Searcharxiv⌕ Search

arXiv subjects

Zhiwei Chen

Publications and source records attributed to Zhiwei Chen.

At least 19 recordsLinked to original sources

Jet energetics and remnant magnetism in short gamma-ray bursts from binary neutron-star mergers: A statistical study via broadband afterglow modeling

Short gamma-ray bursts (sGRBs) are believed to originate from compact binary mergers, particularly binary neutron star (BNS) mergers, providing a probe of jet energetics and merger remnants. We compile broadband afterglow observations of 40 sGRBs and perform forward-shock modeling with off-axis Gaussian jets, excluding data potentially affected by additional energy injection. We derive distributions of beaming-corrected jet kinetic energy $E_k$ and radiative efficiency $η_γ$, and combine these with binary population synthesis and numerical simulations to infer remnant black hole (BH) magnetic fields assuming the Blandford-Znajek (BZ) jet-launching mechanism. For the 15 strictly constrained bursts, we find a median $E_k\simeq3.8\times10^{49}$ erg and $η_γ\simeq0.35$, with respective 68% intervals of $[5.1\times10^{48},1.9\times10^{50}]$ erg and [0.09, 0.79]. The inferred magnetic field supplied by the accretion disk and threading the BH horizon is approximately $7\times10^{15}$ G, with a 68% credible interval of $[2.3\times10^{15},2.4\times10^{16}]$ G, depending slightly on the neutron star equation of state. The full sample yields a higher median field of approximately $2\times10^{16}$ G, with the high-energy and high-field tails predominantly contributed by less well-constrained bursts. These results provide statistical constraints on sGRB jet energetics and suggest characteristic BH magnetic fields of order $10^{16}$ G. Comparison with pre-merger neutron star magnetic fields indicates a characteristic amplification factor of $η_B\sim10^3$, providing an observational constraint on magnetic field amplification during BNS mergers and subsequent BH formation.

astro-ph.HE↗

Prospects for probing supermassive binary black holes in strongly lensed active galactic nuclei via microlensing effects

Gravitational microlensing in strongly lensed active galactic nuclei (AGNs) provides a powerful probe of accretion-disk structure and may offer a unique opportunity to identify sub-parsec supermassive binary black holes (SMBBHs) through distinctive signatures. Upcoming wide-field surveys are expected to discover a large sample of strongly lensed AGNs, a fraction of which may host SMBBHs detectable via microlensing. In this paper, we employ semi-analytic models to assess the detection prospects of sub-parsec SMBBHs in lensed AGNs, focusing on systems with resolvable multiple images suitable for microlensing analysis. Accounting for galaxy-scale strong-lensing statistics, and including the cluster-lensing contribution as an optimistic statistical extension, we estimate that up to approximately 87 such systems could be spatially resolved by individual upcoming surveys, including the Vera C. Rubin Observatory (Rubin), Euclid, China's Space Survey Telescope (CSST), and the Roman. For the Rubin WFD survey, we estimate that periodic oscillations in microlensing light curves could identify $\sim0.12-0.68$ short-period ($<5$\,yr) binaries, whereas diagnostics based on the reconstructed size-wavelength relation apply to a broader population, potentially identifying $\sim0.4-5.3$ systems, depending on the model assumptions. CSST, Euclid, and Roman may also reveal up to $10.6$, $8.9$, and $1.2$ systems exhibiting size-wavelength features, and $2.3$, $1.9$, $0.3$ systems showing periodic oscillations, which should be regarded as imaging-selected candidates whose microlensing-based identification requires adequate time-domain follow-up, including cadence, monitoring baseline, photometric precision, and reliable time-delay measurements. Our results show that strongly lensed AGNs provide a promising, though observationally demanding, pathway for finding candidate SMBBHs via microlensing.

astro-ph.GA↗

Quasi-spherical fallback in binary neutron-star mergers: fuel and obstacle for extended emission

Extended emission (EE) lasting hundreds of seconds has been observed in a fraction of short gamma-ray bursts (sGRB) containing both nonthermal and thermal components, and representing a significant puzzle for models involving binary neutron stars (BNSs). Recent GRMHD simulations of BNS mergers found that the late-time fallback is approximately quasi-spherical and motivated an r-process powered thermal model for EE. However, the available radioactive-heating power may be insufficient to sustain the luminosity inferred by such a model. We therefore propose a fallback-fed secondary-jet scenario in which a fraction of the fallback material circularizes on the black-hole equatorial plane and powers the jet, while polar fallback impedes its propagation. Using a semi-analytic toy model, we follow the propagation of the jet-head through the fallback envelope and identify jet-dominated, cocoon-dominated, and choked scenarios. The boundaries of these regimes depend primarily on the circularization fraction $f_{\rm circ}$, on the jet half-opening angle $θ_j$, and on the polar refilling factor $ξ_{\rm pol}$, with the approximate scaling $\widetilde{L}\propto f_{\rm circ}/(ξ_{\rm pol}θ_j^2)$. By post-processing data from BNS-merger simulations we find that the fraction of bound fallback material that avoids prompt capture is $f_{\rm npc}\simeq0.52$, thus providing an upper bound on the circularizable fallback supply. Under suitable prescriptions for nonthermal jet emission and thermal emission from the jet head, the estimated isotropic-equivalent $0.3$--$10$ keV energies reproduce well both the observed EE distribution for the jet-dominated branch and its low-energy end for the cocoon-dominated branch. Overall, these results suggest that fallback-fed secondary jets represent a dynamically feasible and energetically consistent explanation of the EE in sGRBs.

astro-ph.HE↗

SetGRPO: Calibrating Grader-Induced Policy Optimization

Rubric-based reinforcement learning uses fine-grained grader feedback to train large language models on open-ended tasks, but grader randomness can alter GRPO updates in ways that score discrepancies alone cannot characterize. Because GRPO jointly normalizes rewards within each response group and combines the resulting training coefficients with response-level gradients, a scoring discrepancy can shift the coefficients of the entire group and induce policy-dependent update changes. Selective execution further affects the direction-reversal risk of retained updates. To address this, we propose Set-Valued Group Relative Policy Optimization (SetGRPO). It comprises three modules: (a) Joint Reward Set Calibration constructs a joint uncertainty set for the training coefficients; (b) Geometry-Guided Safe Recovery maps candidate coefficients into the current policy's local update geometry and determines the largest safe recovery ratio for each response group; and (c) Selective Risk-Gated Optimization selects a global threshold through independent risk calibration to control the conditional direction-reversal risk of accepted updates while preserving the original GRPO objective. Under exchangeability, SetGRPO provides finite-sample marginal coverage for the joint coefficient set and simultaneous risk control across candidate thresholds. On ten open-ended benchmarks spanning three domains, SetGRPO achieves the highest macro average among all compared training methods on both Qwen3.5 and Llama3.2 model families.

cs.LG↗

TrawMem: Reframing Agent Memory as Task-Oriented Role-Adaptive Workspaces

Large language model (LLM) agents rely on memory systems to leverage long-term interactions, yet existing systems typically retrieve memories based on their relevance to the current query and use them as contextual evidence. However, relevance alone does not characterize how a memory contributes to task solving: the same memory may serve different roles across tasks, such as directly supporting the answer or linking to complementary memories with weaker semantic relevance but necessary information. We therefore reframe agent memory systems as Task-Oriented Role-Adaptive Workspaces, where memories are selected and organized by their task-oriented roles and relations. Based on this view, we propose TrawMem, which organizes interaction histories into local threads and constructs task-oriented workspaces by assigning roles and jointly selecting complementary memories. Experiments on LoCoMo and MemGallery with four open- and closed-source backbones show consistent improvements over representative memory systems, with macro-F1 gains of 2.23-3.14 points. On LoCoMo, TrawMem improves the LLM-Judge score over SimpleMem by 4.07 and 4.31 percentage points on Qwen3.5-9B and DeepSeek-V4-Flash, respectively, while requiring approximately 12.8% and 5.1% fewer context tokens, respectively.

cs.CL↗

TopoField: Technical Report for ECCV 2026 SceneFun3D Challenge

Functional segmentation requires locating small interactive parts, such as knobs, buttons, and sockets, in indoor point clouds and returning confidence-ranked instance masks. A point-wise semantic predictor produces a continuous probability field, whereas the benchmark evaluates a discrete set of scored instances. This creates a substantial field-to-instance gap. We present TopoField, a deterministic decoder built on top of VOLT. TopoField first converts 13 test-time forward passes into a semantic consensus field, then decodes instance candidates from the consensus geometry, and finally ranks the candidates in a class-aware manner. The augmentation stage retains the processed-point identity of every fragment prediction, accumulates probabilities in a common point array, normalizes by coverage count, and fuses the resulting caches. The decoding stage separates high-confidence cores from broader support regions, constructs a symmetric radius-pruned point graph, and uses a multi-source graph-geodesic partition to split support regions that contain multiple seeds. On 561 ground-truth instances across 30 validation scenes, an IoU-0.5-valid candidate exists for 67.2% of instances, and top-1 coverage is 20.0%. These complementary measurements motivate joint attention to candidate construction and ranking. TopoField achieves 28.286% AP, 41.383% AP50, and 47.558% AP25. TopoField achieved second place on the ECCV 2026 SceneFun3D Challenge.

cs.CV↗

TaskBridge: Technical Report for SIGIR 2026 eCommerce Challenge

The SIGIR 2026 eCommerce Challenge Query Reformulation Task evaluates the reformulation of task-oriented queries into expressions suitable for product retrieval, followed by BM25-based retrieval. These queries often imply product needs through activity-level semantics, creating a lexical gap with catalog descriptions. Systems must preserve task intent while adapting the number of reformulations to the Automatic and Interactive protocols. We propose TaskBridge, a catalog-anchored framework comprising Catalog Semantic Anchoring, Unified Five-Candidate Rewriting, and Protocol-Aware Selection. It grounds queries in catalog vocabulary, generates five complementary reformulations, and selects one query for Automatic retrieval or up to four for Interactive retrieval using BM25 scores, query-product reranking, and weighted Jaccard overlap. The selected queries are independently executed using BM25 to produce results in the required six-column format. Experiments demonstrate improved retrieval effectiveness, with multiple complementary queries providing additional gains in the Interactive setting. TaskBridge achieved first place in the SIGIR 2026 eCommerce Challenge.

cs.IR↗

GradCO: Behavior-Aware Gradient-Conflict Offloading for Text-Based Person Anomaly Search

Text-based Person Anomaly Search (TPAS) retrieves a target pedestrian using natural-language descriptions of appearance and normal or anomalous behavior. Unlike conventional text-based person retrieval, TPAS must preserve identity cues while distinguishing fine-grained behaviors. It presents two challenges: same-identity, different-behavior hard negatives cause gradient conflict during granular alignment, while strong appearance cues can obscure weak behavioral evidence during aggregation. We propose GradCO (behavior-aware Gradient-Conflict Offloading), comprising three complementary components. Behavior-Aware Mixture-of-Experts (B-MoE) forms appearance, normal-behavior, and anomalous-behavior streams whose roles are learned from retrieval objectives without expert-specific semantic labels. Conflict Offload Learning (COL) uses pair-conditioned offload anchors in similarity computation to reduce the conflicting-gradient burden on the main text representations. Hierarchical Intent Alignment (HIA) aggregates expert similarities and features using query-conditioned weights. Experiments on five TPAS/TIPR benchmarks show GradCO significantly surpasses SOTA methods and validate our design.

cs.CV↗

Formation and Detectability of PSR J0653+0443-like Extremely Eccentric Binary Neutron Stars in the Milky Way

Recently, the Five-hundred-meter-Aperture-Spherical-radio-Telescope (FAST) Galactic Plane Pulsar Snapshot (GPPS) survey discovers an extraordinary binary neutron star (BNS) system, PSR J0653+0443, possessing the highest known orbital eccentricity ($e\approx0.992$) among Galactic BNSs (Yang et al., 2026), which provides a unique probe into the formation and evolution of BNSs. In this Letter, we perform compact binary population synthesis calculations with self-consistent neutron star spin evolution to model extremely eccentric BNS population detectable by the FAST GPPS survey, explicitly incorporating observational selection effects. We find that BNSs with $e>0.99$ constitute only $\sim0.6\%$ of the detectable population, with an expected detection number of $λ_{\mathrm{GPPS}}\approx0.31$ over the full planned footprint. Thus, although rare, systems as eccentric as PSR J0653+0443 are compatible with standard binary evolution. We further demonstrate that extremely eccentric BNSs arise preferentially from core-collapse supernovae, whereas imposing $P\lesssim0.1$ s select older, more frequently recycled systems, which naturally reproduce the observed properties of PSR J0653+0443. We further predict that the completed GPPS sample has a $\sim15\%$ chance of finding another $e>0.99$ BNS, but a much higher $\sim88\%$ chance for $e>0.90$ systems. By contrast, future facilities are expected to enlarge the detectable highly eccentric BNS population, with SKA potentially detecting PSR J0653+0443-like systems and sub-mHz gravitational-wave detectors probing a larger population with $e>0.9$, enabling much more in-depth population-level constraints.

astro-ph.HE↗

SAGE: Structured Strategic Reasoning for Efficient LLM Game Playing

A strong LLM strategic agent should reason prospectively over uncertain futures, adapt its strategy to opponents' behavioral tendencies, and continuously recalibrate its decision process from interaction experience. However, incorporating these sources in free-form reasoning could lead to unsupported strategic assumptions, inconsistent opponent estimates, and harmful interference from irrelevant historical interactions. To address these issues, we propose SAGE, a training-free inference-time framework that structures LLM strategic reasoning around three coordinated operations: anchor, adapt, and recalibrate. SAGE first anchors reasoning to an equilibrium policy that provides a strategically valid prior. It then conditions deviations from this anchor on a soft belief over opponent behavioral tendencies, enabling opponent-specific exploitation. Finally, SAGE distills strategically related interactions into counterfactual hypotheses about previously missing considerations, allowing past experience to recalibrate the model's reasoning. We evaluate SAGE on three repeated imperfect-information games: Leduc Hold'em, Liar's Dice, and Goofspiel, against various opponent types in each game. Compared with reasoning-intensive LLM agents, including Suspicion-Agent, ReTA, Agent-Pro, EMO, and Hypothetical Minds, SAGE achieves up to a 127.6% payoff improvement in Liar's Dice while reducing input and output token usage by up to 80% and 90%, respectively. In direct match-up play, it attains non-negative mean payoff against 5/10, 8/10, and 8/10 evaluated opponents in Leduc Hold'em, Liar's Dice, and Goofspiel, respectively, while using relatively fewer tokens. Code is available at https://github.com/chenzhwsysu57/SAGE.

cs.AI↗

LatentRemedy: Efficient Remedy For Non-Prefix KV Cache Reuse in Multi-Agent Systems

Non-prefix KV cache reuse is a promising approach for improving inference efficiency in multi-agent systems as agents share the same context blocks. However, when agents have conflicting tasks, directly reusing non-prefix KV caches across agents can severely degrade model performance, causing up to a 90% drop. Existing remedies, including selective recomputation and offset-based calibration, recover a limited fraction of this loss. We argue that the problem lies not only in contaminated KV representations but also in the agent's difficulty interpreting reused context under its own instructions. To this end, we introduce LatentRemedy, which uses a few task-conditioned latent tokens to help the target agent leverage reused context without recomputing the shared block. Specifically, we use an MLP to map the last hidden state of the target prefix into a small number of latent tokens, which are placed after the reused KV block to interact with the shared context. To guide subsequent predictions toward the target task, we train the MLP through full-prefill distillation. Experiments show that LatentRemedy consistently outperforms existing reuse baselines on conflicting tasks while maintaining TTFT close to direct reuse as cache size grows. Code and data are available at https://github.com/chenzhwsysu57/kvreuse.

cs.CL↗

Identifying the principal mechanism of star formation feedback

Feedback from massive stars regulates the formation of next-generation stars and planets and thus shapes the evolution of galaxies, yet observational evidence capable of determining which mechanism dominates the feedback process has long been lacking. Here,we present a large-scale HI survey toward Orion A$.$ With an unprecedented sensitivity and superior resolution, FAST (Five-hundred-meter Aperture Spherical radio Telescope) reveals a well-defined heart-shaped expanding HI bubble, enshrouding the well-known "Veil" bubble of ionized gas. The photoionization-driven and wind-driven gas expands at 10.9 and 13.8 kilometers per second, respectively, with a kinetic energy ratio of 1:2 assuming a spherical symmetry and a uniform HI-to-H2 ratio. This first direct comparison within a single bubble shows that radiation does not dominate the feedback process as predicted by classical theories; instead, stellar winds contribute a comparable share of the injected kinetic energy.

astro-ph.GA↗

EasyFoam: Skill-Oriented OpenFOAM Agents with Evidence-Driven Evolution

Large language model (LLM) agents are increasingly capable of automating end-to-end OpenFOAM workflows for computational fluid dynamics (CFD). However, current progress is bottlenecked by two critical limitations. First, existing evaluations are dominated by tutorial-level cases and execution-oriented metrics, masking a substantial executability--acceptability gap: successfully executed simulations often fail to satisfy prescribed numerical or quantity-of-interest (QoI) criteria. Second, domain expertise in existing systems is tightly coupled with bespoke agent architectures, limiting its reuse and continual refinement across agent implementations. To address these challenges, we introduce ExtFoamBench, a challenging benchmark for OpenFOAM agents that spans five axes of workflow variation, and separately assesses execution completion, numerical soundness, and QoI satisfaction. Complementing this, we propose EasyFoam, an agent framework that decouples CFD expertise into modular, externalized skills driven by a dual-loop mechanism. An execution loop constructs workflows from explicit task requirements and uses structured simulation evidence to diagnose failures and guide targeted repairs. Meanwhile, an evolution loop distills task experience into reusable skill updates selected through paired evaluation. Empirical evaluations demonstrate that EasyFoam achieves substantially higher task acceptance rates than baseline agents, establishing this work as a starting point for future research toward self-improving CFD agents.

cs.CE↗

Is the Signed Zarankiewicz Number the Same as the Recursive-line Zarankiewicz Number?

Löfberg and Qi introduced the second order Zarankiewicz number \(z_2\), the recursive-line Zarankiewicz number \(z_{RL}\), and the signed Zarankiewicz number \(z_{SL}\) for doubly simple biquadratic forms. It was shown that \[ z_2(m,n)\ge z_{SL}(m,n)\ge z_{RL}(m,n) \] for all \(m\) and \(n\). However, there was no evidence that there exist particular \(m\) and \(n\) such that \(z_{SL}(m,n)>z_{RL}(m,n)\). The motivation for introducing \(z_{SL}\) was as follows: during the study of the exceptional case \(m=15\), \(n=6\), Löfberg and Qi showed that \[ z_2(15,6)=z_{SL}(15,6)=60, \] but the exact value of \(z_{RL}(15,6)\) was unknown then. In this paper we show that \[ z_{RL}(15,6)=60. \] This eliminates the motivation for introducing \(z_{SL}\). Whether \(z_{SL}(m,n)=z_{RL}(m,n)\) in general remains an open problem. Recently, Lebedev presented an explicit construction separating the augmented Zarankiewicz number \(z_A\) from the limited augmented Zarankiewicz number \(z_L\) at \(m=n=1893\). We hope that the separation problem for \(z_{SL}\) and \(z_{RL}\) can also be solved. We also present the exact values of \(z_{RL}(m,6)\) for \(6\le m\le 16\).

math.CO↗

Recursive-Line Zarankiewicz Numbers with Four Columns

The recursive-line Zarankiewicz number maximizes the number of squares in a structured irreducible sum-of-squares representation encoded by an augmentation of an extremal $C_4$-free bipartite graph. We determine its four-column behavior under the strengthened recursive definition in the manuscript of Löfberg and Qi dated 9 September 2026. Combining AI-assisted discovery with exact certificate verification and finite exclusion computations, we determine eighteen of the nineteen values for $2\le m\le20$ and isolate the only unresolved case to $37\le\zr(14,4)\le38$. More significantly, we prove the first eventual exact formula in the four-column setting: \[ \zr(m,4)=\floor{\frac{5m+6}{2}}\qquad(m\ge15). \] The upper bound follows from the classical identity $z(m,4)=m+6$ and a sharp cell count. For the matching lower bound, we construct a two-row extension chain from an explicit $20\times4$ seed and derive the odd orders by a fixed deletion. Analytic propagation, together with two independently audited symbolic certificate tables, proves the construction for arbitrary chain length rather than merely for a finite computational range. Thus every extremal configuration has no holes when $m$ is even and exactly one hole when $m$ is odd, and the same exact formula holds for the second-order number $z_2(m,4)$.

math.CO↗

Implicit Manipulation for Skill Selection in LLM Agents with Semantic Matching

Skill selection is a key stage in LLM-agent workflows, determining which installed skill should handle a user request. Existing attacks on this stage primarily rely on explicit prompt injection or instruction-level steering, which can expose recognizable manipulation signals. In this work, we identify a new implicit attack surface for skill selection: even when the user prompt and skill description appear benign in isolation, their semantic relationship can still be strategically shaped to favor an attacker-chosen skill. Based on this observation, we present Implicit Skill-Selection Manipulation via Semantic Matching (ISM), which jointly shapes target-skill metadata and reusable prompts to manipulate skill selection without explicit selection instructions. Specifically, we develop a three-stage strategy to broaden semantic coverage, strengthen target distinctiveness, and preserve natural prompt wording. Across four task domains and eight selector models, ISM increases the average target-selection rate (TSR) from 15.2% to 63.5%. In a matched comparison, ISM achieves a 73.5% TSR, only 9.8 percentage points below Explicit Steering. Human reviewers block ISM in only 2.9% of judgments, versus 91.4% for Explicit Steering, while five LLM-based inspectors pass ISM at an average rate of 82.9%, versus 37.4% for Explicit Steering. Moreover, ISM remains effective against PPL-W, Llama Prompt Guard 2, and PIGuard.

cs.CR↗

LightAIR: Lightweight Action Inversion and Riemannian Rectification for Text-based Person Anomaly Search

Traditional Text-based Person Search (TPS) is typically limited to matching static appearance attributes, severely neglecting dynamic action information. The Text-based Person Anomaly Search (TPAS) task bridges this gap, requiring models to locate micro-level specific abnormal behaviors while matching macro-level appearance of pedestrians. However, current TPAS methods face fundamental limitations: external explicit pose estimators are fragile in unconstrained surveillance scenarios, and implicit learning encounters visual decoupling failure under pixel-level entanglement, causing dominant appearance information to easily swallow and contaminate subtle action features. Furthermore, performing contrastive optimization on hard negative samples (``same appearance, different actions'') in conventional Euclidean spaces induces severe shortcut learning. To address these, we propose the Lightweight Action Inversion and Riemannian rectification network (LightAIR). First, it introduces textual semantic priors as anchors via a lightweight action inversion operator to extract pure action features, thereby overcoming visual-inherent coupling. Subsequently, it employs orthogonal null-space projection to constrain appearance features within the orthogonal complement space of action features, guaranteeing strict forward decoupling. Finally, we designed a gradient rectification module that computes the Riemannian gradient to constrain the backpropagation trajectory, forcing the gradient flow to update strictly along the tangent space that preserves decoupling properties, thereby cutting off harmful shortcuts. Extensive experiments on the widely used TPAS and TIPR datasets demonstrate that LightAIR significantly outperforms existing state-of-the-art methods. Codes are available at https://github.com/rainy-london/LightAIR

cs.CV↗

The First EgoCross Challenge at EgoVis 2026: Cross-Domain Egocentric Video Question Answering

EgoCross is a cross-domain egocentric video question answering benchmark designed to evaluate whether multimodal large language models can generalize beyond common daily-life scenarios. The first EgoCross Challenge was hosted at the Third EgoVis Workshop at CVPR 2026 and evaluated models on first-person videos from four target domains: surgery, industrial assembly, extreme sports, and animal perspectives. Each test example consists of an egocentric video clip, a question, and four candidate answers, from which the model must select the correct option. This technical report introduces the challenge task, benchmark resources, and two official Codabench tracks. The Source-Limited Track restricts participants to the official baseline model and a small support set, whereas the Open-Source Track permits broader choices of models and training data under rules that prohibit the manual construction of target-domain training data. In total, the challenge received more than 1,500 submissions from over 130 participants, with 19 teams participating in the Open-Source Track and 38 teams in the Source-Limited Track. We further present the official leaderboard results and summarize the winning solutions from both tracks. We hope that this report will serve as a useful technical reference for advancing cross-domain egocentric video understanding. All resources, including the challenge data, baseline implementation, and code released by the winning teams, are made publicly available.

cs.CV↗