BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Yiyang Li

Yiyang Li contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
math.COArtificial IntelligenceComputation and LanguageDiscrete Mathematicscond-mat.mtrl-sciDigital Librarieseess.AShep-exnucl-exnucl-th

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
12works
0followers
10topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

12 published item(s)

preprint2026arXiv

AgentEscapeBench: Evaluating Out-of-Domain Tool-Grounded Reasoning in LLM Agents

As LLM-based agents increasingly rely on external tools, it is important to evaluate their ability to sustain tool-grounded reasoning beyond familiar workflows and short-range interactions. We introduce AgentEscapeBench, an escape-room-style benchmark that tests whether agents can infer, execute, and revise novel tool-use procedures under explicit long-range dependency constraints. Each task defines a directed acyclic dependency graph over tools and items, requiring agents to invoke real external functions, track hidden state revealed incrementally, propagate intermediate results, and submit a deterministically verifiable final answer. AgentEscapeBench includes 270 instances across five difficulty tiers and supports fully automated evaluation. Experiments with sixteen LLM agents and human participants show that performance drops sharply as dependency depth increases: humans decline from 98.3% success at difficulty-5 to 80.0% at difficulty-25, while the best model drops from 90.0% to 60.0%. Trajectory analysis attributes model failures mainly to breakdowns in long-range state tracking, clue adherence, and intermediate-result propagation. These findings suggest that current agents can often handle local tool use but still struggle with deep contextual dependencies. We hope AgentEscapeBench can serve as a diagnostic testbed for measuring current agent capabilities and informing future training efforts toward more robust general-purpose reasoning, action, and adaptation.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Impact of the $^5$Li resonance in $α$-$p$ elastic scattering on precision measurements of neutrino oscillation parameters

Precision measurements of four neutrino oscillation parameters, $θ_{12}$, $θ_{13}$, $Δm^2_{21}$, and |$Δm^2_{31}$|, face significant interference from a previously overlooked correlated background. Recent findings from the SNO+ and JUNO experiments reveal that cascade decays of $^{214}$Bi-$^{214}$Po in liquid scintillator detectors can mimic inverse beta decay signals from reactor and geoneutrinos, with a misidentification probability on the order of $10^{-4}$ when hydrogen neutron capture is used, a rate ten times higher than Geant4 simulations predicted. This work identifies the $^5$Li resonance in $α$-$p$ elastic scattering as the underlying cause. For alpha energies above 5~MeV, the cross section is hundreds of times larger than that of Rutherford scattering. After correctly incorporating the differential cross section into Geant4, the misidentification probability is recalculated as 1.9$\times$10$^{-4}$. The simulated shape of the long tail in the alpha deposited energy also differs from the extrapolation models currently used by SNO+ and JUNO. These results will assist both experiments in more accurately estimating this novel background, thereby refining measurements of neutrino oscillation parameters and the geoneutrino flux. Additionally, the study implies an overlooked background with a rate of 0.5 events per detector per day in the Daya Bay $θ_{13}$ analysis using hydrogen neutron capture, leading to an increase of $\sin^22θ_{13}$ by approximately 0.012. Consequently, the Particle Data Group's reported $\sin^2θ_{13}$ value shall increase by about 0.006~(1$σ$).

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

LongDA: Benchmarking LLM Agents for Long-Document Data Analysis

We introduce LongDA, a data analysis benchmark for evaluating LLM-based agents under documentation-intensive analytical workflows. In contrast to existing benchmarks that assume well-specified schemas and inputs, LongDA targets real-world settings in which navigating long documentation and complex data is the primary bottleneck. To this end, we manually curate raw data files, long and heterogeneous documentation, and expert-written publications from 17 publicly available U.S. national surveys, from which we extract 505 analytical queries grounded in real analytical practice. Solving these queries requires agents to first retrieve and integrate key information from multiple unstructured documents, before performing multi-step computations and writing executable code, which remains challenging for existing data analysis agents. To support the systematic evaluation under this setting, we develop LongTA, a tool-augmented agent framework that enables document access, retrieval, and code execution, and evaluate a range of proprietary and open-source models. Our experiments reveal substantial performance gaps even among state-of-the-art models, highlighting the challenges researchers should consider before applying LLM agents for decision support in real-world, high-stakes analytical settings.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

PreScam: A Benchmark for Predicting Scam Progression from Early Conversations

Conversational scams, such as romance and investment scams, are emerging as a major form of online fraud. Unlike one-shot scam lures such as fake lottery or unpaid toll messages, they unfold through multi-turn conversations in which scammers gradually manipulate victims using evolving psychological techniques. However, existing research mainly focuses on static scam detection or synthetic scams, leaving open whether language models can understand how real-world scams progress over time. We introduce PreScam, a benchmark for modeling scam progression from early conversations. Built from user-submitted scam reports, PreScam filters and structures 177,989 raw reports into 11,573 conversational scam instances spanning 20 scam categories. Each instance is hierarchically structured according to the scam lifecycle defined by the proposed scam kill chain, and further annotated at the turn level with scammer psychological actions and victim responses. We benchmark models on two tasks: real-time termination prediction, which estimates whether a conversation is approaching the termination stage, and scammer action prediction, which forecasts the scammer's subsequent actions. Results show a clear gap between surface-level fluency and progression modeling: supervised encoders substantially outperform zero-shot LLMs on real-time termination prediction, while next-action prediction remains only moderately successful even for strong LLMs. Taken together, these results show that current models can capture some scam-related cues, yet still struggle to track how risk escalates and how manipulation unfolds across turns.

0 citations0 reviewsNo code linkedOpen access
preprint2025arXiv

Delayed 1T to 2H Phase Transition Upon Electrochemical Delithiation of LiMoS2

Molybdenum disulfide (MoS2) is a widely studied layered material for electronic, optical, and catalytic applications. It can host lithium ions between the van der Waals layers, which triggers a phase transition between the semiconducting 2H phase and metallic 1T phase. While lithium insertion triggers a phase transition to the 1T phase, the phase behavior upon electrochemical lithium removal is not resolved. In this work, we conduct single-flake electrochemical (de)lithiation of MoS2 using microelectrode arrays. Through both electrochemical voltage analysis and correlative Raman spectroscopy, we show that an electrochemically cycled and delithiated MoS2 flake initially remains in the 1T phase. However, over the course of several days, it transitions back into the thermodynamically stable 2H phase. This result resolves the phase transformation pathway upon delithiation and showcases the ability to electrochemically synthesize the metastable 1T-MoS2 phase.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Semantic-Preserving Adversarial Code Comprehension

Based on the tremendous success of pre-trained language models (PrLMs) for source code comprehension tasks, current literature studies either ways to further improve the performance (generalization) of PrLMs, or their robustness against adversarial attacks. However, they have to compromise on the trade-off between the two aspects and none of them consider improving both sides in an effective and practical way. To fill this gap, we propose Semantic-Preserving Adversarial Code Embeddings (SPACE) to find the worst-case semantic-preserving attacks while forcing the model to predict the correct labels under these worst cases. Experiments and analysis demonstrate that SPACE can stay robust against state-of-the-art attacks while boosting the performance of PrLMs for code.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Asymptotic values of four Laplacian-type energies for matrices with degree-distance-based entries of random graphs

Let $f(D(i, j), d_i, d_j)$ be a real function symmetric in $i$ and $j$ with the property that $f(d, (1+o(1))np, (1+o(1))np)=(1+o(1))f(d, np, np)$ for $d=1,2$. Let $G$ be a graph, $d_i$ denote the degree of a vertex $i$ of $G$ and $D(i, j)$ denote the distance between vertices $i$ and $j$ in $G$. In this paper, we define the $f$-weighted Laplacian matrix for random graphs in the Erd$\ddot{o}$s-R$\acute{e}$nyi random graph model $\mathcal{G}_{n, p}$, where $p\in (0, 1)$ is fixed. Four weighted Laplacian type energies: the weighted Laplacian energy $\mathscr{LE}_f(G)$, weighted signless Laplacian energy $\mathscr{LE}^{+}_f(G)$, weighted incidence energy $\mathscr{IE}_f(G)$ and the weighted Laplacian-energy like invariant $\mathscr{LEL}_f(G)$ are introduced and studied. We obtain the asymptotic values of $\mathscr{IE}_f(G)$ and $\mathscr{LEL}_f(G)$, and the values of $\mathscr{LE}_f(G)$ and $\mathscr{LE}_f^{+}(G)$ under the condition that $f(D(i, j), d_i, d_j)$ is a function dependent only on $D(i, j)$. As a consequence, we get that for almost all graphs $G_p\in \mathcal{G}_{n, p}$, the energy for the matrix with degree-distance-based entries of $G_p$, $\mathscr{E}(W_f(G_p)) < \mathscr{LE}_f(G_p),$ the Laplacian energy of the matrix, which is a generalization of a conjecture by Gutman et al.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

The asymptotic value of energy for matrices with degree-distance-based entries of random graphs

For a graph $G=(V, E)$ and $i, j\in V$, denote the distance between $i$ and $j$ in $G$ by $D(i, j)$ and the degrees of $i$, $j$ by $d_i$, $d_j$, respectively. Let $f(D(i, j), d_{i}, d_{j})$ be a function symmetric in $i$ and $j$. Define a matrix $W_f(G)$, called the weighted distance matrix, of $G$, with the $ij$-entry $W_f(G)(i, j)=f(D(i, j), d_{i}, d_{j})$ if $i\neq j$ and $W_f(G)(i, j)=0$ if $i=j$. In this paper, we prove that if the symmetric function $f$ satisfies that $f(D(i, j), (1+o(1))np, (1+o(1))np)=(1+o(1))f(D(i, j), np, np)$, then for almost all graphs $G_p$ in the $Erd\ddot{o}s$-$R\acute{e}nyi$ random graph model $\mathcal{G}_{n, p}$, the energy of $W_f(G_p)$ is $\{(\frac{8}{3π}\sqrt{p(1-p)}+o(1))\cdot|f(1, np, np)-f(2, np, np)|+o(|f(2, np, np)|)\}\cdot n^{3/2}$. As a consequence, we give the asymptotic values of energies of a variety of weighted distance matrices with function $f$ from distance-based only and mixed with degree-distance-based topological indices of chemical use. This generalizes our former result with only degree-based weights.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

The asymptotic value of graph energy for random graphs with degree-based weights

In this paper, we investigate the energy of a weighted random graph $G_p(f)$ in $G_{n,p}(f)$, in which each edge $ij$ takes the weight $f(d_i,d_j)$, where $d_v$ is a random variable, the degree of vertex $v$ in the random graph $G_p$ of the Erdös--Rényi random graph model $G_{n,p}$, and $f$ is a symmetric real function on two variables. Suppose $|f(d_i,d_j)|\leq C n^m$ for some constants $C, m>0$, and $f((1+o(1))np,(1+o(1))np)=(1+o(1))f(np,np)$. Then, for almost all graphs $G_p(f)$ in $G_{n,p}(f)$, the energy of $G_p(f)$ is $(1+o(1))f(np,np)\frac{8}{3π}\sqrt{p(1-p)}\cdot n^{3/2},$ where $p\in(0,1)$ is any fixed and independent of $n$. Consequently, with this one basket we can get the asymptotic values of various kinds of graph energies of chemical use, such as Randić energy, ABC energy, and energies of random matrices obtained from various kinds of degree-based chemical indices.

0 citations0 reviewsNo code linkedOpen access
preprint2010arXiv

The asymptotic number of occurrences of a subtree in trees with bounded maximum degree and an application to the Estrada index

Let $\mathcal {T}^Δ_n$ denote the set of trees of order $n$, in which the degree of each vertex is bounded by some integer $Δ$. Suppose that every tree in $\mathcal {T}^Δ_n$ is equally likely. For any given subtree $H$, we show that the number of occurrences of $H$ in trees of $\mathcal {T}^Δ_n$ is with mean $(μ_H+o(1))n$ and variance $(σ_H+o(1))n$, where $μ_H$, $σ_H$ are some constants. As an application, we estimate the value of the Estrada index $EE$ for almost all trees in $\mathcal {T}^Δ_n$, and give an explanation in theory to the approximate linear correlation between $EE$ and the first Zagreb index obtained by quantitative analysis.

0 citations0 reviewsNo code linkedOpen access
preprint2010arXiv

The asymptotic value of Randic index for trees

Let $\mathcal{T}_n$ denote the set of all unrooted and unlabeled trees with $n$ vertices, and $(i,j)$ a double-star. By assuming that every tree of $\mathcal{T}_n$ is equally likely, we show that the limiting distribution of the number of occurrences of the double-star $(i,j)$ in $\mathcal{T}_n$ is normal. Based on this result, we obtain the asymptotic value of Randić index for trees. Fajtlowicz conjectured that for any connected graph the Randić index is at least the average distance. Using this asymptotic value, we show that this conjecture is true not only for almost all connected graphs but also for almost all trees.

0 citations0 reviewsNo code linkedOpen access
preprint2010arXiv

The asymptotic values of the general Zagreb and Randić indices of trees with bounded maximum degree

Let $\mathcal {T}^Δ_n$ denote the set of trees of order $n$, in which the degree of each vertex is bounded by some integer $Δ$. Suppose that every tree in $\mathcal {T}^Δ_n$ is equally likely. We show that the number of vertices of degree $j$ in $\mathcal {T}^Δ_n$ is asymptotically normal with mean $(μ_j+o(1))n$ and variance $(σ_j+o(1))n$, where $μ_j$, $σ_j$ are some constants. As a consequence, we give estimate to the value of the general Zagreb index for almost all trees in $\mathcal {T}^Δ_n$. Moreover, we obtain that the number of edges of type $(i,j)$ in $\mathcal {T}^Δ_n$ also has mean $(μ_{ij}+o(1))n$ and variance $(σ_{ij}+o(1))n$, where an edge of type $(i,j)$ means that the edge has one end of degree $i$ and the other of degree $j$, and $μ_{ij}$, $σ_{ij}$ are some constants. Then, we give estimate to the value of the general Randić index for almost all trees in $\mathcal {T}^Δ_n$.

0 citations0 reviewsNo code linkedOpen access