and drive physical execution, making planner-visible state representations a critical security boundary. Existing attacks primarily manipulate user instructions, prompt contexts, model behavior, or perceptual inputs, while paying limited attention to whether environment-state text itself can serve as deceptive task evidence and propagate beyond planning to affect execution outcomes. Because embodied tasks are constrained by entity grounding, action preconditions, spatial relations, and environmental constraints, planning deviation alone does not guarantee adversarial execution. To address this gap, we investigate environment-state text as an independent attack surface and present the first closed-loop Environment State-Text Injection (ESTI) attack for LLM-driven embodied agents. Without modifying the original user instruction, model parameters, or executor, ESTI reformulates an adversarial objective as false state evidence compatible with the current environment and influences planning and execution through object properties, spatial relations, affordances, task-stage rules, and execution feedback. We further develop ESTI-Bench to evaluate attack propagation across the planning-to-execution closed loop and compare ESTI with Vanilla IPI, EIRAD, and BADROBOT across ProgPrompt/VirtualHome, VoxPoser/RLBench, and AI2-THOR/iTHOR. ESTI consistently outperforms existing baselines, improving planning-level and execution-level attack success rates by up to 89.32\% and 43.69\%, respectively. Further analysis shows that grounding, consistency, and executability jointly determine whether manipulated state evidence can propagate through the embodied closed loop and produce verifiable environmental changes.

cs.RO↗

arXiv2026

Security of Foundation-Model-Powered Embodied Agents: Attack Surfaces, Attacks, Defenses, and Evaluation

Foundation models are increasingly used for perception, reasoning, planning, and action generation in embodied agents, creating security risks that can propagate from digital inputs to physical behavior. Existing surveys often organize threats by mechanisms such as jailbreaks, prompt injection, backdoors, poisoning, or adversarial examples, but these categories do not consistently identify where an adversary first enters the embodied control loop. We present a trust-boundary-centric survey of foundation-model-powered embodied-agent security. Using a first-compromised-trust-boundary principle, we separate attack surface from attack mechanism and organize the system into five layers and twelve attack surfaces spanning the model supply chain, user instructions, context and memory, physical semantic environments, multimodal perception, world state, internal reasoning, task planning, action interfaces, middleware, multi-agent communication, and execution control. Based on 58 attack records and 61 defense records collected through August 15, 2026, we analyze representative attacks, cross-layer propagation, defense placement, and evaluation practices. Our quantitative analysis shows that attack research is concentrated on multimodal perception and action interfaces, while defenses are especially concentrated on action-level and runtime protection. Context and long-term memory, middleware and networking, world-state integrity, and multi-agent trust remain comparatively underexplored. We conclude with open challenges in state provenance, compositional defenses, long-horizon attack propagation, physical realizability, Byzantine multi-robot behavior, and unified closed-loop evaluation.

cs.RO↗

arXiv2026

SynAct: A Reasoning-Acting Large Language Model Agent for Adaptive Synthesis Optimization

Logic synthesis transforms RTL designs into gate-level netlists, where PPA results are highly sensitive to the choice of optimization commands, making synthesis tuning both high-dimensional and expensive. Previous approaches fall into two categories: automated methods, which perform black-box search over fixed action spaces with limited decision-level interpretability, and LLM-based methods, which typically generate static scripts upfront and cannot adapt to evolving circuit states. We present SynAct, an adaptive closed-loop LLM reasoning--acting agent that iteratively diagnoses live synthesis reports and reasons over the current circuit state, retrieved tool knowledge, and historical optimization experience to issue targeted commands. SynAct focuses on improving timing, particularly worst negative slack (WNS), while maintaining balanced area and power trade-offs. Experiments on a commercial synthesis tool across 14 designs show that SynAct reduces average WNS to 27% of that from bootstrap synthesis.

cs.AR↗

arXiv2026

GABench: A Comprehensive Benchmark for Evaluating LLM Agents on Graph Analysis Tasks

Large language model (LLM) agents are increasingly capable of planning, using tools, and interacting with external environments. They are typically supported by harnesses, which manage state and coordinate multi-step execution. Graph analysis provides a promising setting for evaluating their agentic capabilities, because it requires agents to access data and execute operations in a graph environment. However, existing graph benchmarks for LLMs provide limited coverage of graph tasks and graph types, making it difficult to comprehensively evaluate LLM agents. Moreover, they typically formulate graph analysis as text-based question answering, where graph information is directly provided in the prompt, limiting the evaluation of end-to-end agentic capabilities. To address these limitations, we introduce GABench, a comprehensive benchmark for agentic graph analysis. GABench spans three graph types and covers four graph analysis task categories: graph retrieval, graph theory, graph machine learning, and graph open-ended question answering. GABench also provides 84 executable tools for accessing graph data and performing diverse graph operations. Building on these tools, we develop an agentic graph analysis task generation pipeline and construct 10,400 tasks with verifiable ground truth.Using GABench, we evaluate a range of frontier LLMs and agent harnesses. Our experiments reveal three key findings: (1) Existing LLM agents still struggle with complex graph analysis tasks. (2) Harness choice significantly affects performance, yet existing harnesses remain limited on complex graph tasks. (3) Graph analysis depends more on tool-call quality than quantity. Our findings provide practical insights into the development and evaluation of LLM agents for graph analysis.

cs.AI↗

arXiv2026

RaG-Tree: Combining R-Tree and HNSW for Multi-Attribute Range Filtered Approximate Nearest Neighbor Search

Multi-attribute range-filtered approximate nearest neighbor search (MR-ANNS), which retrieves high-dimensional vectors satisfying multiple attribute constraints, is a fundamental operation in modern AI applications. Existing MR-ANNS indexes either exploit a single attribute for range localization or recursively partition objects along individual attributes, which may limit their ability to exploit attribute correlations for effective range pruning and attribute-vector correlations for efficient nearest-neighbor search. In this paper, we propose RaG-Tree, a unified index that couples an R-tree with partition-aware HNSW graphs for MR-ANNS. RaG-Tree leverages hierarchical R-tree partitions for effective range pruning and adapts the sparsity of each HNSW graph to the local vector distributions within its partition, enabling lightweight indexing and efficient query processing. To support efficient query processing and dynamic updates, we develop a cost-based adaptive search algorithm that minimizes unnecessary graph exploration, together with an efficient index maintenance mechanism for incrementally updating affected partition-aware HNSW graphs. Extensive experiments on three real-world datasets show that RaG-Tree achieves superior query performance over state-of-the-art baselines, while also providing lightweight indexing and fast incremental updates.

cs.DB↗

arXiv2026

MultiFixer: A Coordinator-Proposer Based Multi-Agent Framework For Fixing Multi-Hunk Bugs

Automated Program Repair (APR) has benefited greatly from Large Language Models (LLMs), but existing LLM-based APR methods still struggle with multi-hunk bugs that require coordinated changes across multiple locations. These bugs demand repository-level context understanding, repair-order scheduling, and effective hunk-level patch generation and selection. To address these challenges, we propose MultiFixer, a novel Coordinator-Proposer based multi-agent framework for multi-hunk repair. MultiFixer performs tool-augmented bug analysis, constructs fine-grained repair context, iteratively generates patches through a Coordinator-Proposer architecture, and applies two-stage patch refinement for syntactic and semantic correctness. We evaluate MultiFixer on 835 bugs from Defects4J and three vulnerability benchmarks. On Defects4J, MultiFixer fixes 326 bugs, including 62 multi-method and 27 multi-file bugs, and outperforms prior APR baselines in the reported comparisons with the same base model. Moreover, MultiFixer also fixes 46 multi-hunk bugs among 95 unique fixes. When combined with Claude-3.5-Sonnet, MultiFixer repairs 420 bugs, establishing a new state of the art on Defects4J. On VUL4J, MultiFixer repairs 24 real-world vulnerabilities, including 5 multi-hunk cases. On the multi-hunk subsets of SEC-bench and PatchEval, MultiFixer fixes 11 and 19 vulnerabilities, respectively, outperforming all compared baselines under GPT-3.5. These results demonstrate the effectiveness of MultiFixer for multi-hunk repair.

cs.SE↗

arXiv2026

ParasGB: A Graph Benchmark Suite for Parasitic Estimation on AMS Circuits

As chip manufacturing processes advance to deep submicron nodes, parasitic interconnect effects increasingly dominate the performance of analog and mixed-signal (AMS) circuits and often lead to costly layout iterations. This makes early-stage estimation of parasitic capacitance and resistance important for parasitic-aware design exploration before full physical implementation. However, progress on GNN-based parasitic modeling has been hindered by the lack of public, high-fidelity RC benchmarks that support reproducible evaluation. To address this gap, we introduce ParasGB, the first open-source benchmark suite for pre-layout parasitic parameter prediction on circuit graphs. ParasGB provides large-scale, heterogeneous RC networks extracted with commercial EDA tools from tape-out-proven designs, together with a unified evaluation protocol covering node-level ground capacitance, edge-level resistance, and edge-level coupling capacitance. Within this framework, we benchmark diverse GNN architectures using a standardized training pipeline and expose challenges such as extreme label imbalance, long-tailed parasitic distributions, and strong structural heterogeneity. By establishing a physically grounded and standardized benchmark for early-stage parasitic prediction, ParasGB provides an open platform for reproducible research on circuit graph learning and parasitic-aware model development. All datasets, preprocessing scripts, and configurations are publicly available in our code repository https://github.com/ShenShan123/ParasGB.git.

cs.LG↗

arXiv2026

IssueExec: A Test-Driven Approach for Localizing Software Engineering Issues

Issue localization, which identifies code locations requiring modification from issue descriptions, is a critical step in automated software maintenance. Existing approaches predominantly attempt to directly align issue descriptions with code elements, yet often struggle due to the inherent abstraction gap between the issue description and code implementation. Seeking alternative signals, our theoretical analysis suggests that test suites can serve as executable proxies for requirements, reducing localization uncertainty by 7.73 bits of entropy on average. A large-scale empirical study on 18 repositories validates this premise: existing tests cover 96.98\% of ground-truth files, and the two-hop pathway yields stronger semantic connectivity than direct matching in 82.4\% of cases. Despite their potential, leveraging tests for localization faces two key challenges: the semantic gap separating issue descriptions from test identifiers, and the substantial noise in execution traces from infrastructure code. To address these, we propose IssueExec, which bridges the semantic gap through domain-knowledge-enhanced test representations and filters noise via hierarchical trace analysis. Experiments on SWE-bench Lite show that IssueExec achieves state-of-the-art performance, improving function-level Recall@1 by 41.57\% over the strongest baseline. When integrated into the Agentless pipeline, IssueExec resolves 17.72\% more issues, demonstrating practical downstream benefits.

cs.SE↗

arXiv2026

Evidence-Grounded AI for Musculoskeletal Care

Musculoskeletal diseases are among the leading causes of disability and drive the greatest global need for rehabilitation. Because recovery, remodelling and degeneration of bones, joints and related tissues unfold over months to years, care requires longitudinal management rather than isolated decisions. Clinicians must repeatedly integrate evolving patient evidence, medical knowledge and stage-specific functional goals, yet evidence is often fragmented across visits, departments and hospital systems, disrupting continuous, individualised management. Here we report OrthoPilot, a clinical artificial intelligence (AI) system powered by a large language model (LLM) that integrates hospital data streams with authoritative external knowledge for continuous musculoskeletal care. It autonomously retrieves real-time imaging, laboratory, pathology and order data and translates evolving patient states into evidence-based decisions from admission diagnosis through rehabilitation planning. We established a specialist-validated benchmark from real-world electronic health records (EHRs) spanning 1,000 disease codes. In a full-pathway reader study against 81 orthopaedic physicians, OrthoPilot outperformed experts with 25 years of experience in diagnostic reasoning, clinical decision-making and management planning. This advantage generalised across 60 external clinical centres, where OrthoPilot surpassed all evaluated intelligent systems. In a prospective physician decision-making study of 1,870 complex cases, OrthoPilot improved full-chain management success by 10.6%. In a randomised deployment involving 8,240 inpatients, integration into routine care increased cumulative cases per bed by 9.7% and improved patient-reported access to health information. These results move clinical AI from predicting isolated events toward executing longitudinal management across complete musculoskeletal care pathways.

cs.AI↗

arXiv2026

Med-OPD: Improving Medical Vision-Language Models via Evidence-Aware On-Policy Distillation

Medical Vision-Language Models (Med-VLMs) require reliable reasoning from fine-grained visual evidence, yet existing models can produce plausible clinical answers by relying on language priors or medical templates rather than truly attending to diagnosis-critical regions. On-Policy Distillation (OPD) offers dense token-level supervision on student-generated trajectories and provides a privacy-compatible means of capability transfer without requiring the redistribution of raw patient data. However, standard OPD uniformly distills all tokens, causing sparse evidence-dependent tokens to be diluted by abundant clinical narrative tokens. Inspired by the success of OPD in the large language model community, we propose \textbf{Med-OPD}, to our knowledge the first unified post-training framework that integrates on-policy distillation with medical evidence-aware supervision for Med-VLMs. We introduce \textbf{Medical Evidence Advantage} (MEA), a teacher-grounded counterfactual signal that uses an answer-aware hint to focus teacher scoring on evidence supporting the target diagnosis, and measures each token's dependence on medical visual evidence by comparing teacher likelihoods under the original and evidence-degraded imaging modalities. Based on MEA, Med-OPD redistributes the distillation signal at both the token and trajectory levels, emphasizing diagnosis-critical tokens and evidence-reliant rollouts. Experiments on OmniMedVQA subsets show that Med-OPD consistently outperforms SFT and standard OPD across CT, MRI, Disease Diagnosis, and Lesion Grading. These results demonstrate that evidence-aware distillation can better strengthen medical VLMs' reliance on key visual evidence and improve reliable multimodal medical reasoning. The source code and data is publicly available at: https://github.com/yunhang8658/MedOPD.git

cs.CV↗

arXiv2026

CARPP: Parametric Radiative-Transfer Fitting of Molecular Cores from Dust Continuum Data

The density profiles of dense molecular cores are important indicators of their physical and evolutionary states. Multi-wavelength dust continuum data offers excellent constraints on the density profile of cores. Here we introduce CARPP (Core Analysis via Radiative Transfer and Profile Parameters), a publicly available fitting package that generates optimized core density and temperature profiles based on parameterized radiative transfer calculations. CARPP assumes spherical symmetry and adopts physically motivated parametric forms for the density and temperature profiles, and uses dust continuum data for fitting. Tests on synthetic data show that CARPP achieves high accuracy, namely averaged relative errors of CARPP's seven parameters being $<20\%$, when the data quality satisfies $\frac{\rm RMS \,\, noise}{[\rm peak \,\, flux]} < 0.025\times \frac{[r_0]}{\rm resolution} +0.05$, where $r_0$ is the core's characteristic radius. We select the low-mass core TMC-1C and the high-mass core Ori2-2 to demonstrate CARPP's performance on real data. It classifies TMC-1C as a Bonnor-Ebert sphere in near-hydrostatic equilibrium, while Ori2-2 exhibits a power-law-dominated profile indicative of a collapsing envelope. This capability establishes CARPP as a powerful and versatile tool to classify the dynamical states of individual cores. It offers an optimal balance between physical fidelity and computational efficiency, serving as a practical, standardized alternative to both over-simplified SED analyses and complex, time-intensive 3D radiative-transfer modeling.

astro-ph.GA↗

arXiv2026

Rise From The Ashes: LLM-based Static Analysis for Deep Learning Framework Bugs

Deep learning (DL) frameworks are critical AI infrastructures that often hide bugs with serious security implications. While dynamic approaches such as fuzzing are effective in uncovering these bugs, they require real test execution and incur high computational costs. Static analysis is a natural complement because it can detect bugs without runtime execution, offering fast and scalable testing. Unfortunately, there is still limited work targeting static analysis for DL frameworks due to their multilingual architectures and tensor-related program state. We present Phoenix, the first LLM-based static analysis technique for DL frameworks. Our key insight is that cross-language tensor flows in DL frameworks can be modeled, together with concrete code context, as a structured semantic bridge intermediate representation (SBIR) that LLMs can analyze for potential bugs in tensor semantic propagation. We implement this insight through a multi-agent workflow. A summarization agent first distills bug summaries from historical bug-fix patches and CWE rules. Guided by each summary, an extraction agent identifies bug-relevant repository symbols for code retrieval, and a generation agent synthesizes grounded SBIRs from the retrieved context. Finally, an analysis agent is leveraged to check SBIRs and report potential bugs. Our evaluation shows that Phoenix is a practical complement to dynamic DL framework testing for bug finding. To date, Phoenix has found 31 real new bugs in PyTorch for different heterogeneous hardware backends (Intel CPU, NVIDIA CUDA, and Apple MPS). Among them, 20 submitted bug-fixing patches have been merged into upstream.

cs.SE↗

arXiv2026

LemonHarness Technical Report

As large language model (LLM) agents are applied to longer tasks, they increasingly modify workspace state across multiple rounds of iteration. However, agents typically observe only tool outputs and log fragments, while the actual state changes occur in the file system. Without explicit workspace boundaries, state-changing operations such as file writes and temporary artifact generation may scatter changes across paths. Over time, these weakly constrained changes accumulate, making states such as modified files difficult to track. This paper presents LemonHarness, an integrated execution framework for long-horizon agents. LemonHarness establishes an explicit execution boundary by constraining state-changing operations within a clearly defined workspace and bringing model invocation, tool execution, and rule knowledge within a single controlled boundary. State-changing operations, including file writes, dependency installation, and temporary artifact creation, are executed through structured tool interfaces, with execution feedback recorded as observations available to subsequent model decisions. The system also introduces a reusable rule knowledge base, which turns recurring execution rules and acceptance criteria into runtime knowledge. LemonHarness further adds a time-aware execution mechanism that exposes elapsed and remaining budget to the model, so it can rebalance exploration, implementation, and validation effort as time pressure shifts and avoid timeouts from long waits or excessive verification. On Terminal-Bench 2.0, LemonHarness_GPT-5.3-CodeX reached 84.49% accuracy over 445 trials; pairing the same framework with the stronger GPT-5.5 backbone raised the average accuracy to 86.52% across five jobs. The results suggest that a unified runtime boundary, callable rule knowledge, and time-aware execution can improve the stability of long-horizon agent execution.

cs.AI↗