Search arXiv⌕ Search

arXiv subjects

Xueqi Cheng

Publications and source records attributed to Xueqi Cheng.

At least 19 recordsLinked to original sources
arXiv2026

MarkovTS: Pretrained State-Transition Representations for Zero-Shot Time Series Generation

Across heterogeneous real-world domains, time-series generation supports simulation, model development, and data augmentation by generating sequences that preserve target-domain statistics and temporal dependencies when real observations are scarce or costly. However, existing methods predominantly address in-domain generation, limiting their reuse in unseen domains. We study reference-conditioned zero-shot time series generation: target domains are unseen during pretraining, generation uses a single target-domain reference sequence, and no model parameters are updated. MarkovTS characterizes sequence evolution through local morphologies and their ordered transitions at multiple temporal scales. Its pretrained encoder quantizes normalized time-series patches into multiscale morphological states with a state codebook, while a transition codebook encodes contextual transitions between adjacent intervals. These transferable state-transition representations condition a pretrained flow-matching model. At generation, the frozen model combines a reference-derived condition with independent Gaussian noise to produce stochastic samples that retain the reference's temporal organization. Across 12 unseen target datasets, MarkovTS outperforms strong baselines in most distributional comparisons and generates diverse, reference-consistent sequences. As downstream augmentation, its samples yield overall gains across forecasting, classification, and anomaly detection benchmarks and diverse model families. Our code is available at https://github.com/blisky-li/MarkovTS.

cs.LG↗
arXiv2026

HieraNTP: Structured Risk Representations for Time-Series Anomaly Detection via Hierarchical Next-Token Prediction

Time-series anomaly detection commonly converts deviations from learned temporal regularities into anomaly scores. This practice can conflate violations of temporal regularity with task-specific anomaly judgments: the same deviation may be anomalous under one task definition and benign under another. Aggregating heterogeneous deviations into a single score before task-specific adaptation can obscure the evidence needed to distinguish these cases. We introduce HieraNTP, a Hierarchical Next-Token Prediction framework that separates self-supervised predictive modeling from task-specific risk interpretation. HieraNTP pretrains a hierarchical tokenizer and a causal next-token predictor to capture temporal regularities at multiple scales. It then organizes prediction discrepancies into a structured risk representation, preserving complementary evidence across temporal scales in token, local-statistic, and observation spaces. A task-adaptive detector uses anomaly labels to select and combine this evidence for the target task. Across anomaly detection benchmarks, HieraNTP improves VUS-PR by 12.0% on TSB-AD-U and 15.5% on TSB-AD-M relative to the strongest baselines, and achieves the highest composite score on both TAB tracks, with controlled comparisons supporting the value of retaining distinct evidence. Our code is available at https://github.com/blisky-li/HieraNTP.

cs.LG↗
arXiv2026

MemBubble: Benchmarking How Agent Memory Shapes LLM Response Diversity

Memory serves as the core component of LLM-based agents, enabling personalized responses via extracting and using user preferences from past interactions. However, its use may reduce response diversity, thereby narrowing the range of information available to users. Existing evaluations rely largely on synthetic interactions and cover few memory systems, leaving the effects of memory on response diversity insufficiently evaluated in real-world scenarios. We introduce MemBubble, a benchmark of 1000 instances built on preferences extracted from real user-assistant conversations. To measure the extent to which memory concentrates response distributions, we construct test queries in scenarios distinct from user preferences while preserving topical relevance through shared preference categories. Across multiple LLMs and memory mechanisms, entropy decreases by 34.7% on average compared with directly providing the full interaction history, highlighting the important role of memory processing in diversity loss. We also explore simple user-side interventions and changes in information availability but find that these do not effectively close the diversity gap. Our findings highlight the need to consider preserving diversity and user access to information alongside improvements in personalization when designing and using agent memory systems.

cs.CL↗
arXiv2026

How Do LLM-Generated Texts Impact Term-Based Retrieval Models?

As more content generated by large language models (LLMs) floods into the Internet, information retrieval (IR) systems now face the challenge of distinguishing and handling a blend of human-authored and machine-generated texts. Recent studies suggest that neural retrievers may exhibit a preferential inclination toward LLM-generated content, while classic term-based retrievers like BM25 tend to favor human-written documents. This paper investigates the influence of LLM-generated content on term-based retrieval models, which are valued for their efficiency and robust generalization across domains. Our linguistic analysis reveals that LLM-generated texts exhibit smoother high-frequency and steeper low-frequency Zipf slopes, higher term specificity, and greater document-level diversity. These traits are aligned with LLMs being trained to optimize reader experience through diverse and precise expressions. Our study further explores whether term-based retrieval models demonstrate source bias, concluding that these models prioritize documents whose term distributions closely correspond to those of the queries, rather than displaying an inherent source bias. This work provides a foundation for understanding and addressing potential biases in term-based IR systems managing mixed-source content.

cs.IR↗
arXiv2026

Relevance Supervision Can Teach Neural Retrievers to Prefer LLM-Generated Text

Recent studies show that neural retrievers often exhibit source bias, ranking LLM-generated passages above semantically similar human-written ones, which threatens the reliability of modern information access systems. While this bias is often viewed as a model-level property, we show that relevance supervision itself can induce it. Empirically, source bias is clearest in relevance-supervised retrievers, and the same encoders become more LLM-preferring after relevance fine-tuning. We trace this effect to surface-level artifacts in supervised retrieval data: annotated positives and negatives differ systematically in properties such as fluency and lexical specificity, and these differences parallel those between LLM-generated and human-written passages. As a result, retrievers can learn artifact-based shortcuts for relevance. We further show theoretically that, under contrastive learning, artifacts that reliably separate positives from negatives can be encoded into learned relevance scores. Motivated by this mechanism, we propose complementary strategies that reduce source bias during training and at inference: balancing artifact distributions in negative sampling and removing the artifact-aligned embedding component, respectively. Overall, our findings support a data-centric view of source bias: retrievers may prefer LLM-generated text not merely because of inherent model properties, but because relevance supervision teaches them to rely on surface-level artifacts.

cs.IR↗
arXiv2026

Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents

Agents driven by large language models are increasingly deployed on long-horizon tasks, where they use tools and modify real workspaces. How well they perform depends as much on the harness around the model as on the model itself. Existing benchmarks measure downstream task success under a fixed harness, leaving harness engineering itself unexplored. We propose Doc2Harness, a two-stage benchmark that evaluates long-horizon harness engineering directly. In Stage 1, a build model operating inside a fixed builder harness receives an interface-only contract skeleton and a development document that consolidates behavior across twelve frontier harnesses, and then constructs a complete candidate harness in an isolated container. In Stage 2, the frozen candidate harness runs in containers separate from the construction environment, one per test case, and is driven end to end by a scripted mock model. We score each test case using four observable channels, namely the requests sent to the model, the files on disk, the process exit code, and the command output; positive controls rule out vacuous passes. Across nineteen frontier models, each evaluated with three independent builds on 328 test cases, GPT-6 Astra achieves the highest pass rate at 53.05%, while the weakest model reaches 27.44%, a gap of roughly twenty-six percentage points. Even the strongest model fails nearly half of the test cases, and failures cluster around how cross-cutting functionality is split across modules. To our knowledge, Doc2Harness provides the first deterministic benchmark for measuring long-horizon harness engineering.

cs.SE↗
arXiv2026

SelfEvoSkill: Paired Execution Audits for Skill Revision without External Outcome Supervision

Agent skills provide LLM agents with reusable procedures, but a given skill may be incomplete, ineffective, or misleading for the current task. Existing methods for revising skills typically rely on external outcome supervision, such as task rewards, performance on a separate validation set, or feedback from deployment, to decide which updates to retain. However, this supervision may be costly or unavailable when adapting a skill to a new task. Using execution behavior as an alternative signal is challenging: a single run reflects the combined effects of the agent, task, and workspace, making the skill's contribution difficult to isolate. Comparing executions with and without the skill, while holding these factors fixed, provides evidence about how the skill changes behavior. We introduce SelfEvoSkill, which links these behavioral differences to relevant skill passages and iteratively revises and reevaluates those passages through subsequent executions. Checks derived once from the task's explicit requirements prevent revisions from violating task constraints. Across 89 containerized tasks in 8 professional domains, under the same best-of-two evaluation budget, SelfEvoSkill attains a 73.9% mean task reward, exceeding the no-skill condition by +33.0 percentage points and the benchmark's curated skill by +17.2 percentage points, while skill evolution receives neither task rewards nor benchmark verifier outputs. In controlled ablations, using two with-skill runs instead of a matched with/without-skill pair reduces mean reward by 4.6 percentage points, while limiting revision to one round reduces it by 9.0 points relative to repeated revision. Together, these results show that behavioral differences between matched executions can provide an effective signal for revising skills when outcome supervision is unavailable.

cs.AI↗
arXiv2026

HazardWeaver: Scientific Route Selection for Hazard Analysis Agents

Understanding and assessing natural hazards is essential for disaster preparedness and risk reduction. Recent advances in large language models have spurred growing interest in AI agents for hazard analysis, particularly their ability to integrate scientific data, models, and tools into automated workflows. However, effective automation requires agents to determine which scientific methods are appropriate for a given event and executable with the available data and tools. As new evidence and execution results become available, these conditions can change, requiring agents to reconsider their choices. We formulate this problem as state-dependent scientific route selection and introduce HazardWeaver. Specifically, HazardWeaver first leverages the Hazard Knowledge Compiler to extract evidence-linked conditions governing scientific applicability, then its Hazard Capability Graph represents executable scientific capabilities and checks compatibility between their inputs and outputs. Using these complementary representations, the Hazard Weaver Agent component selects applicable and executable routes, carries out their workflows, and revises its decisions as the analysis state changes. To evaluate both the scientific outputs and the decisions that produce them, we introduce the Hazard Weaver Benchmark, comprising 141 instances across seven single-hazard domains and four multi-hazard interaction classes. The benchmark accommodates multiple valid scientific routes and evaluates output correctness, route validity, and justified abstention. Extensive experiments on this benchmark show that HazardWeaver outperforms existing agent systems, with the largest gains on tasks with multiple eligible scientific routes. Our code is publicly available at https://github.com/LabRAI/HazardWeaver.

cs.AI↗
arXiv2026

Capability Scaling-Down Laws for LLM Compression

LLM compression reduces inference costs and memory requirements, but selecting a method and configuration remains largely empirical because comparable resource reductions can produce different capability losses. We systematically investigate capability scaling-down laws for LLM compression across pruning, quantization, and distillation. Our framework measures capability loss in mathematics, code generation, and question answering, and relates these measurements to model size, training stage, compression settings, data availability, and training exposure. We develop simple predictive relations and evaluate their accuracy, measurement efficiency, and generalization to unseen configurations and model states. Sharing the density response across pruning levels halves the configuration measurements needed to fit a pruning predictor: on new Pythia states, on pre-registered OLMo-2 test states and under Wanda pruning, the compact relation matches a regression fitted with all measurements on math and code to within 0.020 nats per token, with coefficients refitted for each setting. Controlled distillation experiments show that the cost of heavy data reuse recurs across question-answering distributions, while the net benefit depends on the evaluation distribution. We further evaluate the decision value of these predictions by comparing numerical selection with configuration medians and fixed method priorities. Independent evaluations across two model families show that selection captures most of the available cross-method benefit for question answering within the tested candidate sets, where a fixed method priority attains the same regret, with smaller opportunities for mathematics and code. These results clarify the predictive scope of capability scaling-down laws and their use in compression method selection. Our code is publicly available at: https://github.com/LabRAI/scaling_down_law.

cs.LG↗
arXiv2026

Experimental Experience Modeling for Autonomous Research

Autonomous research agents can generate hypotheses and conduct experiments, but experimentation remains a major source of computational cost. A fundamental challenge is deciding which experiments are worth running, particularly when prior evidence is insufficient to resolve uncertainty. Yet current research agents lack a systematic way to leverage experimental experience when making such decisions. We introduce Experimental Experience Modeling (EEM), a framework for making informed experimental decisions by acquiring, reusing, and accumulating experimental experience. EEM extracts decision-relevant records from earlier experimental trajectories, distills them into reusable experience, and organizes them in an experience library. For a new experimental decision, EEM retrieves relevant historical experience and assesses whether it provides sufficient support for deciding whether a candidate direction warrants further investment. When historical experience is insufficient, EEM conducts a targeted, low-cost pilot experiment to acquire the missing decision-relevant experience on demand. It then combines this newly acquired experience with retrieved historical experience to determine whether the direction warrants full-scale evaluation, which requires substantial resources. The resulting experimental outcomes are further distilled into reusable experience, allowing the library to continually grow through iterative accumulation. Experiments on autonomous research benchmarks show that EEM improves research performance while reducing model interaction overhead, demonstrating the value of reusing accumulated experience and acquiring additional experience only when needed.

cs.AI↗
arXiv2026

Faithful Chart Generation for Multimodal Deep Research: Frame-Evidence Co-Adaptation

Analytical charts in multimodal deep research encode quantitative claims, requiring every visualized value to be faithfully grounded in supporting evidence. Unlike retrieved images that mainly provide contextual information, charts require numerical fidelity: visualized values should not only match retrieved evidence quantitatively but also preserve its original meaning and scope. However, achieving such fidelity remains challenging because current systems usually construct visualization plans before knowing what quantitative evidence can actually be retrieved from the web. As a result, predefined plans may require entities, temporal ranges, or comparison dimensions that the retrieved evidence only partially supports. Existing approaches mainly address this issue through post-hoc verification after chart plans are fixed, enabling unsupported values to be identified but leaving the underlying visual frames unchanged. To address this challenge, we propose Frame-Evidence Co-Adaptation (FECA), an evidence-adaptive visual planning framework for multimodal deep research. Inspired by the bidirectional sensemaking process in Data-Frame Theory, FECA models chart generation as an iterative interaction between visual frames and retrieved evidence. Each visual frame is adaptive: the frame guides evidence acquisition, while retrieved evidence determines whether the frame should be accepted, revised, or dropped before rendering. By coupling visualization planning with evidence availability, FECA shifts chart generation from fixed-plan verification to adaptive evidence-grounded visual reasoning. Experiments on 100 real-world research topics show that FECA substantially improves numerical fidelity while preserving report quality and chart utility.

cs.HC↗
arXiv2026

SkillAtlas: An Attack Trace Library for Agent Skills

Agent skills are reusable units for language-model agents, but their risks emerge through model decisions, user context, tool calls, and execution feedback rather than through stable signatures or a single sandbox run. Existing static, dynamic, and benchmark-style evaluations rarely preserve public evidence that can be inspected, searched, and reused. We present SkillAtlas, a hosted attack trace library that converts private agent-skill security report bundles into reviewed, redacted, and searchable public cases. The library contains 3,014 cases, 6,589 traces, 151,131 steps, 233 affected skills, and 8 risk categories; 42.5% of successful cases first become successful after a non-success initial round, and trajectory-grounded labels improve pre-execution guard accuracy to 0.770.

cs.CR↗
arXiv2026

Shared Experience, Separate Learning: Companion Confidence Calibration for LLMs

Reliable self-assessment is essential for large language models (LLMs), yet they often remain highly confident when their answers are wrong. We study \emph{concurrent confidence calibration}, where confidence is learned alongside capability improvement rather than calibrated only after training. Reinforcement learning from verifiable rewards (RLVR) provides a natural setting for this paradigm, as it continuously produces responses paired with verifiable correctness feedback. Existing concurrent methods, however, learn both capability and confidence through reinforcement learning within shared policy parameters, potentially coupling two fundamentally different learning problems. We instead propose \emph{shared experience but separate learning}: capability and confidence learn from the same trajectories, but through separate optimization mechanisms and parameters. Based on this principle, we introduce \textbf{CoCal (Companion Confidence Calibration)}, which trains a lightweight companion from rollout hidden states and verifier-derived correctness supervision while leaving task optimization unchanged. Experiments on Qwen3-8B and Qwen3-14B show that CoCal improves confidence estimation without sacrificing task performance, outperforming both RL-based concurrent methods and matched post-hoc calibration. The learned companion further generalizes across domains and policy shifts, while the benefits of CoCal persist at both scales.

cs.CL↗
arXiv2026

Beyond ID Embeddings: Process-Grounded Language Modeling for Cognitive Diagnosis

Cognitive Diagnosis Models (CDMs) play a pivotal role in personalized online learning. Traditional CDMs rely on discrete, ID-based embeddings to represent students, exercises, and concepts. This paradigm diverges from the nature of learner cognition, where knowledge is not stored and retrieved as isolated symbols. As a result, CDMs suffer from semantic limitations when new exercises or concepts appear. In this paper, we propose a Process-aware Language Cognitive Diagnosis (PLCD) framework that uses language-derived structures as cognitive priors and response records to calibrate student posterior states. PLCD leverages large language models (LLMs) to construct concept schemas and cognitive process graphs, and uses target-conditioned semantic memory to retrieve historical responses that are relevant to each target exercise. A process-grounded Language-to-Cognition Mapper with DA-MoE experts and process-level contrastive learning then maps the textual evidence into a unified cognitive space. Experimental results show that PLCD not only outperforms traditional baselines in predicting student performance but also exhibits strong cognitive transfer capabilities. These results connect the computational power of LLMs with the psychometric goal of measuring latent knowledge states, suggesting that structured language priors calibrated by response records can improve cold-start robustness and cognitive grounding.

cs.AI↗
arXiv2026

Less Is Personal: Learning Minimal Sufficient User Profiles for Personalized Language Models

Retrieval-augmented personalization enables large language models to produce more accurate and preference-aligned outputs using relevant records retrieved from user histories. Personalized language models typically prepend a fixed number of retrieved user records, even when additional history is redundant, harmful, or unrelated to a user's distinctive behavior. We study minimal sufficient personalization: constructing the least costly ordered profile for each input while preserving the utility achievable from a retrieved candidate pool. We introduce ENOUGH, a method that iteratively appends behavioral records or emits STOP to construct profiles with adaptive lengths. Offline, bounded counterfactual search evaluates profile prefixes by jointly considering downstream gains, user specificity, and token costs. The resulting long-horizon targets are distilled into a multi-head value controller with explicit ranking and stopping supervision. At inference, the controller selects and orders records through lightweight decisions, and the frozen generator is invoked once after stopping. Extensive experiments on six personalized tasks demonstrate that ENOUGH consistently outperforms strong heuristic and retrieval-augmented baselines in both effectiveness and efficiency, achieving minimal sufficient profiles that preserve personalization utility while reducing unnecessary context costs.

cs.AI↗
arXiv2026

Beyond Dialogue Time: Temporal Semantic Memory for Personalized LLM Agents

Memory enables Large Language Model (LLM) agents to perceive, store, and use information from past dialogues, which is essential for personalization. However, existing methods fail to properly model the temporal dimension of memory in two aspects: 1) Temporal inaccuracy: memories are organized by dialogue time rather than their actual occurrence time; 2) Temporal fragmentation: existing methods focus on point-wise memory, losing durative information that captures persistent states and evolving patterns. To address these limitations, we propose Temporal Semantic Memory (TSM), a memory framework that models semantic time for point-wise memory and supports the construction and utilization of durative memory. During memory construction, it first builds a semantic timeline rather than a dialogue one. Then, it consolidates temporally continuous and semantically related information into a durative memory. During memory utilization, it incorporates the query's temporal intent on the semantic timeline, enabling the retrieval of temporally appropriate durative memories and providing time-valid, duration-consistent context to support response generation. Experiments on LongMemEval and LoCoMo show that TSM consistently outperforms existing methods and achieves up to 12.2% absolute improvement in accuracy, demonstrating the effectiveness of the proposed method.

cs.AI↗
arXiv2026

HiDiffTIR: Hierarchical Difficulty-Aware Policy Optimization for Multi-Turn Tool-Integrated Reasoning

Tool-Integrated Reasoning (TIR) is a fundamental capability for LLM agents to solve complex tasks by interacting with external tools iteratively. Reinforcement Learning (RL) has become the dominant paradigm for enabling this capability. However, existing approaches typically assign uniform trajectory-level advantages and treat all correct tool calls equally, ignoring the varying difficulty and learning value across trajectories and reasoning steps. This can lead to imprecise learning signals that do not adequately distinguish between trivial and challenging tool-use patterns. To address this limitation, we propose HiDiffTIR, a Hierarchical Difficulty-aware policy optimization framework for multi-turn TIR. HiDiffTIR performs difficulty-aware credit assignment at both trajectory and turn levels, enabling the policy to focus on more informative trajectories and harder reasoning steps. Notably, this fine-grained optimization is achieved without additional supervision, relying solely on group-level statistics derived from standard RL rollouts. Extensive experiments on three tool-using benchmarks demonstrate that HiDiffTIR consistently improves multi-turn TIR performance and tool invocation accuracy over strong RL baselines, highlighting the necessity of difficulty-aware credit assignment for effective policy optimization in tool-integrated LLM agents.

cs.CL↗
arXiv2026

Popular but Wrong: Understanding and Mitigating LLM Overconfidence through Knowledge Popularity

Large language models (LLMs) often produce incorrect answers with high confidence, yet the factors associated with such overconfidence remain insufficiently understood. We study this problem through the lens of knowledge popularity. Using entity-centric factual QA derived from Wikidata triplets, we characterize popularity through question entity popularity, answer popularity, and question-answer co-occurrence. We find two consistent patterns. First, hallucinated answers are far from random: compared with ground-truth answers, they tend to be more popular or more frequently associated with the question entity. Second, confidence is strongly tied to the popularity of generated answers: even among incorrect predictions, more popular answers or those with higher question-answer co-occurrence receive higher confidence. Together, these findings suggest that popular but wrong alternatives may contribute to overconfidence. We further show that popularity-related signals can mitigate overconfidence and improve overall confidence estimation. Across six models and three datasets, incorporating knowledge popularity reduces average confidence on incorrect answers from 0.765 to 0.254 and overall ECE from 0.356 to 0.050, while improving Alignment from 77.08% to 83.72%.

cs.CL↗