Search arXiv⌕ Search

arXiv subjects

Chen Zhang

Publications and source records attributed to Chen Zhang.

At least 55 records · Page 3Linked to original sources
arXiv2026

Do simulated agents move like real people?

Human mobility is increasingly represented using synthetic populations that offer scalable alternatives when individual-level observations are unavailable or sensitive. Yet validation typically emphasizes aggregate statistics, which can obscure whether simulated agents traverse transportation networks in ways that resemble real travelers. Here, we develop a path-centric framework that combines direct path-level comparisons with higher-order network models to compare observed and simulated mobility on a shared metropolitan road network. Observed and simulated paths share broad statistical regularities and short-range memory. Beyond these similarities, however, simulated mobility underrepresents long paths, exhibits greater redundancy among long route sequences, covers a smaller and partly different portion of the network, and is more predictable overall. These discrepancies show that agreement in aggregate mobility patterns does not imply fidelity in how travelers move through the underlying infrastructure. Higher-order path analysis therefore offers a framework for validating synthetic mobility at the spatial and sequential scales relevant to scientific inference, urban planning, and policy.

cs.CE↗
arXiv2026

ContextPipe: Database-Inspired Context Assembly for Long-Horizon Agents

Long-horizon large language model (LLM) agents require context assembly: the runtime must decide what to include in each prompt, in what order, and when to compact history under a hard context-window budget and a byte-sensitive prompt cache. In production agentic systems, this logic is scattered across prompt builders, ad hoc compaction routines, cache-break workarounds, and per-provider shims. We argue that context assembly is structurally isomorphic to query execution in a relational database: both execute under a hard budget, exploit a tiered cache, and leverage statistics. We adopt this discipline in ContextPipe: a five-phase pipeline (Plan Bind Optimize Execute Feedback) backed by a structured data-source catalog, a deterministic cache-aware optimizer, and an EXPLAIN ANALYZE trace. We show that context in ContextPipe is auditable, replayable, and failure-isolated. A preliminary evaluation using the SWE-bench Pro Qutebrowser subset shows that, compared with the append-only context construction policy, ContextPipe reduces total token volume by 31%, LLM calls by 23%, and response time by 9%, at the cost of a lower KV cache-hit ratio.

cs.AI↗
arXiv2026

Harness-of-Harness: Multi-Day Autonomous Software Development with Continual Improvement

This paper studies autonomous software development, in which LLM-based coding agents transform high-level requirements into complete, functional, and usable software systems without human intervention. We introduce Harness-of-Harness (HoH), a framework that enables coding agents to continually improve software during autonomous development. HoH operates on existing coding-agent harnesses, and organizes their executions into iterative planning-coding-testing loops. To sustain improvement across loops, HoH balances repair with capability growth, scopes development into small and verifiable increments, separates implementation-time testing from independent evaluation, and constrains verifiable outputs rather than prescribing agent workflows. It progressively exposes deliverables, role-specific tools, and skills, encourages reuse rather than recreation, and maintains versioned project histories. On GameCraft-Bench, FrontierSWE, and ProgramBench, three harness-model pairs (Codex with GPT-5.5, OpenCode with DeepSeek-V4-Pro, and Pi with MiniMax-M3), HoH consistently outperforms the corresponding standalone harnesses, achieving an average relative gain of 52.25 percent and a maximum gain of 82.86 percent after three iterations. In a multi-day deployment with more than 70 iterations, HoH autonomously develops a first-person-shooter game, featuring a coherent storyline, fully implemented core mechanics, human-playable experience, polished visuals and integrated audio. Github: https://github.com/Flesymeb/HarnessOfHarness Project Page: https://flesymeb.github.io/HarnessOfHarness/

cs.AI↗
arXiv2026

Skill-as-API: Confidential Multi-Agent Coordination for Agentic Software Engineering

AI coding agents are evolving from solitary tools into collaborative teammates that discover and invoke one another's specialized skills. But the coordination channel itself can leak a skill's intellectual property. Protocols such as MCP and A2A run implementations server-side, yet they still publish each skill's description and typed schemas to every peer, offer no way to hide a skill's existence, and cannot guarantee that a wrapped system prompt stays off the wire. Application-layer privacy filters help, but act only after the model has decided to emit sensitive text. We take a complementary, protocol-layer route: Skill-as-API, a coordination protocol whose public view of a skill is limited to its name, description, typed input/output schemas, and trust tier. The skill body is closure-captured in the owner's process and never crosses the wire. Four layers add access control and narrow the prompt-injection surface structurally rather than by filtering content. We provide an open-source Python implementation over XMTP with 1.8-2.9 s cross-continent hot-reconnect latency, and a software-engineering case study in which three agents coordinate a pull-request review while each retains ownership of its proprietary analysis prompts.

cs.CR↗
arXiv2026

Closing the Verification Loop: Self-Check Captioning for Long-Paragraph Detailed Audio Captioning

Long-paragraph detailed audio captioning, which requires dense and transcript-faithful descriptions of fine-grained audio content, remains unsolved for current audio-visual multimodal language models. We attribute this failure to two structural problems. The first is data poverty, as no public corpus jointly provides long clips, paragraph captions, and verbatim-transcript fidelity. The second is generation-mode failure, evidenced by a 44.8 to 46.4 percentage-point gap between right-audio and shuffled-audio multiple-choice question (MCQ) accuracy. We address both within Self-Check Captioning (SCC), a unified framework that instantiates audio-grounded question answering as the verification primitive at every lifecycle stage. SCC yields three artifacts. Long-paragraph Audio Caption 50k (LACap-50k) is a 50,222-clip audio-visual corpus with 491.5-word captions and a post-hoc automatic speech recognition (ASR) audit. Layer-Curvature Supervised Fine-Tuning (LC-SFT) is the first on-policy supervised fine-tuning method to weight tokens by intermediate-layer evidence, motivated by our identification of Late-Layer Semantic-Entropy Collapse (SEC). SCC-Verifier arbitrates among caption rollouts via audio-grounded self-answering at inference. Across multiple benchmarks, our system attains state-of-the-art among open-source captioners and is competitive with proprietary baselines. We release LACap-50k to fill the resource gap for long-paragraph detailed audio captioning research.

cs.SD↗
arXiv2026

A variation of the Morris constant term

The Morris constant term identity is important due to its equivalence with the well-known Selberg integral. We find a variation of the Morris constant term, denoted $h_n(t)$, in the study of the Ehrhart polynomial $H_n(t)$ of the $n$-th Birkhoff polytope, which consists of all doubly stochastic matrices of order $n$. The constant term $h_n(t)$ corresponds to a particular constant term in the study of $H_n(t)$. We give a characterization of $h_n(t)$ as a polynomial of degree $(n-1)^2$ with additional nice properties involving the Morris constant term. We also construct a recursion for $h_n(t)$ using a similar technique for the proof of the Morris constant term identity by Baldoni-Silva and Vergne, and by Xin. Using this method, we have produced explicit formulas for $h_n(t)$ for $3 \le n \le 29$ without difficulty.

math.CO↗
arXiv2026

Large-Scale Bayesian Tensor Reconstruction via Approximate Message Passing

While CANDECOMP/PARAFAC (CP) decomposition (CPD) is fundamental for tensor reconstruction, Bayesian CPD often scales poorly because variational updates require repeated matrix inversions. We develop CP generalized approximate message passing (CP-GAMP) for incomplete noisy Bayesian CPD. The algorithm uses Gaussian message approximations to avoid high-dimensional inversions, and it combines a Bernoulli-Gaussian prior with expectation-maximization updates to estimate effective CP rank and noise variance. We also give a formal state evolution (SE) recursion and relate its fixed points to replica-symmetric saddle points, so CP-GAMP's SE-predicted error can be compared with the formal replica-symmetric minimum mean-squared error (MMSE) benchmark in the matched limit. Synthetic and image-inpainting experiments show that CP-GAMP substantially reduces runtime relative to variational Bayesian CPD while maintaining competitive reconstruction accuracy.

cs.LG↗
arXiv2026

Jigsaw-CRL: Recovering Global Latent Causal Order from Fragmented Multi-Client Interventions

Causal representation learning (CRL) aims to recover latent causal variables and their structural relations from high-dimensional observations. Existing CRL methods typically assume that all environments are defined over the same latent variables, or at least share a common latent representation space. We study a fragmented multi-client setting, where multiple clients interact with the same global latent causal system but each client only accesses and intervenes on a subset of the latent variables. In this regime, marginalizing unused latent variables induces bidirected edges, so a single client no longer admits a node-wise latent causal graph, and the global latent causal order must be recovered by assembling client-specific structural fragments. We propose \textbf{Jigsaw-CRL}, a framework for recovering global latent causal order from such fragmented interventions. Under soft interventions, differences between precision matrices across environments exhibit a low-rank structure governed by latent ancestor relations. This enables recovery, for each client, of a block partition, the corresponding block-level ancestral order, and latent subspaces, and then assembly of these fragments into the global node-level latent causal order. We establish identifiability guarantees, develop practical algorithms, and validate the framework on synthetic data. Our codes are available on https://anonymous.4open.science/r/code-for-Jigsaw-CRL-7B26

stat.ML↗
arXiv2026

PAPO: Stabilizing Rubric Integration Training via Decoupled Advantage Normalization

We propose Process-Aware Policy Optimization (PAPO), a method that integrates process-level evaluation into Group Relative Policy Optimization (GRPO) through decoupled advantage normalization, to address two limitations of existing reward designs. Outcome reward models (ORM) evaluate only final-answer correctness, treating all correct responses identically regardless of reasoning quality, and gradually lose the advantage signal as groups become uniformly correct. Process reward models (PRM) offer richer supervision, but directly using PRM scores causes reward hacking, where models exploit verbosity to inflate scores while accuracy collapses. PAPO resolves both by composing the advantage from an outcome component Aout, derived from ORM and normalized over all responses, and a process component Aproc, derived from a rubric-based PRM and normalized exclusively among correct responses. This decoupled design ensures that Aout anchors training on correctness while Aproc differentiates reasoning quality without distorting the outcome signal. Experiments across multiple model scales and six benchmarks demonstrate that PAPO consistently outperforms ORM, reaching 51.3% vs.\ 46.3% on OlympiadBench while continuing to improve as ORM plateaus and declines.

cs.AI↗
arXiv2026

DEEPCHART: How Far are LLMs from Faithful Data-Science Chart Generation?

Faithful chart generation in real-world data-science workflows requires grounding visualizations in scattered evidence, computing chart-ready quantities, and rendering them accurately. Modern LLMs can produce visually plausible, instruction-compliant charts, yet data-level hallucinations remain difficult to detect in long, noisy, and multimodal contexts. To measure this gap, we introduce DEEPCHART, an expert-annotated benchmark of 1,482 task-conditioned chart-generation instances drawn from real-world scientific papers, financial filings, and ecosystem reports. DEEPCHART formulates chart generation as an Extract--Reason--Visualize pipeline and evaluates source-data extraction, derived-data reasoning, and chart rendering stage by stage. Experiments with state-of-the-art models show that visually plausible charts often conceal data-level hallucinations, with extraction and reasoning errors common in realistic long and multimodal settings. These findings suggest that larger context windows alone are insufficient; faithful chart generation also requires reliable evidence extraction and quantitative reasoning before rendering. Our benchmark and associated resources are available at https://github.com/tangdouer1005/DeepChart.

cs.AI↗
arXiv2026

AsymSpec: Context-Asymmetric Speculative Decoding for Agentic LLMs

Agentic LLM pipelines face escalating inference costs as context accumulates across retrieval, tool use, and multi-turn interactions. To control latency, deployments routinely compress inputs, but this degrades task accuracy. Speculative decoding (SD) accelerates generation losslessly, yet it assumes the drafter and verifier share an identical context, preventing SD from resolving the accuracy-overhead trade-off. We propose AsymSpec, an asymmetric speculative decoding framework that breaks this symmetry: a lightweight drafter reads the full input while the large verifier operates on the compressed view. The drafter steers the verifier via a contrastive $δ$-fusion of logits, modulated by a divergence-aware acceptance gate that preserves verification stability and high draft acceptance rates. Evaluated across four agentic capabilities and two end-to-end agent benchmarks, AsymSpec reaches $\approx 90\%$ of full-context accuracy on average, delivering $1.3$--$1.7\times$ throughput speedups at $0.2$--$0.3\times$ the compute cost on isolated text capabilities. These results show that asymmetric context access yields substantial gains precisely when compression discards critical reasoning signals.

cs.AI↗
arXiv2026

Descent and Brauer-Manin Obstructions on Deligne-Mumford Stacks

We generalize and compare local-global obstructions for algebraic stacks over number fields. For smooth separated Deligne-Mumford stacks of finite type with a quasi-projective coarse moduli space, we prove that the descent obstruction is contained in the Brauer--Manin obstruction. By lifting $\mathbb{G}_m$-gerbes, we obtain an inclusion between the corresponding composite obstructions. We also show that in this setting the descent obstruction coincides with both the étale Brauer-Manin obstruction and the iterated descent obstruction. The Brauer-Manin obstruction also coincides with the iterated Brauer-Manin obstruction.

math.AG↗
arXiv2026

Minutes-long soft X-ray prompt emission from a compact object merger

Compact object mergers are multi-messenger sources and known progenitors of some gamma-ray bursts, bright flashes of high-energy radiation powered by a central engine, either an accreting black hole or a neutron star. Our understanding of these events has so far been shaped primarily by observations in the gamma-ray band, leaving their prompt phase poorly constrained at lower energies. A long-lasting ($\approx$100 s) engine-driven X-ray emission was discussed to explain rapidly fading X-ray afterglows following several ($\approx$30%) bursts of short ($\lesssim$2 s) duration. However, this prompt X-ray component was not directly observed and past candidates were not confirmed. Here we report the discovery of EP250704a containing a minutes-long ($\sim$560 s) flash of soft (0.5--4 keV) X-rays immediately following the short ($\sim$0.4 s) GRB 250704B. The variability and spectral shape of this emission are inconsistent with the canonical picture of a hard, accretion-powered spike followed by a standard external-shock afterglow. Instead, the long-soft bump points to a distinct phase of prompt emission in X-rays, which would not have been detected without the soft X-ray coverage of Einstein Probe. The detection of a prompt soft X-ray counterpart in an otherwise ordinary short GRB shows that long-lasting X-ray emission is likely a common feature of merger-driven bursts and a promising electromagnetic counterpart to gravitational wave sources.

astro-ph.HE↗
arXiv2026

Self-Harness: Harnesses That Improve Themselves

The performance of LLM-based agents is jointly shaped by their base models and the harnesses that mediate their interaction with the environment. Because different models exhibit distinct behaviors, effective harness design is inherently model-specific. Yet agent harnesses are still largely engineered by human experts, a paradigm that scales poorly as modern LLMs become increasingly diverse and rapidly evolving. In this paper, we introduce Self-Harness, a new paradigm in which an LLM-based agent improves its own operating harness, without relying on human engineers or stronger external agents. We operationalize Self-Harness as an iterative loop with three stages: Weakness Mining, which identifies model-specific failure patterns from execution traces; Harness Proposal, which generates diverse yet minimal harness modifications tied to these failures; and Proposal Validation, which accepts candidate edits only after regression testing. We instantiate Self-Harness across Terminal-Bench-2.0, SWE-bench Verified, and AppWorld using a minimal initial harness and three base models from diverse families: MiniMax M2.5, Qwen3.5-35B-A3B, and GLM-5. Across all nine model--benchmark combinations, every final harness improves both held-in and held-out pass rates, with overall relative gains of up to 132%. Qualitative analyses further show that the retained mechanisms address benchmark-specific bottlenecks in artifact handling and runtime control, software-patch verification, and application-state retrieval. These results suggest a path toward LLM-based agents that are not merely shaped by their harnesses, but can also participate in reshaping them.

cs.CL↗
arXiv2026

ACE-Cap: Active Evidence Acquisition via Agentic Co-Evolution for Long-Paragraph Fine-Grained Audio Captioning

Long-paragraph fine-grained audio captioning requires models to recover diverse acoustic facts while avoiding omissions and unsupported details. However, prevailing captioners remain passive one-shot generators: once a detail is overlooked, they cannot identify the evidence gap, query the audio for targeted information, or decide when sufficient evidence has been collected. We formulate this task as active evidence acquisition and introduce Agentic Co-Evolution for Captioning (ACE-Cap). The framework uses multi-turn interaction between a Composer and an Instruct model to form a closed evidence-acquisition loop. A Captioner first produces an initial description. Conditioned on this description and the interaction history, a text-only Composer asks targeted questions about unresolved acoustic attributes, while an audio-conditioned Instruct model provides grounded answers. The Composer then decides when to terminate and synthesizes the accumulated evidence into a final caption. ACE-Cap trains these roles through a unified gold-to-prediction reward derived from fixed, gold-grounded multiple-choice questions and a frozen caption-only judge. For credit assignment in variable-length interactions, LOOP-GRPO replaces the trajectory-wide scalar advantage with span-aligned signals: leave-one-out contributions of individual questions to the accumulated evidence, a quality-cost utility for stopping, and an evidence-preservation utility for final synthesis. Role-wise warm-up followed by alternating Composer and Instruct optimization keeps each update a well-defined single-policy problem while allowing the roles to co-evolve. ACE-Cap thus turns captioning from passive one-shot generation into an adaptive process that learns what evidence to acquire, when to stop, and how to preserve it in a long-paragraph caption.

cs.SD↗
arXiv2026

A Thread-Register Decoupled GPU Execution Model for Efficient Tensor Computation

Modern GPUs increasingly integrate Tensor Cores into the execution pipeline. Although aggregate tensor throughput continues to grow, aided by an operand supply that has evolved from register-based in Ampere to redundancy-free, memory-based in Hopper and Blackwell, efficiently orchestrating the complete tensor compute pipeline for the modern AI workloads remains challenging. We identify the fundamental bottlenecks as fixed parallelism and coarse-grained scheduling, both of which are exposed by modern AI workloads that interleave diverse non-GEMM operations with GEMM. To orchestrate tensor computation efficiently, we propose FIBER, a new architecture that extends the GPU SIMT (single instruction, multiple thread) model. Its basic execution instance, the \emph{fiber}, is decoupled from private register ownership, carrying only minimal control state while accessing an SM's registers through a shared view. This enables dynamic parallelism scaling, fine-grained register-level dataflow scheduling, and offers a redundancy-free alternative for matrix operand supply. We extend the ISA, microarchitecture, and compiler to realize shared-register addressing, conflict-free operand delivery, and fiber-based program mapping. Under a typical mixed-precision LLM serving scenario, FIBER achieves a 2.25x end-to-end speedup on Ampere (1.15x for the original FP16 computation), with 1.8x and 2.09x on Hopper and Blackwell respectively, and kernel-level gains up to 2.49x.

cs.AR↗
arXiv2026

Modeling and Forecasting Realized Volatility with Multivariate Fractional Brownian Motion

A multivariate fractional Brownian motion (mfBm) with component-wise Hurst exponents is used to model and forecast realized volatility (RV). We investigate the interplay between correlation coefficients and Hurst exponents and propose a novel method to estimate model parameters, establishing its consistency and asymptotic normality. Additionally, we develop a time-reversibility test, which is typically not rejected by RV data. When the data generating process is a time-reversible mfBm, we derive optimal forecasting formulae and analyze their properties. A key insight is that an mfBm with different Hurst exponents and non-zero correlations can reduce forecasting errors compared to a one-dimensional model. Consistent with this theory, out-of-sample forecasts using the time-reversible mfBm show improvements over univariate fBm, particularly when the estimated Hurst exponents differ significantly. Empirical results demonstrate that mfBm outperforms HAR and its variants in terms of out-of-sample forecast.

q-fin.ST↗
arXiv2026

Rapid post-merger gravitational-wave signals from magnetic black hole superradiance: novel approach to detect magnetic monopole and ultralight boson

We present an analytic framework showing that a spinning black hole with net magnetic charge exhibits a greatly enhanced superradiant instability against charged scalar fields compared with the neutral Kerr case. The enhancement arises from the monopole-induced reduction of the centrifugal barrier, $\ell(\ell+1)\to\ell(\ell+1)-q^2$, encoded by an effective quantum number $\ell_q$, with $q=eP=N/2$ fixed by Dirac quantization. This deepens the bound-state potential well and increases the instability growth rate. The resulting cloud can source near-monochromatic continuous gravitational waves (GWs). For a charged complex scalar, the stress tensor of a single monopole-harmonic sector is stationary, so the leading $2ω$ GW source instead arises from coherent north--south, equivalently charge-conjugate, cross terms. These select $(\tilde{\ell},\tilde{m},\tildeω)=(2q,+2q,+2ω)$ and its conjugate $(2q,-2q,-2ω)$. We find $P_{\rm GW}\propto(E_NE_S/M^2)α^{4\ell_q+8}$, or $P_{\rm GW}\propto(E_c/M)^2α^{4\ell_q+8}$ for a balanced cloud, rather than the neutral-Kerr scaling $α^{4\ell+10}$. This motivates prompt post-merger searches for magnetic monopoles and ultralight bosons. Unlike the Kerr case, where the signal turn-on may be delayed by years to centuries, a magnetic remnant can form a cloud and emit a stronger continuous signal within weeks to months. For $M\sim10^6M_\odot$, the signal can appear within weeks in the mHz band with strain $h\sim10^{-20}$.

gr-qc↗