arXiv subjects

Yi Chang

Publications and source records attributed to Yi Chang.

At least 19 recordsLinked to original sources

arXiv2026

EvoTeam: Multi-Agent Collaboration via Evolving Teams

LLM-based multi-agent systems (MAS) rely on collaboration among specialized agents to solve complex tasks. Existing methods improve MAS by refining the prompts, skills, and execution strategies of individual agents based on task feedback. However, improving individual agents does not necessarily lead to better team collaboration. Recent studies have therefore extended evolution to the collaboration level, using collective execution experience to adjust team organization, and inter-agent interactions. Nevertheless, evolving collaboration across heterogeneous tasks remains challenging, as existing approaches often constrain team reorganization within a shared structure and reuse interaction rules across incompatible team contexts. In this paper, we propose EvoTeam, a collaboration-centric evolution framework that jointly evolves team organization, interaction rules, and individual agent skills through execution experience. It maintains a library of reusable teams, selecting or creating agent teams and guiding collaboration through team-specific interaction rules. Collaboration experience accumulates within compatible team contexts, while individual skills remain reusable across teams. Experiments across four benchmarks demonstrate its effectiveness. Our code is available at https://github.com/DEEP-JLU/EvoTeam.

cs.AI↗

arXiv2026

SOS-LoRA: Static Orthogonal-Subspace Low-Rank Adaptation with Fixed Multi-Scale Scaling

Low-Rank Adaptation (LoRA) is a widely used parameter-efficient fine-tuning (PEFT) method for large language models. Under a fixed rank budget, LoRA parameterizes each adapted weight through a single low-dimensional input-side pathway, which may couple heterogeneous behaviors through shared input directions and induce interference during optimization. We propose Static Orthogonal Subspace LoRA (SOS-LoRA), a drop-in extension that reparameterizes a rank-rtot update as a sum of K static (always-on, non-routed) low-rank experts. SOS-LoRA (i) decomposes the total rank across experts, (ii) applies a fixed multi-scale scaling scheme to encourage scale-separated optimization dynamics, and (iii) promotes diverse input-side directions via cross-expert orthogonal initialization and a lightweight regularizer. SOS-LoRA remains fully mergeable, adding no inference-time parameters or latency after merging. Experiments on reasoning and knowledge-intensive benchmarks (Llama 2/3), encoder-based NLU (GLUE), and math reasoning (GSM8K/MATH) show consistent gains over matched-budget LoRA baselines and recent variants. Code is available at https://github.com/llm172/sos-lora.

cs.LG↗

arXiv2026

BOSS: Token-Budgeted Online Sampling and Selection for LLM Reasoning

Test-time scaling can improve LLM reasoning, but existing approaches typically adapt generation or apply answer selection after a predetermined generation schedule. We study within-instance allocation: under a hard per-instance prompt-plus-completion token cap, when should inference stop, generate another candidate, or spend residual tokens adjudicating candidates already observed? BOSS is a training-free policy for this three-way decision, with worst-case budget checks before every generation and judge call. Its key contribution is online generation-adjudication allocation under one shared token ledger. Across two Llama-3.1 models and four reasoning benchmarks, BOSS attains the highest accuracy in 22 of 24 model-task-budget cells under the common hard cap. At Llama-3.1-8B and B=4k, it reaches 60.5 macro-average accuracy versus 58.6 for Adaptive-Consistency, 59.1 for TALE-EP, and 58.9 for fixed-schedule League. On identical Stage-I candidate pools, randomized A/B judging with repeated voting improves plurality from 58.4 to 60.3, with the full BOSS selector reaching 60.5. Approximately matched-cost controls further characterize how the benefit of adjudication changes with available inference budget. Together, these results establish generation-adjudication allocation as a distinct design axis for reasoning under strict per-instance caps.

cs.AI↗

arXiv2026

Answer Delivery Under a Shared Token Budget: An Audited Study of Stopping and Finalization

An inference budget is useful only when the system delivers an answer within it. We study a fixed-budget policy combining first-valid-box stopping with a charged finalization cue. On 100 fresh, independently audited GSM8K test questions per model, it improves delivered endpoint accuracy over first-box stopping by 8.0 percentage points for Qwen3-4B-Thinking-2507 and 7.0 for DeepSeek-R1-Distill-Llama-8B. A prelocked repeat on the same questions gives 7.0 and 10.0 points; neither seed shows a gross harm relative to first-box stopping. The point estimates of incremental physical-slot savings are below one percent. A finalization-only ablation separates cue recovery from stopping, and a fixed scalar reader tests extraction as an alternative explanation. The cue is prior art; the contribution is a component and readout analysis with charged injections and verified paths. Results cover two checkpoints, one task, one prompt family, and two fixed seed conditions.

cs.AI↗

arXiv2026

PremiseSQL: Evaluating Premise Critique and Abstention in Text-to-SQL Systems

Recent advances in large language models (LLMs) have substantially improved Text-to-SQL performance, yet existing NL2SQL systems largely assume that user queries are valid and answerable. As a result, models often generate executable SQL even for queries with flawed premises. We introduce premise critique ability in NL2SQL, namely the ability to recognize flawed queries and abstain from generating misleading SQL. To evaluate this capability, we propose PremiseSQL, a benchmark containing 1,800 flawed NL2SQL queries across four categories of premise failures, along with their 1,800 original queries. We further design an evaluation framework to measure intrinsic and prompt-induced premise-aware behavior across three prompting settings. Experiments on frontier LLMs show that current models are strongly premise-trusting by default and rarely critique flawed premises. Stronger critique-oriented prompting improves detection and abstention on flawed queries, but also increases false invalid judgments and suppresses SQL generation on originals. The code is available at https://github.com/vegeet/PremiseSQL.

cs.CL↗

arXiv2026

More Choices, Fewer Decisions: Ordinal-Scale Bias in JEV-like Direct-Decision Models

Direct-decision models enable efficient classification and evaluation by selecting from predefined candidates, but their reliability depends on more than prediction accuracy. Across 40 datasets and nine models from the JEV, KEV, and StartLux Decision families, we identify a systematic tendency to underuse ordinal rating scales. We call this phenomenon ordinal scale-utilization bias: final decisions concentrate on fewer effective labels than the gold distribution. The bias is substantially weaker on tasks with unordered semantic categories. Evaluating the same items on finer ordinal scales strengthens compression despite controls for gold imbalance and candidate position. Randomizing candidate order reduces but does not eliminate compression, while widening ordinal gaps at fixed candidate count can improve accuracy without restoring utilization. For most models, concentrated decisions coexist with broad average candidate probabilities. Greater model size improves accuracy without consistently restoring scale utilization. Together, these findings characterize compression as strongly associated with ordinal structure and intensified by scale refinement, rather than fully explained by presentation position or local spacing. This bias can be effectively mitigated through targeted training, making scale utilization an actionable reliability target alongside accuracy. The code and data are available at https://anonymous.4open.science/r/jev_ordinal_scale_bia/.

cs.AI↗

arXiv2026

ReFormBench: Benchmarking the Stability of Response-Conditioned Format Correction in Large Language Models

Reliable use of large language models requires responses to satisfy formatting requirements across changing instructions. Standard compliance scores do not distinguish preserving a model's observed format from correcting it, or reveal whether that correction holds across variants. We introduce ReFormBench, a benchmark that uses each model's unconstrained response to the same question as its formatting baseline. It links targets by feature and require/forbid mode, evaluating their instantiated requirements across variants. ReFormBench comprises 5,000 difficulty-screened three-constraint test instances derived from 910 source questions and covering 66 formatting features. TCPR measures complete instruction compliance, while EMCR measures individual and joint correction of targets opposed to the annotated baseline state. Across ten models, EMCR ranges from 34.04% to 64.72%, and the highest three-target correction estimate is 50.02%. Compliance and correction scores yield different model rankings and task-level profiles. A prompting experiment on Qwen3.5-9B improves both metrics, and the catalog covers over 95% of extracted instances on four additional models. ReFormBench makes response-conditioned correction across instruction variants a measurable dimension of format following. The code and data are available at https://anonymous.4open.science/r/ReFormBench/.

cs.AI↗

arXiv2026

CSWBench: Evaluating Context-Sensitive Code-Switching in Creative Writing

Large language models (LLMs) have demonstrated multilingual capabilities across diverse language generation and understanding tasks. Yet effective code-switching requires more than multilingual proficiency: models must decide when, where, and why to switch languages in ways that fit the surrounding context. This context-sensitive ability remains insufficiently evaluated. We introduce CSWBench, a benchmark for evaluating context-sensitive code-switching in creative writing through two complementary settings: Focused Narrative and Extended Narrative. We further propose CSWEval, a theory-informed framework with two complementary levels: event-level evaluation of Licensing, Contextual Appropriateness, and Functional Gain, and whole-text evaluation of task-specific quality---overall literary and narrative quality in Focused Narrative and quality emphasizing multilingual organization in Extended Narrative. Evaluating twelve LLMs, we find that models exhibit meaningful but uneven code-switching competence across narrative contexts. Model differences are particularly pronounced in multilingual literary integration, while multilingual-focused dimensions show stronger difficulty effects overall than the general narrative dimensions; narratively salient switches are associated with stronger contextual and functional realization; and event-level CS quality is moderately associated with whole-text performance.

cs.CL↗

arXiv2026

TRACESTEER: Trace Driven Activation Steering for Hallucination Mitigation in Diffusion Language Models

Diffusion large language models (dLLMs) have emerged as a promising alternative to autoregressive LLMs, yet remain susceptible to hallucination. Activation steering offers a promising mitigation approach by guiding parallel token predictions through internal representations. However, existing steering methods largely overlook two characteristics of dLLMs: dynamic denoising states and temporal hallucination risks, which challenge predefined steering vectors and uniform intervention strengths. We propose TRACESTEER, a trace-driven activation steering framework that uses preceding denoising predictions as feedback to jointly adapt steering direction and strength. Specifically, Denoising Feedback Steering (DF-Steering) constructs step-specific steering vectors from preceding predictions and current hidden states. Trajectory-Guided Steering Gate (TS-Gate) regulates their strength using prediction uncertainty and the denoising timestep. With the backbone frozen, factual supervision and magnitude regularization jointly guide the learning of adaptive steering interventions, promoting factual reliability and stability throughout denoising. Experiments on two dLLMs show improved factual reliability on TruthfulQA and generalization across five downstream benchmarks.

cs.CL↗

arXiv2026

Beyond Outcome Feedback: Trajectory-Quality-Guided Experience-based Learning

Experience-based learning enables large language model (LLM) agents to improve over time by reusing knowledge from past executions. However, existing methods typically rely on final task outcomes as feedback for experience learning, overlooking the execution process and limiting their ability to evaluate and optimize experience based on trajectory quality. To address this limitation, we propose TQG-Exp, a trajectory-quality-guided experience-based learning framework that introduces process feedback. Specifically, we introduce Trajectory Quality Loss (TQL), which jointly considers task completion and process quality to provide a learning signal beyond final task outcomes. Based on this signal, we employ paired rollouts with and without retrieved experience to guide experience optimization. Representative trajectories are selected based on their outcomes and trajectory quality to extract task-level and task-type-level experiences. Meanwhile, differences in trajectory quality between the paired groups are used to estimate the contribution of retrieved experience and update its utility. The learned utility is then combined with semantic relevance to guide subsequent experience retrieval. Experiments on ALFWorld, WebShop, and ScienceWorld with two backbone LLMs show that TQG-Exp outperforms existing experience-based methods, improving Avg.@3 over the strongest baseline by 4.50 and 8.55 percentage points on DeepSeek-V4-Flash and Qwen3.5-Flash, respectively.

cs.AI↗

arXiv2026

CCRV-Bench: Constraint-Based Evaluation of Causal Reasoning in Vision-Language Models

Vision-language models (VLMs) have demonstrated excellent performance in visual tasks, but their visual causal reasoning capabilities still lack reliable evaluation. Existing evaluations struggle to distinguish whether a model is performing causal reasoning based on visual evidence or relying on statistical correlations for shortcut learning, thereby potentially overestimating their actual capabilities. This paper proposes CCRV-Bench, a constraint-driven visual causal reasoning benchmark for single-image physical scenarios. We construct an orthogonal framework that evaluates four causal task dimensions: causal relation discovery, state prediction, causal diagnosis, and intervention-outcome prediction. We further introduce entity symbolization, spatial grounding, the factual adversarial constraint, and minimalist output constraints to reduce shortcut cues while preserving the physical commonsense required by the task. Experiments across 14 multimodal models show that constraint sensitivity is task- and model-dependent: intervention-outcome prediction has the largest average effective degradation among the four causal tasks, spatial grounding is the most damaging constraint on average, and the factual adversarial constraint improves DCR for all evaluated models. These results show that unconstrained performance does not determine constrained robustness and that a single aggregate score can obscure distinct failures in causal identification, spatial grounding, and constraint-compliant expression. CCRV-Bench provides a standardized framework for diagnosing image-grounded causal reasoning under controlled constraints. The code is available at https://github.com/0815linyuan/CCRVBench

cs.CV↗

arXiv2026

CombEval: A Framework for Evaluating Combinatorial Counting in Large Language Models

We present CombEval, a dynamic benchmark for evaluating combinatorial counting in large language models. CombEval represents each problem as a typed Cofola specification over entities, combinatorial objects, object dependencies, and constraints, enabling controlled generation of natural-language counting problems with exact solver-verified answers. Unlike static collections, CombEval supports systematic variation of object type, entity scale, constraint count, and reasoning depth. We evaluate 11 LLMs under direct and code-augmented settings and find that models remain brittle on ordered objects, indistinguishable elements, relatively positional constraints, and nested object dependencies. Error analysis further identifies failures in constraint interpretation and counting principles. CombEval provides a diagnostic testbed for studying when and why LLMs fail at combinatorial reasoning. The code and generated benchmark suites are publicly available at https://github.com/YuxuZhou-CN/combination-problem-generation.

cs.AI↗

arXiv2026

Denoising-Enhanced Coarse-to-Fine Infrared Small Target Detection with Attention Prior-Guided Knowledge Distillation

Infrared small target detection (IRSTD) in high-resolution images is crucial for unmanned aerial vehicle (UAV) surveillance and UAV-based ground monitoring. However, small target size, weak features, and interference from complex dynamic backgrounds make IRSTD challenging. Existing methods incur redundant computation in non-target background regions and insufficiently exploit target context, limiting detection performance. To address these issues, we propose ECFNet, an efficient coarse-to-fine IRSTD framework with attention prior-guided knowledge distillation. In the coarse stage, we design a region binary classification network (RBCN) on grid-based multi-scale feature maps to efficiently identify target-containing context region proposals. A new denoising-assisted training strategy incorporates noisy ground-truth (GT) masks into RBCN feature maps and trains the network to reconstruct the original GT masks. This auxiliary task encourages explicit learning of target-background context to better distinguish target proposals from background regions. In the fine stage, we customize a lightweight target detector to the coarse-stage region proposals to balance accuracy and efficiency. Furthermore, we introduce a knowledge distillation strategy guided by a teacher-student cross-attention prior. This strategy directs the student to focus on critical target regions, enhancing discriminative feature representations for infrared small targets. Extensive experiments on three real infrared datasets demonstrate that ECFNet outperforms existing single-stage and two-stage approaches while maintaining high real-time processing efficiency. Code: https://github.com/IVPLabs/ECFNet.

cs.CV↗

arXiv2026

When VLMs Trust Context: Evaluating Scene Text Recognition under Misleading Context

Vision-language models (VLMs) can read text in natural scenes, but their predictions may be influenced by the surrounding context. When the printed text conflicts with what the scene suggests, a model may return a more plausible word instead of the shown text. We introduce SceneFaith, a benchmark of 781 generated scene images for studying this behavior. Each output is classified as Literal, Canonical, or Other, separating faithful transcription from context-consistent rewriting and ordinary recognition errors. Across 15 models from seven families, all models show rewriting on clear images, with rates ranging from 8.45\% to 58.51\%. Controlled experiments further show that surrounding context matters: removing surrounding scene information reduces rewriting and improves literal accuracy, while changing the scene around the same text patch can also change model outputs. Moreover, weakening the target text with blur increases rewriting. These results show that reliable scene-text recognition requires VLMs to balance visual character evidence with contextual information, preserving clear text while using context mainly when the visual evidence is uncertain.

cs.CV↗

arXiv2026

ConflictVLA-Bench: Benchmarking Behavioral Responses of Vision-Language-Action Models to Premise Conflicts

While Vision-Language-Action (VLA) models perform strongly on manipulation tasks, their responses to invalid task premises remain underexplored. Existing evaluations of premise conflicts often focus on terminal task outcomes, yet task failure alone cannot distinguish behavioral disengagement from continued pursuit followed by an execution error. We call the latter pattern Failed Persistence. To study this phenomenon, we introduce ConflictVLA-Bench, which pairs conflict rollouts with premise-consistent reference rollouts and evaluates both outcomes and execution processes. Built on LIBERO, the benchmark contains 2,826 prompt-conditioned conflict tasks spanning four conflict families, four structural configurations, and two prompt conditions. Across all eight VLAs, invalid premises reduce original goal completion by at least 17.3 percentage points, with the reduction reaching 56.2 percentage points for OpenVLA. Crucially, even when models succeed on premise-consistent tasks and fail on their matched conflict tasks, they often continue to approach the original targets, retain early trajectory structure, and show limited action magnitude suppression. Failed Persistence therefore recurs across the evaluated models. Explicit premise checking does not consistently produce selective and coordinated behavioral changes. These findings show that terminal failure alone establishes neither behavioral disengagement nor refusal and that outcomes alone are insufficient for VLA evaluation. Experimental data and additional details are available on the project page: https://github.com/EmbodiedAISurvey/ConflictVLA-Bench

cs.AI↗

arXiv2026

Semiparametric Receiver Operating Characteristic Analysis in the Presence of an Imperfect Reference Standard via a Box-Cox Density Ratio Model

Receiver operating characteristic (ROC) analysis is commonly used to evaluate the diagnostic accuracy of continuous biomarkers. In practice, the true disease status may be unavailable and only a nominal disease status provided by an imperfect reference standard is observed. Existing nonparametric methods have been developed for ROC analysis in this setting, but may suffer from reduced estimation efficiency, numerical instability, or sensitivity to the choice of biomarker scale. We propose a semiparametric method based on a Box-Cox density ratio model, which links the biomarker distributions of the truly healthy and diseased populations while leaving the baseline distribution unspecified. A key feature of the proposed method is that the transformation parameter is estimated from the data rather than specified in advance, allowing the density-ratio structure to adapt to different transformation scales. We develop an empirical likelihood approach for estimation and an expectation-maximization algorithm for computation. We establish the asymptotic distributions of estimators of the ROC curve, area under the curve, Youden's index, and the sensitivity and specificity at the Youden-optimal cutoff, and develop bootstrap confidence intervals and a goodness-of-fit test. Simulation studies demonstrate that the proposed method provides accurate and numerically stable estimation and inference across a range of distributional settings without requiring the transformation scale to be specified in advance. The proposed method is illustrated using data from a malaria study.

stat.ME↗

arXiv2026

Beyond Distribution Matching: Semantics-Consistent Tabular Diffusion with Weak Semantic Priors

Synthetic tabular data can match real data distributions while still violating the semantic constraints that govern valid tabular rows. This reveals a key limitation of existing tabular generators: they mainly optimize distributional fidelity, but do not explicitly model weak semantic priors encoded in tabular schema and textual descriptions. In this paper, we propose \ours, a semantics-consistent tabular diffusion framework for high-fidelity synthetic data generation under weakly specified semantic priors. \ours\ first constructs two types of priors, namely intra-column semantics and inter-column symbolic rules, with LLM-assisted extraction from metadata and validation on the real training split. These priors are then used as generation conditions rather than post-hoc filters. Specifically, \ours\ maps heterogeneous column values, column identities, and semantic priors into a unified semantic space, and performs column-wise forward corruption and prior-conditioned reverse denoising to preserve both marginal distributions and rule-consistent cross-column dependencies. Extensive experiments on six real-world tabular benchmarks show that \ours\ consistently improves distributional fidelity, semantic consistency, and downstream task utility over representative VAE-, GAN-, LLM-, and diffusion-based baselines. Additional analyses further demonstrate the robustness of \ours\ when semantic priors are partially unavailable.

cs.LG↗

arXiv2026

What if LLMs Ate Their Words: Causal History Effects in Multi-Turn Interaction

Multi-turn interaction creates a feedback process in which an LLM's previous responses become context for later behavior. Prior work shows substantial multi-turn degradation and that assistant-generated history can affect later behavior. However, it remains unclear how these effects manifest across models, tasks, turns, and inside a model. We study these gaps across six task families and five models. Degradation from fully specified single-turn input (FULL) to progressively revealed multi-turn interaction (SHARDED) is clearly task- and model-dependent, and stronger one-shot performance does not imply greater interaction robustness. We then retrospectively analyze completed SHARDED conversations by replaying the user messages already observed in each trajectory while editing only assistant-generated history. Replacing prior assistant responses with neutral content (termed neutralization) changes downstream min-max normalized performance by +.027 across 2,973 trajectories. On a prespecified length-controlled subset, short and length-matched neutralization yield nearly identical effects (+.069 versus +.068), showing that simple context shortening is insufficient to explain the effect of history editing. Turn Surgery further intervenes on one assistant turn at a time. Among 237 selected degraded trajectories, 63.7% contain at least one beneficial intervention, while most tested positions remain unchanged; for binary tasks, 48.4% admit a fail-to-success reversal. An open-weight case study links behaviorally consequential history changes to measurable downstream state differences, but finds task-dependent rather than universal internal signatures. Overall, assistant-generated history has active but selective effects on multi-turn performance, motivating selective rather than uniform history management.

cs.CL↗