Search arXiv⌕ Search

arXiv subjects

Bo Chen

Publications and source records attributed to Bo Chen.

At least 37 records · Page 2Linked 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

Multi-Task Deep Recommender Systems: A Survey

Multi-task learning (MTL) aims at learning related tasks in a unified model to achieve mutual improvement among tasks considering their shared knowledge. It is an important topic in recommendation due to the demand for multi-task prediction considering performance and efficiency. Although MTL has been well studied and developed, there is still a lack of systematic review in the recommendation community. To fill the gap, we provide a comprehensive review of existing multi-task deep recommender systems (MTDRS) in this survey. To be specific, the problem definition of MTDRS is first given, and it is compared with other related areas. Next, the development of MTDRS is depicted and the taxonomy is introduced from the task relation and methodology aspects. Specifically, the task relation is categorized into parallel, cascaded, and auxiliary with main, while the methodology is grouped into parameter sharing, optimization, and training mechanism. The survey concludes by summarizing the application and public datasets of MTDRS and highlighting the challenges and future directions of the field.

cs.IR↗
arXiv2026

Structure and Implementation of New Practical English Textbooks Driven by Artificial Intelligence

Artificial intelligence is changing the form of applied English materials from fixed paper sequences to adaptive learning systems that can diagnose learners, recommend tasks, and provide formative feedback. This paper studies the structure and application of a new practical English textbook driven by artificial intelligence. A five-layer architecture is proposed: knowledge mapping, learner profiling, task generation, feedback orchestration, and teacher-side governance. A prototype was tested on 186 non-English-major undergraduates for eight weeks of teaching. Compared with a static digital textbook, the proposed system increased the unit completion accuracy from 72.4% to 84.9%, raised the average score for speaking tasks by 10.8 points, and reduced the teacher's correction time by 31.6%. Therefore, an AI-driven textbook can maintain the stability of the curriculum while providing personalised learning paths, rich practice materials and traceable classroom data.

cs.AI↗
arXiv2026

Homological Description of Equivariant Geometric Bordism

Using the evenness criterion in \cite{LCLS} and duality principle in \cite{CLT}, we construct a finite chain complex $\mathfrak{B}_{\bullet}((\mathbb{Z}_2)^k)$ built from the universal complex $X((\mathbb{Z}_2)^k)$ and its links. We then show that the equivariant unoriented bordism group $\mathcal{Z}_{k+1}((\mathbb{Z}_2)^k)$ of all $(k+1)$-dimensional smooth closed connected manifolds with effective $(\mathbb{Z}_2)^k$-actions fixing isolated points, is naturally isomorphic to $H_{k-2}(\mathfrak{B}_{\bullet}((\mathbb{Z}_2)^k);\mathbb{Z}_2)$. The vertical spectral sequence associated with the natural double-complex structure on $\mathfrak{B}_\bullet((\mathbb{Z}_2)^k)$ collapses at $E^3$, yielding an explicit formula for $\dim_{\mathbb{Z}_2}\mathcal{Z}_{k+1}((\mathbb{Z}_2)^k)$ for every $k$.

math.AT↗
arXiv2026

Token Counts Are Not Model Lineage: A Frozen-Threshold Holdout Study of Black-Box LLM API Fingerprinting

Black-box model attribution is increasingly relevant when large language models (LLMs) are served through relay and reseller APIs. A tempting low-cost signal is the prompt-token count returned by an OpenAI-compatible endpoint: two models that share a tokenizer and chat template may produce the same count sequence up to a fixed offset. Yet the validity of this signal for broader \emph{model-family} attribution has received little direct holdout testing. We conduct a frozen-threshold study over 24 labeled endpoint pairs, split evenly into a development set and an untouched holdout set, with three temporal repeats and 30 controlled texts per pair. We introduce a validity-gated result contract that distinguishes an observed dissimilarity from an uninformative measurement caused by missing usage data, rate limits, or endpoint policy. The resulting shift-invariant exact-match score perfectly separates the 12 development pairs, yielding a frozen threshold of 0.725. On holdout, however, only 6 of 12 pairs are eligible under the pre-specified three-repeat rule. Among eligible pairs, balanced accuracy is 0.75, sensitivity is 0.50 (95\% Wilson interval 0.15--0.85), and specificity is 1.00 (0.342--1.00). Two same-family pairs---Qwen 3.8 and DeepSeek V4 variants---fall below the frozen threshold. Across 4,320 formal API calls, every log is replayable, while holdout contains 189 non-200 responses and 157 successful responses without prompt-token usage. The study therefore validates token-count consistency as a fingerprint of a shared \emph{tokenization stack}, but rejects its use as a standalone necessary test for model-family lineage.

cs.CL↗
arXiv2026

Yang-Mills-Higgs-Schrödinger flow

In this paper, we initiate the study of the Yang-Mills-Higgs-Schrödinger(YMHS) flow, i.e. the Hamiltonian flow of the Yang-Mills-Higgs functional defined on a symplectic fiber bundle. The YMHS flow provides a natural gauge-theoretic extension of the classical Schrödinger flow within the framework of symplectic reduction theory, and generalizes the Chern-Simons-Schrödinger equations to a non-Abelian gauge and non-linear fiber setting. We study its geometric structures and establish the local well-posedness of the corresponding Cauchy problem on compact Riemann surfaces.

math.DG↗
arXiv2026

On-Policy Self-Distillation in Diffusion Models

Reinforcement learning can align diffusion models with human preferences and task-specific objectives, but endpoint rewards do not specify how an intermediate denoising prediction should change. We introduce DiffusionOPSD as an on-policy self-distillation framework that converts image-level reward guidance into explicit targets for clean-output predictions at sampled queries. At each outer iteration, a frozen behavior policy generates trajectories and supplies query states and anchors. Reward gradients construct bounded positive and negative targets around each anchor. The trainable policy fits these targets as detached supervision through finite fitting before an exponential moving average update refreshes the behavior policy. This setup lets us measure target construction and finite realization separately. Controlled same-query experiments show that larger target-construction gains do not necessarily translate into larger realized gains after a single fitting update. Across SD 3.5-M and the step-distilled Z-Image-Turbo, our approach achieves the best final held-out scores in 19 of 20 reward-matched settings across two backbones and ten evaluators. It outperforms the strongest competing method by up to 44.0% and reduces training GPU-hours relative to DiffusionNFT by 40% on SD 3.5-M and 63% on Z-Image-Turbo. These results support on-policy self-distillation as an efficient and analyzable approach to diffusion post-training by converting image-level reward guidance into explicit and continually refreshed intermediate supervision, thereby opening a path toward more efficient and diagnosable alignment.

cs.CV↗
arXiv2026

RetroDFM-R: Reasoning-Driven Retrosynthesis Prediction with Large Language Models via Reinforcement Learning

Retrosynthetic planning is a cornerstone of organic synthesis and drug discovery. Yet existing AI methods often rely on pattern matching rather than transferable chemical reasoning, limiting both generalizability and interpretability. Here we introduce RetroDFM-R, a reasoning-driven large language model (LLM) for chemical retrosynthesis. Leveraging large-scale reinforcement learning, RetroDFM-R moves beyond black-box prediction by coupling improved accuracy with transparent, step-by-step rationale. On the USPTO-50K benchmark, RetroDFM-R achieves 60.4% accuracy without augmentation and 66.1% with the full inference setup, outperforming previous state-of-the-art baselines. Beyond standard metrics, double-blind expert evaluation further supports the chemical plausibility and practical utility of its proposed pathways. We also demonstrate that RetroDFM-R can reconstruct complex, multistep synthetic routes for real-world pharmaceuticals and self-assembled monolayer materials. By making its reasoning explicit and human-interpretable, RetroDFM-R addresses a key barrier to trust and supports practical deployment in automated retrosynthetic planning.

cs.CE↗
arXiv2026

Outcome Disclosure and Temporal Refinement in Multi-Battle Team Contests

A team-contest designer values output rather than expenditure; nonlinear conversion makes the distinction consequential. We study two non-pecuniary instruments in majority-rule contests decided by pairwise all-pay battles with private abilities: disclosing resolved outcomes and splitting the battle schedule into finer blocks. Neither changes a battle's average pivotality; each only redistributes it across histories. Under nested information structures, this redistribution makes equilibrium ability-scaled expenditure weakly more dispersed player by player without changing its mean; expected aggregate expenditure is invariant across all designs considered. The resulting convex-order comparison ranks expected total output: convex output costs favor no disclosure and coarser temporal structures, concave costs favor full disclosure and finer ones, and linear costs make both comparisons neutral. The rankings hold for finite-support and smooth continuous-type ability distributions. The mechanism extends to degree-zero component contest technologies with a unique equilibrium outcome distribution. No and full disclosure bound every admissible public garbling.

econ.TH↗
arXiv2026

SxSSD: A Secure and Extensible Software-defined Solid State Drive

Solid-state drives (SSDs) are built on NAND flash memory and expose it to the operating system through a block-based storage interface. As NAND flash has special read/write constraints due to its hardware nature, a translation between OS-level I/Os and raw flash memory I/Os is needed. This results in a flash translation layer (FTL) that creates a ``trusted computing base'' due to its physical isolation from the OS. Building on this trusted computing base, some security designs (e.g., data recovery from malware attacks) can ensure strong data security properties even if the OS is compromised. However, they mostly require modifying the FTL's firmware code, which is hard in practice because the traditional block-based FTL does not provide an interface to modify its internal functions. New flash storage interface designs, such as open-channel SSDs or zoned namespaces, have moved key FTL functions into the OS. These interfaces ease modification of FTL functions, at the cost of blurring the trusted boundary, as the FTL is no longer isolated from the OS. In this work, we have introduced SxSSD, a secure yet extensible software-defined SSD design. By decoupling internal policy definitions from primitive FTL mechanisms, we allow trusted applications to dynamically and securely define FTL policies and the exposed storage interface (achieving increased flexibility compared to open-channel and zoned namespaces SSDs). Most significantly, SxSSD retains the isolation of traditional FTL execution (achieving security similar to traditional block-based SSDs). We have identified and addressed key security challenges introduced under a compromised OS. In addition, we have implemented a prototype of SxSSD and evaluated its overhead with different FTL policies and storage interfaces. Experimental evaluation demonstrates that the overhead incurred by SxSSD is small compared to native FTL implementations.

cs.CR↗
arXiv2026

Representation characterization of equivariant geometric bordism

Let $G_k=(\mathbb Z_2)^k$. We establish a representation characterization determining when finitely many faithful $G_k$-representations can serve as the fixed-point data of a smooth closed $G_k$-manifold. By partitioning representations via multiplicities of nonzero weights $ρ$ and isomorphic restrictions to $\ker ρ$, we formulate an evenness condition; realizability is equivalent to this condition, yielding a finite local restatement of the tom Dieck--Kosniowski--Stong integrality criterion. As an application, we prove that $\dim_{\mathbb Z_2}\mathcal Z_4(G_3)=32$ and exhibit 32 basis elements represented by $G_3$-actions on $\mathbb RP^2\times\mathbb RP^2$, $\mathbb RP^4$ and $\mathbb RP(γ\oplusγ\oplusγ\oplus\underline{\mathbb R})$, obtained from three basic actions by precomposition with automorphisms of $G_3$.

math.AT↗
arXiv2026

A Runtime Decentralized Attestation and Coordinated Repair Framework for Securing Automotive ECUs

The evolution of automotive technology increasingly integrates components, transforming vehicles into interconnected systems of systems. Modern vehicles are controlled by a distributed system of computing devices, known as electronic control units (ECUs). However, this interconnectedness means that any error poses significant risks to the vehicle operator. In particular, malware can be injected into ECUs, threatening vehicle safety. To address this, we need mechanisms to detect compromised ECUs then repair them to a benign state. Existing approaches mainly focus on detection and do not address the challenge of integrating detection with runtime ECU repair. This integration is nontrivial because runtime repair involves both local rollback and reboot with timing determined from global vehicle context to avoid unsafe behavior. In this work, we have designed DACER, a runtime decentralized attestation and coordinated repair framework for automotive ECUs. DACER is the first approach that co-designs attestation and repair to unify the ``local'' nature of firmware rollback with the ``global'' nature of ECU reboot. In DACER, each ECU performs efficient local self-attestation and self-repair functions, enabling low-overhead coordination for distributed operations. In addition, DACER takes advantage of the hierarchical vehicle computing architecture. Our resulting DACER design checks the entire state of the vehicle, resists single points of failure, conforms to real-time constraints, and enables firmware restoration during runtime. The key functions are enabled by the ARM TrustZone equipped within each ECU and the secure flash memory controller embedded in the storage device. We implemented DACER on real-world hardware and experimentally demonstrated its low overhead.

cs.CR↗
arXiv2026

From Runnable to Verifiable: An Independent Reproducibility Study of LLM/Agent-Driven Vulnerability Validation Artifacts

Security research artifacts---repositories, PoC exploits, and validation pipelines---are increasingly produced by LLM/agent-driven vulnerability workflows, yet the gap between \emph{publicly available}, \emph{runnable}, \emph{signal-producing}, and \emph{semantically confirmed} artifacts is poorly measured. We conduct a pre-registered reproducibility audit of this literature. A search covering 2023--2026 with dual screening yields a 104-paper consensus corpus, of which 59 papers (56.7\%) have a publicly reachable artifact. We execute an 18-paper sample at R0/R1 and all 102 cases of the anchor benchmark (arXiv:2509.24037), with patched-counterfactual verdicts on 30 signal-producing cases and matched-negative-control verdicts on 19. Three findings stand out. First, 58/102 (56.9\%) anchor cases contain a script-internal CVE identifier that diverges from the declared directory CVE. Second, only 10/18 (55.6\%) paper-level artifacts complete their declared workflow at R0, rising to 11/18 (61.1\%) after environment-only R1 repair. Third, artifact-embedded oracles prove unreliable: 20/30 patched-counterfactual audits still produce the claimed signal on the patched build, 7/19 matched negative controls still trigger on benign input, and the oracle confusion matrix has sensitivity 60\% and specificity 45\%. A trigger on the vulnerable build is not evidence of CVE-specific reproduction without a clean patched counterfactual. These are exploratory results from a pre-registered protocol, and our protocol---pre-registered post-conditions, R0/R1 repair ladder, G1--G3 semantic evidence levels, and patched-counterfactual oracles---is a reusable template for the security reproducibility community.

cs.CR↗
arXiv2026

Quasi-Sinusoidal Single Diamond Structure in Royal Jewel Butterfly: An Angle-Independent Photonic Structure

Structural colouration with narrow spectral photonic bandwidth and high reflectivity is of critical importance for modern optical applications, including displays, laser systems, and optical sensing, etc. Achieving such angle independent colouration typically relies on polycrystalline or inherent structural disorder. However, balancing angular uniformity with high brightness and strong colour contrast remains challenging. Herein, we uncover the structural origin of the spectacular bright, angle-independent blue colouration of Hypochrysops polycletus, a sapphire-like Royal Jewel butterfly. Three-dimensional (3D) electron microscopy reveals that the dorsal wing scale has a single diamond structure, a 3D photonic crystal previously documented only in beetles and weevils. The crystal domains form an extraordinary quasi sinusoidal surface geometry with a distinct template morphology-guided arrangement. Unlike typically thicker biophotonic structures that support multiple high symmetry stopbands, this design contains only 3-4 unit cells in the propagation direction. Its optical response is dominated by the fundamental stopband, with two dominant scattering mechanisms: specular reflection at the {111} inclined sidewalls of the hierarchical structure, and funnelling into localised quasi-normal modes enabled by a strongly anisotropic Bloch transport. By mimicking these features with two-photon polymerisation, we artificially reproduced the optical response in the infrared region. The study opens a pathway towards bioinspired brilliant diffuse colouration and angle-robust photonic devices.

physics.optics↗
arXiv2026

Hierarchical Quantization with Domain-Adaptive Sparse Routing for Generative Cross-Domain Recommendation

Generative Recommendation (GenRec) represents a promising paradigm that achieves remarkable empirical success by encoding items as compact Semantic IDs (SIDs) and modeling user behavior via next-token prediction across diverse recommendation scenarios. Extending this paradigm to cross-domain recommendation is challenging because a unified model must accommodate heterogeneous item semantics and behavioral patterns across domains. Existing methods commonly rely on globally shared representations or lightweight domain adaptation, which may provide insufficient capacity for modeling heterogeneous patterns at different semantic granularities. To address these challenges, we propose HD-Rec, a unified generative framework for cross-domain recommendation. HD-Rec employs a hierarchical domain-aware quantizer that constructs semantic identifiers using globally shared coarse-level codebooks and adaptively routed fine-level codebooks. It further introduces a domain-adaptive sparse mixture-of-experts module that combines a continuously activated shared expert with a dynamically selected specialized expert. To improve the coherence of multi-token item representations, we develop a cross-granularity routing consistency objective that regularizes token-level routing decisions toward their item-level consensus. Experiments on three public cross-domain recommendation benchmarks show that HD-Rec consistently improves over competitive sequential, generative, and cross-domain recommendation baselines.

cs.IR↗
arXiv2026

Reachability under arc crossing changes

Cericola proved that every knot diagram can be transformed into an ascending unknot diagram by arc crossing changes. We refine this result for all diagrams on a fixed R1-reduced classical knot shadow with more than three crossings. Apart from at most two source diagrams, any two diagrams of the same state parity are mutually reachable. Each source diagram reaches every non-source diagram of its parity but cannot be reached from another diagram. A local five-occurrence condition on the marked Gauss word characterizes the sources and thereby determines the full directed reachability relation.

math.GT↗
arXiv2026

SITA: Semantic Interest Tokens for Target-Aware Compression in Long-Sequence Recommendation

As user behavior histories continue to grow on modern Internet platforms, effectively modeling long behavior sequences has become crucial for predicting user interests in candidate items. Existing methods have evolved along two directions. One line dynamically retrieves target-relevant behaviors from long histories, enabling target-aware modeling but requiring target-dependent computation during inference. The other line compresses entire behavior sequences into compact user representations, achieving high efficiency and scalability but sacrificing target-specific adaptation due to target-independent encoding. The key challenge is therefore to enable target-aware modeling while preserving the efficiency and scalability of compressed user representations. To address this challenge, we propose \textbf{SITA}, a target-aware compression framework for long-sequence recommendation. SITA enables target-aware compression by organizing compressed interests into semantic structures through semantic identifiers learned via parallel semantic quantization. Conditioned on the semantic identifier of the target item, SITA adaptively aggregates the corresponding structured interests to construct the target-specific user representation. Extensive experiments on public datasets and a large-scale industrial dataset demonstrate that SITA consistently outperforms representative baselines while maintaining strong scalability, highlighting its strong potential for real-world recommender systems.

cs.IR↗
arXiv2026

Universal Speed Limit in a Far-from-Equilibrium Bose Gas: Symmetry and Dynamical Decoherence

Predicting universal transport coefficients in far-from-equilibrium quantum systems remains a fundamental challenge. A paradigmatic example is the non-thermal fixed point (NTFP) of isolated Bose gases, where coherence spreads as $\ell^2(t) = C\hbar t/m$ with a universal constant $C$. While the scaling exponent $z=2$ is well established, the amplitude $C$ has remained elusive because the underlying particle cascade $n(k)\sim k^{-4}$ leads to a divergent kinetic energy, threatening the very existence of a constant speed limit. Here we resolve this paradox and present the first analytical, parameter-free prediction of a universal amplitude $C$. A deep interplay between symmetry and dissipation is uncovered. The emergent weak U(1) symmetry at the NTFP enforces a conserved total current, forcing the low-energy phase dynamics to obey a diffusive Langevin equation with noise entering as the divergence of a stochastic current. This structure, combined with dynamical decoherence of high-momentum modes, yields a universal power-law momentum distribution $\tilde{f}(v)\sim(1+v^2)^{-3}$ (with $v=k\ell$) that naturally regularizes the ultraviolet divergence. From this, a parameter-free geometric baseline $C=3$ is obtained, independent of microscopic details. The experimental value $C=3.4(3)$ [Martirosyan et al., Nature 647, 608 (2025)] is then shown to be quantitatively consistent with universal logarithmic corrections arising from a marginally irrelevant coupling at the fixed point. A new paradigm is thus established for predicting transport coefficients in strongly correlated non-equilibrium systems: symmetry constraints determine the low-energy effective theory, dynamical decoherence provides a natural ultraviolet completion, and scaling analysis delivers testable predictions moving beyond scaling exponents to quantitative amplitude prediction.

cond-mat.quant-gas↗