arXiv subjects

Qi Qi

Publications and source records attributed to Qi Qi.

At least 19 recordsLinked to original sources

arXiv2026

Harbor Adapters and Harbor-Index: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation

Evaluating agents on the growing number of agentic benchmarks is challenging because they often require complex environments and agent integrations. We introduce Harbor Adapters, a unified evaluation infrastructure for agentic benchmarks. Our work makes three contributions. First, we develop benchmark adapters that port more than 80 benchmarks to evaluate arbitrary agents, and validate them through rigorous code review and parity experiments. Second, we conduct a large-scale evaluation of 8 models spanning capability tiers across 54 benchmarks; every model is run with Terminus-2 and with one of 3 native harnesses. This enables a broader analysis of agent capabilities and failure modes than was previously possible. Third, we introduce Harbor-Index, a curated set of 82 difficult, diverse, and high-quality tasks spanning 29 benchmarks, refined from the adapted suite through difficulty filtering, AI and human audit, and an audit-and-fix loop. Harbor-Index preserves the challenge and breadth of large-scale agentic evaluations while being affordable to run; no evaluated model-harness configuration exceeds 30% pass rate, and the strongest (GPT-5.5 with Codex) reaches 28.0%. We release the adapters, evaluation results, in-depth analysis, and Harbor-Index as open-source artifacts to support more reliable and comprehensive evaluation of language-model agents.

cs.AI↗

arXiv2026

Token-Level Advertising

Generative AI is transforming how people access information, challenging traditional advertising mechanisms built around predefined slots. Towards generation-native advertising, we propose the Latent Advertiser Mixture Auction (LAMA), a token-level advertising mechanism that embeds advertiser influence directly into the generation process. Advertisers report local continuation values that induce advertiser-specific next-token policies, from which the platform decodes through a latent mixture while updating an allocation posterior. We show that LAMA satisfies Markov DSIC and IR, and achieves near-optimal KL-regularized welfare. We further develop a learning-based implementation that reconstructs the required reports online from learned local advantages and root values. Proof-of-concept experiments on real-world commercial-search query splits show that LAMA improves platform welfare and revenue while maintaining user-facing response quality, providing initial evidence for the feasibility of generation-native advertising.

cs.GT↗

arXiv2026

TransRetrieval: Scaling Up Transformer-Based Retrieval for Industrial Recommendation

Applying scaling laws to recommendation retrieval is hindered by feature heterogeneity: naively stacking Transformer layers yields diminishing returns because heterogeneous fields produce severe token-norm divergence. We present TransRetrieval, a Transformer-based retrieval framework that scales with both computational budget and cross-domain data. The key enabler is (1) weighted average aggregation, which restores the homogeneous-token assumption Transformers rely on. Building on this, we introduce (2) target token compression that cuts per-candidate FLOPs by 85% while preserving cross-attention expressiveness, and (3) position-style domain embeddings that unify multiple domains at negligible additional cost, turning cross-domain data into a scaling asset. On a 40-billion-interaction industrial dataset and the public KuaiRand benchmark, scaling compute from 0.1 to 2 MFLOPs per target yields +19.3/+22.2 pt Recall@2000, confirming robust log-linear scaling. In online A/B tests, TransRetrieval lifts platform revenue by 2.53% under the same end-to-end latency constraint as the production baseline.

cs.IR↗

arXiv2026

Detecting Lorentz-violation induced by a tensor field with S-star's motion around Sgr A*

Testing Lorentz symmetry in strong gravitational fields provides a unique probe of extensions to standard model. The orbiting motions of the S-stars around the supermassive black hole Sgr~A* provide a natural laboratory for such tests. In this paper, we analyze the S2 orbital data focusing on a static and spherically symmetric black hole within Kalb--Ramond gravity, where the deviations from general relativity are encoded in a single Lorentz-violating parameter $\ell$ introduced by the Kalb--Ramond tensor field. Using a full 14-dimensional Markov Chain Monte Carlo analysis under uniform and Gaussian priors, we obtain $\ell = {1.60 \times 10^{-5}}^{+1.38 \times 10^{-4}}_{-1.76 \times 10^{-4}} $ and $\ell = {-1.02 \times 10^{-5}}^{+1.26 \times 10^{-4}}_{-1.19 \times 10^{-4}} $ at $1\sigma$ confidence level, respectively. These constraints are about three orders of magnitude tighter than those from Event Horizon Telescope imaging of Sgr~A*. We also perform MCMC simulation by fitting data of S38 and S55 stars, as well as their joint analysis. Our results show that the best fit values of $\ell$ in all simulations are always of $10^{-5}$ order, but S2 star provides the most stringent constraints on the parameters because S2 star has higher precision observational data comparing to the fewer public data for other two stars.

gr-qc↗

arXiv2026

AIGB-R1: Self-Evolving Generative Auto-Bidding via Hierarchical Planner-Executor Optimization

Auto-bidding plays an essential role in online advertising, automatically adjusting bids for advertisers to optimize their commercial goals. The emerging AI-Generated Bidding (AIGB) paradigm widely adopts generative modeling to optimize bidding strategies, yet suffers from the limited mode coverage of offline datasets and inadequate task-state understanding, hindering effective exploration of optimal strategies. Large Language Models (LLMs), with prior world knowledge and reasoning capabilities, offer a promising approach to overcome these limitations. However, directly applying LLMs to auto-bidding tasks faces inherent challenges in limited numerical precision, hallucinations, and inference latency. To address these limitations, we propose AIGB-R1, a hierarchical self-evolving auto-bidding framework aiming to enhance AI-Generated Bidding via LLMs' Reasoning capabilities, comprising a high-level Planner module for macro-level strategy planning and a low-level Executor module for fine-grained decision-making. Building upon this, we design an experience-driven self-evolving loop, enabling autonomous strategy exploration and optimization from accumulated experience. We adopt a two-stage pipeline of offline pre-training and post-training alignment, and build an interactive bidding simulation environment for strategy rollout. Furthermore, we propose Decoupled Group Relative Policy Optimization (D-GRPO) to achieve end-to-end optimization via advantage decoupling. Experimental results on a large-scale public dataset demonstrate the effectiveness of AIGB-R1.

cs.LG↗

arXiv2026

Geometry-Aware Online Scheduling for LLM Serving: From Theoretical Bound to System Practice

The explosive demand for interactive Large Language Model serving has highlighted the management of the Key-Value cache's dynamic memory footprint as a critical area for performance optimization in inference engines. Modern inference systems overwhelmingly rely on time-centric scheduling heuristics, such as Shortest Job First. However, their theoretical optimality is rooted in traditional schedule modeling, failing to capture the highly dynamic, 2D spatio-temporal geometric growth specific to LLM inference mechanisms. To resolve this, we propose the geometry-aware online scheduling by introducing the Smallest Volume First (SVF) algorithm and its highly efficient variant, 1-bit SVF. Theoretically, we provide a rigorous mathematical foundation for our approach. Via a novel volume-certificate proof, we sharpen SVF's worst-case competitive ratio from the prior best of 48 towards \textbf{3} in the high-concurrency regime of LLM serving. Building upon this core breakthrough, we complete a comprehensive theoretical taxonomy analyzing our algorithms across different traffic scenarios and information availability. Practically, we seamlessly integrate our approach as a plug-and-play layer in vLLM. Extensive evaluations on Llama-3.1 models demonstrate comprehensive performance gains: SVF delivers strong reductions in both average and tail latency, while 1-bit SVF, with merely a single bit information, achieves competitive throughput and latency. This work establishes a theoretically sound and empirically proven approach for resolving memory-constrained scheduling in modern LLM deployments. To facilitate future research, our code is available at https://github.com/Aurora-Kl/Geometry-Aware-Online-Scheduling.git.

cs.AI↗

arXiv2026

X-OmniClaw Technical Report: A Unified Mobile Agent for Multimodal Understanding and Interaction

Inspired by the development of OpenClaw, there is a growing demand for mobile-based personal agents capable of handling complex and intuitive interactions. In this technical report, we introduce X-OmniClaw, a unified mobile agent designed for multimodal understanding and interaction in the Android ecosystem. This unified architecture of perception, memory, and action enables the agent to handle complex mobile tasks with high contextual awareness. Specifically, Omni Perception provides a unified multimodal ingress pipeline that integrates UI states, real-world visual contexts, and speech inputs, leveraging a temporal alignment module to decompose raw data into structured multimodal intent representations. Omni Memory leverages multimodal memory optimization to enhance personalized intelligence by integrating runtime working memory for task continuity with long-term personal memory distilled from local data, enabling highly context-aware and personalized interactions. Finally, Omni Action employs a hybrid grounding strategy that combines structural XML metadata with visual perception for robust interaction. Through Behavior Cloning and Trajectory Replay, the system captures user navigation as reusable skills, enabling precise direct-access execution. Demonstrations across diverse scenarios show that X-OmniClaw effectively enhances interaction efficiency and task reliability, providing a practical architectural blueprint for the next generation of mobile-native personal assistants.

cs.CV↗

arXiv2026

SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks

Agent Skills are structured packages of procedural knowledge that augment large language model (LLM) agents at inference time. Despite rapid adoption, there is no standard way to measure whether they actually help. We present SkillsBench, a benchmark whose current inventory contains 87 tasks across 8 domains paired with curated Skills and deterministic verifiers. Our latest aggregate evaluation runs the 87-task benchmark under matched no-Skills and curated-Skills conditions for 18 model-harness configurations. Curated Skills raise the average pass rate from 33.9% to 50.5% (+16.6 percentage points; 25.5% normalized gain), with configuration-level gains ranging from +4.1 to +25.7 pp. Focused Skills with at most three modules outperform larger or exhaustive bundles, and smaller models with Skills can match larger models without them. SkillsBench establishes paired evaluation as the foundation for rigorous measurement of Skill efficacy on agentic, expertise-heavy work.

cs.AI↗

arXiv2026

Budget-Constrained Agentic Large Language Models: Intention-Based Planning for Costly Tool Use

We study budget-constrained tool-augmented agents, where a large language model must solve multi-step tasks by invoking external tools under a strict monetary budget. We formalize this setting as sequential decision making in context space with priced and stochastic tool executions, making direct planning intractable due to massive state-action spaces, high variance of outcomes and prohibitive exploration cost. To address these challenges, we propose INTENT, an inference-time planning framework that leverages an intention-aware hierarchical world model to anticipate future tool usage, risk-calibrated cost, and guide decisions online. Across cost-augmented StableToolBench, INTENT strictly enforces hard budget feasibility while substantially improving task success over baselines, and remains robust under dynamic market shifts such as tool price changes and varying budgets.

cs.AI↗

arXiv2026

Incentive Effects of a Cut-Off Score: Optimal Contest Design with Transparent Pre-Selection

Shortlisting is a common and effective method for pre-selecting participants in competitive settings. To ensure fairness, a cut-off score is typically announced, allowing only contestants who exceed it to enter the contest, while others are eliminated. In this paper, we study rank-order contests with shortlisting and cut-off score disclosure. We fully characterize the equilibrium behavior of shortlisted contestants for any given prize structure and shortlist size. We examine two objective functions: the highest individual performance and total performance. For both objectives, the optimal contest is in a winner-take-all format. For the highest individual performance, the optimal shortlist size is exactly two contestants, but, in contrast, for total performance, the shortlist size does not affect the outcome, i.e., any size yields the same total performance. Furthermore, we compare the highest individual performance achieved with and without shortlisting, and show that the former is 4/3 times greater than the latter.

cs.GT↗

arXiv2026

DIVER: A Robust Text-to-SQL System with Dynamic Interactive Value Linking and Evidence Reasoning

In the era of large language models, Text-to-SQL, as a natural language interface for databases, is playing an increasingly important role. The sota Text-to-SQL models have achieved impressive accuracy, but their performance critically relies on expert-written evidence, which typically clarifies schema and value linking that existing models struggle to identify. Such limitations stem from the ambiguity of user queries and, more importantly, the complexity of comprehending large-scale and dynamic database values. Consequently, in real-world scenarios where expert assistance is unavailable, existing methods suffer a severe performance collapse, with execution accuracy dropping by over 10%. This underscores their lack of robustness. To address this, we propose DIVER, a robust system that automates evidence reasoning with dynamic interactive value linking. It leverages a compatible toolbox containing diverse tools to probe the database. Then, restricted by a structured workspace (CoTF, Chain of Thoughts and Facts), it reflects based on probe results and selects a new tool for next round of probing. Through this automatically iterative process, DIVER identifies schema and value linking missed by existing methods. Based on these accurate linkings, DIVER is able to infer correct usage of SQL functions and formulas and generate high-quality evidence, achieving robust Text-to-SQL without expert assistance. Extensive experiments demonstrate that: 1) The DIVER system significantly enhances the robustness of various Text-to-SQL models, improving performance by up to 10.82% in Execution Accuracy (EX) and 16.09% in Valid Efficiency Score (VES). 2) Our dynamic interactive value linking significantly improves the robustness of existing systems and the accuracy of schema and value linking, especially when confronted with challenges posed by large-scale, dynamic database values.

cs.DB↗

arXiv2026

Probing a Lorentz-violating parameter from orbital precession of the S2 star around the galactic centre supermassive black hole

Testing Lorentz symmetry in strong gravitational fields provides a promising probe of extensions to general relativity. The supermassive black hole Sgr~A* and the orbit of the S-stars offer a laboratory for such tests in a regime beyond weak field limit. We analyze the S2 orbital data focusing on the Schwarzschild-like black hole within bumblebee gravity, where deviations from general relativity are encoded in a single Lorentz-violating parameter $\ell$. Using a full 14-dimensional Markov Chain Monte Carlo analysis under uniform and Gaussian priors, we obtain $\ell = {-8.01 \times 10^{-5}}^{+2.77 \times 10^{-4}}_{-2.09 \times 10^{-4}} $ and $\ell = {1.00 \times 10^{-5}}^{+2.90 \times 10^{-4}}_{-2.91 \times 10^{-4}} $ at $1\sigma$ confidence level, respectively. These constraints are about three orders of magnitude tighter than those from Event Horizon Telescope imaging of Sgr~A*.

gr-qc↗

arXiv2026

UniFinEval: Towards Unified Evaluation of Financial Multimodal Models across Text, Images and Videos

Multimodal large language models are playing an increasingly significant role in empowering the financial domain, however, the challenges they face, such as multimodal and high-density information and cross-modal multi-hop reasoning, go beyond the evaluation scope of existing multimodal benchmarks. To address this gap, we propose UniFinEval, the first unified multimodal benchmark designed for high-information-density financial environments, covering text, images, and videos. UniFinEval systematically constructs five core financial scenarios grounded in real-world financial systems: Financial Statement Auditing, Company Fundamental Reasoning, Industry Trend Insights, Financial Risk Sensing, and Asset Allocation Analysis. We manually construct a high-quality dataset consisting of 3,767 question-answer pairs in both chinese and english and systematically evaluate 10 mainstream MLLMs under Zero-Shot and CoT settings. Results show that Gemini-3-pro-preview achieves the best overall performance, yet still exhibits a substantial gap compared to financial experts. Further error analysis reveals systematic deficiencies in current models. UniFinEval aims to provide a systematic assessment of MLLMs' capabilities in fine-grained, high-information-density financial environments, thereby enhancing the robustness of MLLMs applications in real-world financial scenarios. Data and code are available at https://github.com/aifinlab/UniFinEval.

q-fin.GN↗

arXiv2026

ROI-Reasoning: Rational Optimization for Inference via Pre-Computation Meta-Cognition

Large language models (LLMs) can achieve strong reasoning performance with sufficient computation, but they do not inherently know how much computation a task requires. We study budgeted inference-time reasoning for multiple tasks under a strict global token constraint and formalize it as a Ordered Stochastic Multiple-Choice Knapsack Problem(OS-MCKP). This perspective highlights a meta-cognitive requirement -- anticipating task difficulty, estimating return over investment (ROI), and allocating computation strategically. We propose ROI-Reasoning, a two-stage framework that endows LLMs with intrinsic, budget-aware rationality. In the first stage, Meta-Cognitive Fine-Tuning teaches models to predict reasoning cost and expected utility before generation, enabling explicit solve-or-skip decisions. Next, Rationality-Aware Reinforcement Learning optimizes sequential decision making under a hard token budget, allowing models to learn long-horizon allocation strategies. Across budgeted mathematical reasoning benchmarks, ROI-Reasoning consistently improves overall score while substantially reducing regret under tight computation budgets.

cs.AI↗

arXiv2025

Atomically-precise synthesis and simultaneous integration of 2D transition metal dichalcogenides enabled by nano-confinement

Two-dimensional (2D) materials, such as graphene, transition metal dichalcogenides (TMDs), and hBN, exhibit intriguing properties that are sensitive to their atomic-scale structures and can be further enriched through van der Waals (vdW) integration. However, the precise synthesis and clean integration of 2D materials remain challenging. Here, using graphene or hBN as a vdW capping layer, we create a nano-confined environment that directs the growth kinetics of 2D TMDs (e.g., NbSe2 and MoS2), enabling precise formation of TMD monolayers with tailored morphologies, from isolated monolayer domains to large-scale continuous films and intrinsically-patterned rings. Moreover, Janus S-Mo-Se monolayers are synthesized with atomic precision via vdW-protected bottom-plane chalcogen substitution. Importantly, our approach simultaneously produces ultraclean vdW interfaces. This in situ encapsulation reliably preserves air-sensitive materials, as evidenced by the enhanced superconductivity of nano-confined NbSe2 monolayers. Altogether, our study establishes a versatile platform for the controlled synthesis and integration of 2D TMDs for advanced applications.

cond-mat.mtrl-sci↗

arXiv2025

Beyond Last-Click: An Optimal Mechanism for Ad Attribution

Accurate attribution for multiple platforms is critical for evaluating performance-based advertising. However, existing attribution methods rely heavily on the heuristic methods, e.g., Last-Click Mechanism (LCM) which always allocates the attribution to the platform with the latest report, lacking theoretical guarantees for attribution accuracy. In this work, we propose a novel theoretical model for the advertising attribution problem, in which we aim to design the optimal dominant strategy incentive compatible (DSIC) mechanisms and evaluate their performance. We first show that LCM is not DSIC and performs poorly in terms of accuracy and fairness. To address this limitation, we introduce the Peer-Validated Mechanism (PVM), a DSIC mechanism in which a platform's attribution depends solely on the reports of other platforms. We then examine the accuracy of PVM across both homogeneous and heterogeneous settings, and provide provable accuracy bounds for each case. Notably, we show that PVM is the optimal DSIC mechanism in the homogeneous setting. Finally, numerical experiments are conducted to show that PVM consistently outperforms LCM in terms of attribution accuracy and fairness.

cs.GT↗

arXiv2025

Merging Mechanisms for Ads and Organic Items in E-commerce Platforms

In contemporary e-commerce platforms, search result pages display two types of items: ad items and organic items. Ad items are determined through an advertising auction system, while organic items are selected by a recommendation system. These systems have distinct optimization objectives, creating the challenge of effectively merging these two components. Recent research has explored merging mechanisms for e-commerce platforms, but none have simultaneously achieved all desirable properties: incentive compatibility, individual rationality, adaptability to multiple slots, integration of inseparable candidates, and avoidance of repeated exposure for ads and organic items. This paper addresses the design of a merging mechanism that satisfies all these properties. We first provide the necessary conditions for the optimal merging mechanisms. Next, we introduce two simple and effective mechanisms, termed the generalized fix mechanism and the generalized change mechanism. Finally, we theoretically prove that both mechanisms offer guaranteed approximation ratios compared to the optimal mechanism in both simplest and general settings.

cs.GT↗

arXiv2025

AdvancedIF: Rubric-Based Benchmarking and Reinforcement Learning for Advancing LLM Instruction Following

Recent progress in large language models (LLMs) has led to impressive performance on a range of tasks, yet advanced instruction following (IF)-especially for complex, multi-turn, and system-prompted instructions-remains a significant challenge. Rigorous evaluation and effective training for such capabilities are hindered by the lack of high-quality, human-annotated benchmarks and reliable, interpretable reward signals. In this work, we introduce AdvancedIF (we will release this benchmark soon), a comprehensive benchmark featuring over 1,600 prompts and expert-curated rubrics that assess LLMs ability to follow complex, multi-turn, and system-level instructions. We further propose RIFL (Rubric-based Instruction-Following Learning), a novel post-training pipeline that leverages rubric generation, a finetuned rubric verifier, and reward shaping to enable effective reinforcement learning for instruction following. Extensive experiments demonstrate that RIFL substantially improves the instruction-following abilities of LLMs, achieving a 6.7% absolute gain on AdvancedIF and strong results on public benchmarks. Our ablation studies confirm the effectiveness of each component in RIFL. This work establishes rubrics as a powerful tool for both training and evaluating advanced IF in LLMs, paving the way for more capable and reliable AI systems.

cs.CL↗