arXiv subjects

Zihan Chen

Publications and source records attributed to Zihan Chen.

At least 19 recordsLinked to original sources

arXiv2026

RAHC: Rule-Augmented Hyper-Relational Knowledge Graph Completion for Materials Synthesis

Scientific discovery depends on reusing experimental knowledge, yet records scattered across papers and repositories are often incomplete. In materials synthesis, recovering missing conditions requires reasoning about the target material and the observed context of a specific experiment. Hyper-relational knowledge graphs (HKGs) represent this context through qualifiers, but existing completion methods leave domain knowledge and experimental regularities implicit. We propose RAHC, a rule-augmented HKG framework for single-slot and joint multi-slot synthesis-condition completion. RAHC builds a traceable rule catalog from training records and retrieved literature, retrieves rules for each query-candidate pair, and separately encodes graph structure and rule evidence. Hard rules constrain candidate validity, while soft rules guide ranking. RAHC-G aggregates rules using global reliability; RAHC-Q additionally learns query-specific relevance. Gated fusion combines structural and rule representations, while tuple-conclusion rules provide cross-condition evidence for joint completion. Experiments on five materials-synthesis datasets show improvements in single-slot and joint completion under Semi-inductive and Open-Answer Inductive settings, with Semi-inductive MRR gains of up to 15.6% over MAYPL. RAHC also improves performance on the entity-disjoint ILPC'22 Small benchmark, supporting transfer to fully inductive KG completion. These results support experimental condition selection, synthesis planning, and the reuse of scientific knowledge.

cs.AI↗

arXiv2026

Ask More, Hear Less: How a Review Prompt Changes What Online Ratings Show

Platforms ask customers for online reviews to reduce self-selection, but theory conflicts on whether review solicitation makes online ratings more or less informative. Selection theory implies that asking helps, voice theory that it dilutes the news, and research on rating inflation that compression destroys information. We reconcile these views with signal detection theory, which separates what a rating knows (its sensitivity) from what it shows (its criterion). We test the framework on Steam, a leading PC video game store, whose client began in October 2019 to prompt players for a review after about three hours of play. Using a difference-in-discontinuities design at that inferred threshold in 21.6 million Steam reviews of 315 games, we find that review counts just above the threshold become 4.25 times those just below, and the jump in the positive share grows by 6.6 percentage points. Agreement with critics changes little near launch and erodes later. The rating's movement changes far more: pass-through from reviews written in the first two hours falls from 0.73 to 0.18 just above the threshold, against 0.81 to 0.64 just below, and a fixed rating tier responds to 12% of downturns in those reviews above the threshold, down from 42%, against 41% and 47% below it. What the stream knows changes less. At equal review counts its sensitivity falls more above the threshold, because added reviews respond about half as much and scores near the ceiling are noisier per review, but at natural counts added volume offsets this loss, leaving a change of -0.03 relative to the stream below (95% CI -0.13 to 0.06). Failures that developers acknowledge, which run through complaints, still move the score after launch. Review prompts therefore mainly change how a rating must be read, and platforms that solicit reviews should recalibrate their rating labels.

cs.HC↗

arXiv2026

Crowds Believe in You: Online Prediction Markets Overestimate How Often People Achieve Their Own Goals

People increasingly share personal goals online and invite others to forecast them. Research on the planning fallacy finds that observers predict a person's behavior less optimistically than the person does, and prediction markets aggregate such judgments, harnessing the wisdom of crowds. We study 6,150 prediction markets on Manifold in which 1,660 users asked about their own futures ("Will I ...?"), reconstruct every order and execution, and compare these self-markets with markets about external events. Self-markets resolved YES 4.4 percentage points less often than their final prices implied, whereas external markets were nearly calibrated (0.9 points); the difference was 2.2 points at the same price level and 1.9 points within creators who made both kinds of market. Absent when markets opened, the overstatement emerged within a day of trading, even where the person never traded, and peaked in the week before close. In a market's first day, observers moved external-market prices down toward the base rate, but moved self-market prices 3.6 points further toward YES, except in markets naming an outcome the person would not want, which were not overpriced. The correction came late and largely from the person, whose orders supplied 38% of the eventual movement toward the outcome in self-markets, against 9% in external markets. Because self-market prices mainly failed to separate successes from failures, a recalibration learned from earlier markets improved later forecasts by only 1.5%. Crowds believe in the futures people pose for themselves, and the information that would correct them lies with the person.

cs.HC↗

arXiv2026

MuQ-Eval: An Open-Source Per-Sample Quality Metric for AI Music Generation Evaluation

Distributional metrics such as Fréchet Audio Distance cannot score individual music clips and correlate poorly with human judgments, while the only per-sample learned metric achieving high human correlation is closed-source. We introduce MUQ-EVAL, an open-source per-sample quality metric for AIgenerated music built by training lightweight prediction heads on frozen MuQ-310M features using MusicEval, a dataset of generated clips from 31 text-to-music systems with expert quality ratings. Our simplest model, frozen features with attention pooling and a two-layer MLP, achieves system-level SRCC = 0.957 and utterance-level SRCC = 0.838 with human mean opinion scores. A systematic ablation over training objectives and adaptation strategies shows that no addition meaningfully improves the frozen baseline, indicating that frozen MuQ representations already capture quality-relevant information. Encoder choice is the dominant design factor, outweighing all architectural and training decisions. LoRA-adapted models trained on as few as 150 clips already achieve usable correlation, enabling personalized quality evaluators from individual listener annotations. A controlled degradation analysis reveals selective sensitivity to signal-level artifacts but insensitivity to musical-structural distortions. Our metric, MUQ-EVAL, is fully open-source, outperforms existing open per-sample metrics, and runs in real time on a single consumer GPU. Code, model weights, and evaluation scripts are available at https://github.com/dgtql/MuQ-Eval.

cs.AI↗

arXiv2026

Beauty Is Human: When People Love AI-Generated Art, They Think a Human Made It

Generative AI now produces images and poems that people cannot reliably distinguish from human-made work, so people often judge for themselves who made a work. We examine how these perceived-authorship judgments relate to aesthetic preference. In a public online AI Art Turing Test, 11,123 people judged whether each of 50 pictures (26 AI-generated) was made by a human and were asked for their favourite. Among the 9,152 respondents who judged their favourite, a picture was 22.1 percentage points more likely to be judged human-made when it was the respondent's favourite, holding respondent and picture fixed. The association was similar for AI-generated and human-made favourites, was positive for all 50 pictures, and appeared under every reported detection strategy. Respondents most negative about AI art chose fewer AI-generated favourites (47% against 60% among the most positive) but more often believed them human-made, partly because others also judged those pictures human. As a result, in every opinion group a third to two fifths of respondents named an AI-generated favourite they believed human-made. A reanalysis of a published experiment on AI-generated poetry, in which 230 people rated each poem before judging its authorship, found the same pattern, although the AI poems were rated higher. When provenance is hidden, liking and perceived human authorship travel together, consistent with aesthetic response serving as evidence of a human maker and with beliefs about the maker shaping enjoyment. The findings qualify research on bias against AI art, which typically uses explicit labels, and inform AI disclosure policy.

cs.HC↗

arXiv2026

What Victims Take Away: Attack Reuse and Defense Revision after Prompt-Injection Attacks

Attack logs and red-team reports show targets the attacks used against them, to help them repair their defenses. Prompt injections against large language models (LLMs) are plain text, so such records also hand targets a working copy. Drawing on social learning theory and work on the victim-offender overlap, we study what targets do with that copy in Tensor Trust, an online game whose players defended LLM-guarded accounts, attacked one another's, and could read every attack they received. Using all 563,349 attack records, we compare each received attack with matched attacks that circulated among similar players at the same moment but never reached the target. Reuse mainly followed success: within a week, targets attacked other players with 10.0% of the attacks that had broken their defense, versus 0.03% of matched attacks (adjusted difference: 8.8-10.0 percentage points). Near-misses, whose replies began with "access granted" but that scored as failures, were reused about as rarely as failures: reuse tracked whether an attack paid off, not how its reply read, consistent with payoff-biased social learning. Breaches were also followed by defense changes, after which same-family attacks became 24.5 percentage points less successful against the target, relative to other defenders. Reuse came mainly from players already attacking, not newcomers. Previously received texts accounted for 23.2% of the successful hijacks we analyze. The attack history thus served both repair and reuse; we derive testable hypotheses for how AI security tools should disclose attacks, such as describing the technique without the full text.

cs.CR↗

arXiv2026

Ferroelastic Reversal Magnon Thermal Hall Effect in a Fully Compensated Ferrimagnet

Magnons offer a charge-neutral channel for spin and heat transport, yet reversible and nonvolatile control of their thermal Hall response poses a fundamental challenge in systems with zero net magnetization. Here, we establish ferroelastic switching as an effective route to manipulate magnonic transverse responses in fully compensated ferrimagnets. A minimal Heisenberg-Dzyaloshinskii-Moriya model reveals that ferroelastic switching can re-orientate the lattice anisotropy, which reconstructs the chirality-resolved magnon bands and Berry curvature distribution. Consequently, the two orthogonal fully compensated ferrimagnetic variants related by [C2||C4z] exhibit magnon thermal Hall responses with opposite signs, whereas the response vanishes in the intermediate altermagnetic phase. First-principles calculations further identify monolayer V2SSe as a promising material candidate for realizing the proposed ferroelastic control of transverse magnon transport. Remarkably, ferroelastic switching drives a dual magnonic-electronic band reconstruction, enabling nonvolatile reversal of the magnon thermal Hall effect while producing anisotropic orbital Hall responses and distinct magneto-optical spectra as complementary transport and optical fingerprints. Our findings establish ferroelasticity as an effective route to nonvolatile magnon control and multichannel state identification in zero net magnetization systems.

cond-mat.mes-hall↗

arXiv2026

Demand-Driven Routing Space for Lattice-Surgery Compilation

Lattice-surgery compilation places logical qubits on a grid of surface-code tiles and routes their interactions. Sparse static layouts limit routing contention but reserve space that often remains idle. Reducing this reservation requires balancing area savings against additional gate serialization and qubit movement. In this paper, we present a co-designed dynamic architecture and compiler that allocates routing space according to circuit demand. The architecture preserves a fixed virtual qubit floorplan while allowing its physical spacing to change between execution stages. The compiler coordinates placement, scheduling, and routing to implement lattice surgeries using fewer physical qubits. Across our application benchmarks, our method reduces space-time volume by 55.6% in geometric mean and compiles 75.5 times faster than the evaluated DasCot configuration. A circuit-synthesis case study shows how our compiler exposes optimization tradeoffs.

quant-ph↗

arXiv2026

Abstract Priorities, Concrete Rewards: How Stated Preferences Relate to What People Reward in AI Responses

AI assistants built on large language models (LLMs) are trained on human feedback and increasingly personalized to users' stated preferences. Yet how closely these preferences reflect what people reward in responses remains unclear. We compare stated and revealed preferences in the public PRISM dataset, in which 1,396 participants reported how much seven response attributes mattered to them and then rated 29,347 responses from 21 LLMs. Among responses to the same prompt, features the survey never asked about, such as response length, formatting and refusal language, were at least as strongly associated with ratings as text proxies of the surveyed attributes. Whether stated priorities matched ratings depended on how attributes were measured: participants who prioritized an attribute favoured responses from models that others perceived as strong on it, but not responses that scored higher on text proxies for it. Written feedback was more telling: participants who asked for shorter answers, even in earlier conversations, gave length less weight in their ratings, and those asking for longer answers gave it more. Their relative priorities over the surveyed attributes, however, did not predict this weight. Reasons given for choices reflected perceived attributes more than measured features. Participants also differed stably in how much they weighted several concrete features, especially length, but with a median of 6 conversations per participant, these weights were estimated poorly. The largest gain from personal information in predicting held-out choices was 0.13 percentage points, compared with 1.11 for a stronger pooled model. Stated priorities thus track perceived attributes of AI responses but say little about the concrete features that ratings reward, a distinction that matters for preference elicitation and AI personalization.

cs.HC↗

arXiv2026

Workflow-Aware Communication and Computation Scheduling for Mobile Edge AI Agents

AI agents are increasingly deployed in mobile edge environments to autonomously handle diverse tasks through multi-step workflows. Unlike conventional dependency-aware tasks with predefined dependency structures, agent workflows are dynamically generated based on intermediate execution results. To minimize the weighted sum of job completion latencies, this paper models partially revealed agent workflows using dynamic workflow graphs and formulates an online scheduling problem that jointly optimizes computation placement, wireless resource block allocation, and edge computing resource allocation. To address the uncertainty of future workflow evolution, we first transform the weighted completion time objective into an equivalent per-slot holding cost and characterize the optimal policy through a Bellman equation. We then construct a tractable look-ahead cost-to-go surrogate based on the revealed workflow and the estimated remaining latencies of active jobs. The proposed scheduling algorithm leverages the surrogate to determine computation placement and uses the resulting operation criticality to allocate wireless and edge computing resources online. Simulation results show that the proposed algorithm outperforms the benchmark schemes across diverse scenarios.

cs.NI↗

arXiv2026

Auditing the Product, Not the Recursion: The Evaluation Evidence Behind Recursive Self-Improvement Claims

Recursive self-improvement (RSI) promises AI systems, such as self-evolving LLM agents, that become better at producing further improvements. Evaluating this promise requires separating product claims about the final system from process claims about the improvement process itself. Existing surveys specify the evidence these claims require, but how often studies report that evidence remains unmeasured. We examine this question through full-text coding of 114 eligible studies in a reproducible arXiv search frame frozen in October 2026, including 90 that describe their own systems as RSI. The codebook links claims to evaluation designs. Independent human coding, third-reader adjudication, and a separate blind coding of improver comparisons assess coding reliability. Among the 90 RSI studies, 90% report product evaluation beyond development tasks under a broad criterion that includes partial or unstated separation, while 60% report evaluation on tasks unused for selection. Only 22% audit two or more reruns of the full loop. In a human-coded random sample, the RSI studies show the same contrast: 45% evaluate on tasks unused for selection and 14% audit two or more reruns. Of the 26 studies claiming a better improvement procedure, 23 report a related comparison, but only 4 compare earlier and later procedures from identical starting artifacts at a matched budget. Across these results and a comparison set of established works, evidence for repeatability and improved procedures remains less developed than product evaluation. Three propositions explain how selection effects, shared evaluator errors, and changes in system state limit what product evaluations can establish. Together, the findings support a claim-indexed reporting standard that connects each claim to the evaluation design needed to test it.

cs.LG↗

arXiv2026

Memory as Belief: Bayesian Evolution of Memory for Self-Evolving LLM Agents

Large language model (LLM) agents increasingly rely on external memory to accumulate past experiences for continual adaptation. However, effectively reusing memory requires accurately assessing its value, as retrieved experiences may become unreliable when transferred across task contexts. Despite its importance, memory valuation remains largely underexplored, with existing methods relying on historical retrieval success rates that overlook the context dependency of memory usefulness and the varying reliability of estimates under different amounts of evidence. Inspired by the Bayesian brain hypothesis, we propose BEAM (Bayesian-style Evolutionary Agentic Memory), a framework that reformulates memory value evaluation as a parameterized cognitive inference process, where memory value is represented as a context-conditioned dynamic belief rather than a passive historical statistic. Specifically, BEAM infers memory value beliefs from current task contexts and continuously calibrates them using execution feedback as empirical evidence, transforming memory from passive storage into an adaptive cognitive mechanism for continual self-evolution. Extensive experiments across reasoning and code generation benchmarks demonstrate that BEAM consistently improves memory utilization and enables continual self-evolution of LLM agents.

cs.LG↗

arXiv2026

Joint User Association and Resource Allocation for Adaptive Semantic Communication in 5G and Beyond Networks

Semantic communication (SemCom) has emerged as a promising paradigm that leverages Deep Neural Networks (DNNs) to extract task-relevant information, thereby substantially reducing the volume of transmitted data. In existing implementations, the semantic transceiver is typically pre-trained for a specific task and uniformly adopted by all users. However, due to user heterogeneity in computational and communication capabilities, employing a single, fixed semantic transceiver may degrade the coding efficiency and transmission robustness. To address this issue, we first demonstrate the feasibility of dynamically adjusting the computational and communication overhead of DNN-based semantic transceivers, enabling a more flexible paradigm referred to as Adaptive Semantic Communication (ASC). Building on this concept, we formulate a joint user association and resource allocation problem for ASC in 5G and beyond networks, aiming to maximize overall system utility under energy and latency constraints. However, the problem is very challenging due to the inherent interdependencies among decision variables. To tackle this complexity, we decompose the original problem into three subproblems: (i) ASC scheme selection for each user, (ii) spectrum allocation at each Small-cell Base Station (SBS), and (iii) user association across SBSs. Each subproblem is solved sequentially based on the solutions of the preceding stages. The proposed algorithm efficiently yields near-optimal solutions with polynomial-time complexity. Simulation results demonstrate our approach outperforms existing baselines under various situations.

cs.NI↗

arXiv2026

DecepEval: A Benchmark for Evaluating Deception in LLM Agents

As large language model (LLM) agents become increasingly autonomous, they may pursue task performance through deception, raising concerns about their reliable deployment. Existing evaluations show that LLM agents can deceive, but often examine isolated scenarios or narrowly defined conditions, limiting systematic understanding of when deception becomes more likely. To address this gap, we introduce DecepEval, a benchmark comprising 1,532 instances across 3 task families and 28 professional scenarios. Drawing on classical fraud theories, we propose the LLM Deception Diamond framework, which characterizes four external conditions that may induce deception: pressure, incentive, opportunity, and conflict. DecepEval pairs neutral and induced versions of each instance to measure condition-dependent changes in deception rates, while explicit task facts and observable agent behavior help distinguish deception from capability-related errors. Evaluations of nine frontier LLMs show that inducements increase deception across models and task families, even among models with low baseline deception rates. DecepEval makes these vulnerabilities measurable, providing a shared benchmark for progress toward trustworthy artificial intelligence.

cs.LG↗

arXiv2026

When Synthetic Users Fail: A Cross-Domain Benchmark of LLM-Simulated Human Survey Responses

Large language models (LLMs) are increasingly used as synthetic users, stand-ins for human respondents whose simulated answers feed product, policy, and market decisions. We ask when this substitution is valid and when it fails, and package the answer as an evaluation framework for intelligent synthetic-user systems. A single protocol, run across four models spanning two families and an 8B-to-frontier capability range, is applied to two independent domains of real human-response data: U.S. general social attitudes (General Social Survey) and cross-cultural values (World Values Survey). Every model is benchmarked against a suite of non-LLM baselines fit on held-out human data. Under demographic prompting and the survey-simulation protocols we test, two failures replicate across both domains, all four models, and both families. First, at the individual level no LLM beats even the strongest baseline; on cross-cultural values every model falls well below it, and the gap survives distance-aware and proper scoring. Second, models systematically over-determine demographics, treating identity as far more predictive of attitudes than it is among real people, a distortion present for nearly every question-group combination and robust to a coding-invariant measure. Neither failure is remedied by a larger, more capable model. A decision-impact analysis shows why this matters in practice: on a segment-targeting task the models inflate between-segment gaps two to fourfold, would direct a team to the wrong segment in half of U.S. and most cross-cultural cases, and manufacture segment splits that do not exist in real people. We publicly release the cross-domain benchmark and validation framework, including all code and data, so that teams can determine in advance when synthetic-user evidence is safe for decision support and when it is not.

cs.CL↗

arXiv2026

Two Routes to the Middle: Placement Search and Brain Readouts Converge on Where Continual Learners Should Specialize

Continual learners that keep a task-specific adapter in every block of a pre-trained vision transformer accumulate storage linearly with the number of tasks; keeping task-specific adapters in only a few blocks curbs this growth but raises the question of where to place them. We investigate this question from two perspectives. Algorithmically, training all contiguous four-block placements yields an inverted U: final accuracy peaks at intermediate depth and varies by up to 3.5 percentage points (pp), while inexpensive criteria based on weight spectra or activation statistics favor the deepest blocks. From neuroscience, the hierarchical organization and intermediate-stage plasticity of the visual cortex motivate us to ask whether a measurement taken outside the learner can guide layer specialization without placement search. LS-B observes the first tasks through a frozen fMRI encoding model of twelve human visual areas and commits task-specific capacity once to the blocks whose readouts vary most across tasks relative to their stable structure. Across three ViT-B/16 backbones, LS-B yields stable, backbone-specific allocations. On the two backbones with placement search, AugReg and iBOT, the selected blocks overlap the intermediate-depth region identified by search. Under matched storage and observation budgets, the selected blocks outperform the shallowest and deepest four-block configurations. On Split ImageNet-R, LS-B uses 60% of full-BiLoRA adapter storage while remaining within 1.5 pp of its final accuracy. The allocation requires no labels or backpropagation, adds under 0.6% runtime, and exhibits backbone-specific cortical signatures.

cs.LG↗

arXiv2026

TeacherGRPO: Closing the Capacity Gap in Reasoning Distillation via Teacher Alignment

Reasoning distillation from powerful teacher models to smaller students faces the Gap Curse: as teachers grow more sophisticated, their complex distributions increasingly diverge from what students can approximate, causing performance degradation. Existing mitigation strategies either filter out challenging examples through data selection or introduce weaker intermediate assistant models, inherently compromising supervision coverage or quality. We propose Teacher Alignment, which directly adapts the teacher toward the student's distribution without discarding data or degrading reasoning quality. However, naive alignment through standard knowledge distillation triggers catastrophic collapse of the teacher's reasoning capabilities. To address this, we reformulate teacher alignment as reinforcement learning and introduce TeacherGRPO, built on Group Relative Policy Optimization with two key innovations: (i) Curriculum Selective Alignment applies dual token- and distribution-level curricula to focus rewards on high-signal reasoning gaps while filtering noise from trivial tokens and uncertain tail distributions, and (ii) Importance-Adaptive Length Regularization selectively penalizes verbose redundancy while preserving pedagogically critical reasoning steps. The aligned teacher then distills knowledge to students via standard pipelines. Extensive experiments show TeacherGRPO significantly outperforms baselines across diverse reasoning benchmarks and distillation methods. Our code is available at https://github.com/LzyFischer/TeacherGRPO.

cs.CL↗

arXiv2026

KeyRec: Bounded Visual Memory for Streaming and Long-Video Understanding

Vision-language models are increasingly used to understand long videos and continuous streams. However, dense visual tokens accumulate with video duration, making long-context inference prohibitively expensive. Existing training-free visual-token selection methods reduce this cost by retaining informative tokens, but may lose coherent event evidence and fail to distinguish detailed recent observations from long-range history. We propose \textbf{KeyRec}, a training-free framework for constructing bounded visual memory. During query-agnostic writing, KeyRec preserves fine-grained recent observations in a visual cache and organizes historical evidence into a structured event bank. Candidate events are proposed according to their novelty relative to previously stored events and maintained through an online add--merge--evict update. When a question arrives, a text-only router adaptively allocates a fixed readout budget between recent and event memory, without reprocessing historical frames. KeyRec operates on model-facing visual embeddings and supports both modular encoder--projector VLMs and the encoder- and projector-free NEO-ov architecture. Across four streaming and long-video benchmarks and three VLM backbones, KeyRec achieves the best compressed performance in 13 of 15 settings using only 10\% of the dense decoder-facing visual-token budget. It outperforms the strongest compressed baseline by 2.21--18.37 points on real-time questions, achieves the best compressed result in five of six long-video settings, and performs best in every NEO-ov 2B setting.

cs.CV↗