Searcharxiv⌕ Search

arXiv subjects

Bo Zhang

Publications and source records attributed to Bo Zhang.

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

Success Leaves Detours: Learning Executable Walkthroughs for Long-Horizon Agents

Test-time self-evolving agents improve by reusing past experience, yet sparse-reward trajectories contain failures, loops, and detours, while summaries often omit the state conditions and action dependencies needed for execution. We study executable Walkthrough induction from sparse-reward trajectories: extracting compact, state-conditioned, and verifiable procedures. Our key observation is that delayed credit identifies actions associated with progress but cannot determine whether they produce facts required by later actions. We propose Trace, a credit-guided, dependency-grounded framework that compiles noisy trajectories into executable Walkthrough Memory. It detects progress anchors from rewards and persistent state changes, propagates credit to identify valuable transitions, and estimates action prerequisites from cross-episode success and failure evidence. Backward dependency slicing then traces required facts to their producers, extracting dependency-consistent action chains while removing irrelevant loops and detours. The resulting Walkthroughs encode entry conditions, ordered state--action--effect steps, and completion and failure predicates, supporting reuse, intermediate-state resumption, and programmatic verification. Experiments on J-TTL, WebShop, and ScienceWorld with three open-source LLMs show that Trace consistently outperforms eight test-time learning and memory baselines. Compared with the strongest baseline, it improves average AUC and Final-$3$ by $30.0%$ and $40.5%$, respectively, while using fewer inference tokens. These results show that long-horizon interaction benefits more from state-conditioned executable procedures than from complete trajectories or abstract summaries.

cs.LG↗
arXiv2026

Holtercare-Bench: A Multimodal Benchmark for Evaluating Long-Term Dynamic ECG Analysis

While multimodal large language models (MLLMs) excel in medical applications, most of them favor static images or short-term signals. In the critical field of dynamic electrocardiograms (ECG), models struggle with complex temporal reasoning and diagnostic report generation due to a lack of high-quality datasets and benchmarks. To address this, we introduce (i) Holtercare-23K, a large-scale multimodal dynamic ECG dataset comprising 22,980 QA pairs derived from 788 clinical Holter records and featuring a novel signal-video-text tri-modal alignment. Based on this dataset, we present (ii) Holtercare-Bench, a multimodal benchmark that evaluates models on temporal localization, clinical diagnosis, and global summarization. Zero-shot evaluations of leading MLLMs reveal a significant performance gap in processing ultra-long pathological sequences. However, fine-tuning representative models yields substantial improvements. This work illuminates the limitations of current MLLMs in electrophysiology and provides a foundational benchmark for long-term medical MLLMs. Our project is available at https://github.com/ZJU4HealthCare/Holtercare-Bench.

cs.LG↗
arXiv2026

A Helium-shell Burning Blue Horizontal Branch Star Produced from Common Envelope Evolution

Observationally, blue horizontal branch (BHB) stars are defined as hot stars occupying a characteristic region between the extreme blue horizontal branch and RR Lyrae variables in the Hertzsprung-Russell diagram. Most of them are interpreted as stripped core-helium-burning stars, but the role of binary interaction in their formation remains unclear. Here, we report the discovery of a metal-rich BHB star in a 0.82628-day binary system (Feige 64) comprising a $0.35\pm0.03\,M_{\odot}$ BHB star and a likely $1.26\pm0.17\,M_{\odot}$ white dwarf (WD). The BHB star has an effective temperature of $15{,}524\pm310$ K and a luminosity of $39.7\pm4.1\,L_{\odot}$. Stellar evolution modelling indicates that it is a helium-shell-burning star produced through the common-envelope channel, retaining a hydrogen-rich envelope that is more massive than previously thought for low-mass stars. This finding provides direct evidence for binary interaction in the formation of BHB stars, offering a fresh perspective on interpreting this emerging population.

astro-ph.SR↗
arXiv2026

APTER: Adaptive Post-Training with Expert-Grounded Rubrics

As large language models enter professional domains, they must satisfy domain constraints, include critical evidence, and provide complete reasoning rather than merely produce fluent responses. Existing post-training methods often rely on holistic preferences or outcome-level verification, while recent rubric-based methods usually generate rubrics independently for each query. In specialized domains, such unconstrained rubrics may omit critical requirements and vary across samples, hindering the diagnosis and targeted repair of persistent capability deficiencies. We propose APTER (Adaptive Post-Training with Expert-Grounded Rubrics), a framework that integrates structured domain knowledge into fine-grained evaluation, optimization, and diagnosis for specialized complex reasoning. First, expert-grounded rubric construction starts from an expert criteria framework built by domain experts, where each criterion represents a stable professional capability. For each query, APTER selects relevant criteria and instantiates them into query-level rubrics linked to their source criteria, turning reusable expert criteria into executable query-level supervision without reference answers. Second, adaptive post-training uses rubric verdicts as both optimization and criterion-level diagnostic signals. Aggregating low-scoring verdicts by criterion ID reveals persistent deficiencies and triggers targeted supervised fine-tuning updates during reinforcement learning. Experiments on mathematical reasoning and medical question answering show consistent gains across both domains. Across three model generations, APTER improves the mathematics and medical averages over the corresponding base models by up to 15.86 and 8.04 points, respectively. Code and rubric datasets are available at https://github.com/AntDT-APTER/APTER.

cs.AI↗
arXiv2026

OH Line Detections in Southern Galaxies of the IRAS Revised Bright Galaxy Sample

We present a systematic study of OH main-line emission and absorption in 186 southern galaxies from the IRAS Revised Bright Galaxy Sample, using archival MeerKAT snapshot data. OH features are detected in 38 galaxies, including eight with OH maser emission (three new) and 30 showing OH absorption, mostly unreported previously. Four absorption systems exhibit weak OH emission superposed on strong absorption. OH-emitting regions are generally more compact than the associated radio continuum. Most absorption profiles are well fit by two Gaussian components (1667 and 1665 MHz), with an average integrated line ratio of $\sim$1.5. LIRGs show an OH emission detection rate of ~13\%, versus significantly lower rates in non-LIRGs. For sources with radio continuum flux densities >20 mJy, OH absorption detection rates reach ~36\% (LIRGs) and ~27\% (non-LIRGs), while no OH absorption features were detected among sources with lower radio continuum flux densities. This suggests that sufficient background continuum is likely an important factor for the detection of OH absorption. Detected OH emitters follow the empirical $L_{\rm OH}$--$L_{\rm FIR}$ relation, consistent with far-infrared pumping, while non-detections show upper limits below the relation. No significant differences are found between OH absorbers and non-detections in infrared luminosity or radio continuum compactness. Stacked spectra of non-detections reveal no significant OH features, suggesting that sensitivity and orientation alone do not fully explain the absence of absorption. In contrast, mid-infrared colors (e.g., W2--W3) and q_TIR differ between the two populations. OH absorption galaxies occupy an intermediate regime in L_HCN/L_CO between OH megamasers and non-detections, implying that OH absorption detectability is linked to dense molecular gas conditions, with extreme star formation potentially suppressing its occurrence.

astro-ph.GA↗
arXiv2026

Towards Physics-Faithful Generation of Scientific Diagrams

Text-to-image generation has reached photorealistic quality, yet state-of-the-art systems remain unreliable at producing scientific diagrams, whose value depends not on appearance but on physical faithfulness: correct force directions, valid coordinate systems, consistent thermodynamic states, and equations matching the depicted scenario. Trained on web imagery with physically shallow captions, generic models produce diagrams that look plausible but are physically wrong, harmful in education and scientific communication. We present Princigram, a physics-faithful scientific-diagram generator, and its data pipeline. Our central advance is Structured Physical Chain-of-Thought (SP-CoT): a per-subdiscipline schema that decomposes a physics diagram into an explicit multi-step reasoning chain across six subdisciplines, from scene identification through force or process analysis to governing laws and synthesis. Unlike free-form chain-of-thought, SP-CoT follows a fixed schema with strict fidelity rules that separate visually grounded facts from physically inferred reasoning and type all mathematics symbolically; it serves both as dense training supervision and, at inference, as a structured "thinking" prompt. With it we curate and structurally annotate 4.3 million physics images, of which 115,037 carry expert-level annotation, and adapt a unified multimodal backbone. We further introduce VeriphyT2IBench, whose questions are derived from each held-out diagram's own structured annotation: each diagram becomes an item-specific bank of binary questions about its objects, forces, and states, so a judge model's score decomposes into named physical facts rather than one holistic number. On the physics subset of GenExam and on VeriphyT2IBench, Princigram shows that explicit physics-structured supervision improves the physical faithfulness of generated scientific diagrams.

cs.CV↗
arXiv2026

Synchrotron self-Compton process for constraining sub-GeV dark matter in Omega Centauri via SKA

The search for the particle identity of dark matter (DM) continues to be a primary objective in modern physics. In this field, the sub-GeV mass range of DM detection remains a crucial yet challenging window. We investigate synchrotron self-Compton (SSC) emission from electrons and positrons produced by MeV-scale DM annihilation as a novel indirect detection channel. Focusing on the globular cluster Omega Centauri and the sensitivity of the Square Kilometre Array, we derive constraints on the annihilation cross section reaching $\langleσv\rangle \sim 10^{-29}\,\rm{cm}^{3}\,\rm{s}^{-1}$ in the tens-of-MeV range. Furthermore, constraints can reach below $\langleσv\rangle \sim 10^{-30}\,\rm{cm}^{3}\,\rm{s}^{-1}$ under favorable parameter choices. Although the derived limits depend on the uncertain propagation parameters, the SSC channel remains competitive with existing indirect constraints over a representative range of astrophysical assumptions, establishing SSC emission as a promising probe of sub-GeV DM.

astro-ph.CO↗
arXiv2026

PE-CSNet: An equivariant network architecture with learnable patch-based sparse representation

Compressive sensing (CS) enables accurate signal reconstruction from sparse measurements and is widely applied in medical imaging, remote sensing, and image compression. However, designing an effective, task-specific sparse transform and the corresponding optimization procedure for high-quality CS remains challenging. This process typically requires expert domain knowledge and laborious parameter tuning. To address this issue, we present a Patch-based Equivariant deep unrolling architecture, termed PE-CSNet, for accurate CS recovery. While traditional CS methods generally use predefined patch-based transform sparsity, we generalize this idea by incorporating learnable transform sparsity that adapts to the specific CS task through an optimization-driven process. Specifically, we first establish a generalized patch-based CS model, which we solve via a block coordinate descent (BCD) algorithm. The BCD solver is then unrolled into a deep neural network, where all parameters of both the CS model and solver are learned through end-to-end training. To improve data efficiency, we introduce a stochastic equivariant training strategy that exploits the patch-wise structure of the network, enabling PE-CSNet to learn effectively even from limited data. We further provide a simpler, parameter-shared version of PE-CSNet and briefly discuss its convergence as an iterative solver. For practical applications, the network uses stage-specific (non-shared) parameters to enhance its expressive power and thereby improve its performance. On the tasks of CS magnetic resonance imaging (CS-MRI) and CS coded diffraction patterns (CS-CDP), PE-CSNet achieves state-of-the-art accuracy with fast computational speed, outperforming traditional methods and existing deep unrolling methods.

cs.CV↗
arXiv2026

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding

Recent advancements in MLLM-based long-form video understanding have mitigated inference-time computational cost and limited context lengths by selecting query-relevant frames. However, existing approaches predominantly rely on external proxy scorers and rigid heuristic rules, inevitably suffering from misalignment with the target MLLM's intrinsic evidence and failing to accommodate the non-uniform spatiotemporal information density. In this paper, we propose a fine-grained dynamic visual selection framework named EviSelect, grounded in the target MLLM internal attention evidence. Our method efficiently probes visual evidence via sparse prefilling as a structured prior to guide distribution-aware dynamic sampling. Specifically, we efficiently approximate attention maps of the target MLLM using highly compressed visual inputs and sparse attention, well-aligned to the full counterpart. Conditioned on three complementary attention components derived from this prior, we design a lightweight selector that not only precisely locates query-relevant timestamps but also adaptively adjusts the local sampling rate and spatial resolution. To enable evidence-conditioned spatiotemporal sampling, we formulate the selector as a stochastic policy and optimize it via GRPO under a joint accuracy--efficiency reward. By rewarding correct predictions under lower visual cost through group-relative comparisons, our method encourages the policy to allocate computation dynamically according to the information density of each video. Across three long video understanding benchmarks, EviSelect achieves superior performance compared to existing methods while reducing selected visual tokens by about 50\% and achieving a 3.9x end-to-end speedup.

cs.CV↗
arXiv2026

Improving the efficiency of infectious disease prevention trials using negative control outcome event times

Baseline covariate adjustment can enhance the efficiency of randomized trials by improving precision of treatment effect estimates. However, the precision gain depends on how strongly the baseline covariates are prognostic for the primary outcome. In randomized trials of infectious disease prevention interventions (e.g., vaccines or passively administered antibodies), an individual's exposure to the pathogen is a leading prognostic factor but is rarely measurable at baseline. Hence, conventional covariate adjustment offers limited precision gain in prevention trials. We propose adjusting for a negative control outcome (NCO) event time, which is causally unaffected by the intervention but shares overlapping exposure mechanisms with the primary outcome. We formalize assumptions under which adjustment for the NCO event time is valid, and show that right-censoring of the NCO event time further complicates adjustment. We derive the efficient influence function for the treatment-arm-specific survivor function of the primary outcome when both the primary outcome and the NCO event time are right-censored, and use it to construct a cross-fitted, one-step estimator that is multiply robust to nuisance misspecification and asymptotically efficient when the nuisances are estimated accurately. In numerical experiments, our estimator compares comparably to benchmarks when the NCO event time is uninformative, and gains precision as the NCO event time is more prognostic for the primary outcome. We apply our method to HVTN 704/HPTN 085, a randomized, double-blinded trial of VRC01, a broadly neutralizing antibody against HIV-1. Adjusting for the time to a bacterial sexually transmitted infection --- a negative control outcome for HIV-1 acquisition --- reduced the estimated variance of the prevention efficacy estimate by approximately 27%, compared to roughly 2.5% for baseline covariate adjustment.

stat.ME↗
arXiv2026

AgentPanel: Toward a New Paradigm for Human--AI Collaboration in Exploring Scientific Questions

Identifying promising scientific ideas remains an important challenge in research practice. Researchers commonly rely on small-group discussions or one-to-one interactions with a single large language model, yet these approaches often expose them to only a limited range of perspectives and directions. We present AgentPanel, a multi-agent forum for human--AI collaboration in scientific exploration. Heterogeneous agents asynchronously discuss scientific questions in a forum-style environment, while researchers can submit questions, browse and organize candidate ideas, engage agents in follow-up interactions, and optionally generate post-hoc summary reports. We evaluate AgentPanel in terms of idea quality, exploration breadth, interaction effectiveness, candidate-selection efficiency, and practical utility. Offline experiments show that AgentPanel outperforms a centralized multi-agent debate baseline. A human study with 20 participants further shows that users value AgentPanel for perspective diversity and exploration support. In experience-based comparisons with commonly used LLM tools, 65\% of participants favored AgentPanel for both breadth of research directions and overall suitability for early-stage exploration. The platform is publicly available at https://agentpanel.cc/.

cs.AI↗
arXiv2026

DriveCode: Domain Specific Numerical Encoding for LLM-Based Autonomous Driving

Large language models (LLMs) have shown great promise for autonomous driving. However, discretizing numbers into tokens limits precise numerical reasoning, fails to reflect the positional significance of digits in the training objective, and makes it difficult to achieve both decoding efficiency and numerical precision. These limitations affect both the processing of sensor measurements and the generation of precise control commands, creating a fundamental barrier for deploying LLM-based autonomous driving systems. In this paper, we introduce DriveCode, a novel numerical encoding method that represents numbers as dedicated embeddings rather than discrete text tokens. DriveCode employs a number projector to map numbers into the language model's hidden space, enabling seamless integration with visual and textual features in a unified multimodal sequence. Evaluated on OmniDrive, DriveGPT4, and DriveGPT4-V2 datasets, DriveCode demonstrates superior performance in trajectory prediction and control signal generation, confirming its effectiveness for LLM-based autonomous driving systems.

cs.CV↗
arXiv2026

SeekBrain: An Autonomous Multi-Agent System for Accelerating Neuroscience Discovery

Modern neuroscience relies on integrating multi-scale, multimodal datasets to uncover the neural principles underlying intelligence. However, analytical challenges posed by highly heterogeneous data and fragmented workflows increasingly constrain discoveries. Here we introduce SeekBrain, an autonomous multi-agent framework designed to accelerate neuroscience discovery through domain-grounded hierarchical planning and cross-modal data analysis. SeekBrain dynamically constructs a repertoire of analysis recipes extracted from code-paper pairs. By coupling this codified expertise with agentic planning and execution engines, the framework scalably generates hypotheses and analytical pipelines on demand. Systematic evaluation on the expert-annotated BrainArena benchmark demonstrates that SeekBrain substantially outperforms state-of-the-art agent baselines across various analysis tasks. Crucially, when deployed in real-world research, SeekBrain integrated behavioral, neural, and anatomical data to reveal structured, distributed neural representations of larval zebrafish behavior and a shared axis of regional decoding strength across the brain in a mouse decision-making task. These results establish SeekBrain as a scalable and practical tool for accelerating data-driven discoveries in neuroscience.

cs.MA↗
arXiv2026

CoDe-SSM: Context-Detail Decoupled State Space Model for Efficient UHD Image Restoration

Ultra-high-definition (UHD) image restoration must balance the aggregation of spatially recurring degradation cues with the preservation of localized image structures. Compact aggregation can reduce redundant processing but may attenuate edges, textures, and other fine structures. Existing approaches manage UHD restoration cost through downsampling, window partitioning, or cluster-based token reduction; yet many of them do not explicitly retain information that is poorly represented by shared aggregation. In this study, we propose a Context-Detail Decoupled State Space Model (CoDe-SSM) for UHD restoration, which processes aggregated context and clustering residuals in separate pathways. The context modeling pathway, implemented by the Global Cluster Scan Module (GCSM), aggregates features into $K$ input-dependent cluster centers and applies selective SSM reasoning over the resulting fixed-order sequence, enabling cross-region context sharing while decoupling computational cost from spatial resolution. The detail recovery pathway, implemented by the Local High-Frequency Module (LHFM), processes the clustering residual with an input-derived high-frequency mask and a sparse mixture of convolutional experts. Extensive experiments on five UHD benchmarks and five degradation types demonstrate that our explicit context-detail decoupling strategy yields substantial gains in restoration quality while maintaining desirable efficiency.

cs.CV↗
arXiv2026

Convergent and efficient iteratively regularized contrast source inversion-type methods for inverse medium scattering problems

The contrast source inversion (CSI) method and the subspace-based optimization method (SOM) are first proposed in 1997 and 2009, respectively, and subsequently modified. The two methods and their variants share several properties and thus are called the CSI-type methods. The CSI-type methods are efficient and popular methods for solving inverse medium scattering problems, but their rigorous convergence remains an open problem. In this paper, we propose two iteratively regularized CSI-type (IRCSI-type) methods with a novel $\ell_1$ proximal term as the iteratively regularized term: the iteratively regularized CSI (IRCSI) method and the iteratively regularized SOM (IRSOM) method, which have a similar computation complexity to the original CSI and SOM methods, respectively, and prove their global convergence under natural and weak conditions on the original objective function. To the best of our knowledge, this is the first convergence result for iterative methods of solving nonlinear inverse scattering problems with a fixed frequency. The convergence and performance of the two IRCSI-type algorithms are illustrated by numerical experiments.

math.NA↗
arXiv2026

OwlPath: Lossless Knowledge Compression for LLM Bug Repair

LLM-based software engineering agents are constrained by limited context windows: roughly 100K tokens must store structurally relevant code subsets to resolve bugs. Standard retrieval models treat code as plain text, forcing agents to resolve multi-hop dependencies including subclass chains, transitive callers and interface implementations through slow trial and error. We tackle this limitation with lossless knowledge compression, encoding source code into an OWL2 ontology to answer structural queries using minimal relevant code fragments. We present OwlPath, an OWL2 reasoning layer atop CodeGraph, a widely used code intelligence platform with 500K+ GitHub stars, offering a unified CLI for structural code retrieval. Powered by tree-sitter parsing, OwlPath supports multi-language repositories (Python, JavaScript, TypeScript, Go, etc.) and encodes language-specific semantics into a unified OWL2 ontology. It adopts two complementary modules. First, a transitive-closure engine fetches all structurally linked symbols via single SPARQL property-path queries, capturing multi-hop relations missed by string matching. Second, the OWL Software Knowledge Map (OWL-SKM) precomputes a compact 3KB summary with module trees, core APIs and issue-related symbols, directing agents to target modules in the first query. Evaluated on 18 SWE-bench Pro instances, OwlPath obtains a 68.4% strict-apply rate versus 66.7% for the CodeGraph baseline, cutting token usage by 28.8% and runtime by 39.5%. In offline retrieval tests over 67 instances, OwlPath improves recall 2.06 times (0.464 vs 0.226) and reaches 88.1% hit rate compared to CodeGraph's 59.7%. On a 37-question structural retrieval benchmark, recall rises from 4.4% to 28.8%, with 69-80% accuracy on transitive caller and interface tasks.

cs.SE↗
arXiv2026

On the Identifiability of Controlled World Models

World model serves as a promising tool to infer environment dynamics under high-dimensional observations and candidate actions. Recently, LeCun's JEPA provides a compelling framework for learning such models in representation space. Its action-conditioned extension plays a central role in visual control and latent-space planning, but leaves a fundamental question: can it recover the controlled dynamics from nonlinear observations? This paper presents a joint identifiability condition for controlled world models with Gaussian latent states, which consists of two coupled components: (1) representation identifiability and (2) transition identifiability. The former depends on the spectral separation property while the latter is related to non-degenerate variation of conditional action. We prove that when this condition holds, minimizing the LeJEPA-style predictive objective can recover both latent states and controlled dynamics in the sense of orthogonal transformation. We further prove that the upper bound of transition prediction error is inversely proportional to the spectral separation margin. We also characterize an attainable amplification of counterfactual prediction error that scales inversely with the weakest conditional action-excitation margin. The theoretical predictions are empirically supported across four nonlinear observation settings.

cs.LG↗
arXiv2026

LiteResearcher: A Scalable Agentic RL Training Framework for Deep Research Agent

Reinforcement Learning (RL) has emerged as a powerful training paradigm for LLM-based agents. However, scaling agentic RL for deep research remains constrained by two coupled challenges: hand-crafted synthetic data fails to elicit genuine real-world search capabilities, and real-world search dependency during RL training introduces instability and prohibitive cost, which limits the scalability of Agentic RL. LiteResearcher is a training framework that makes Agentic RL scalable: by constructing a lite virtual world that mirrors real-world search dynamics, we enable a continuously improving training recipe that empowers a tiny search agent to outperform large-scale open-source and commercial models (e.g., Tongyi DeepResearch and Claude-4.5 Sonnet). Specifically, on common benchmarks such as GAIA and Xbench, our LiteResearcher-4B achieves open-source state-of-the-art results of 71.3% and 78.0% respectively, demonstrating that scalable RL training is a key enabler for Deep Research Agents.

cs.AI↗