arXiv subjects

Hanjun Wei

Publications and source records attributed to Hanjun Wei.

10 recordsLinked to original sources

arXiv2026

Correct Tests Are Not Enough: Measuring and Training Oracle Conversion in Specification-Based Test Generation

Generating tests from a natural-language specification requires both an input that exposes faulty behavior and a correct expected output. These requirements need not improve together: a model can increase test correctness by choosing easier inputs, or discover useful inputs whose expected outputs it cannot predict. We study this interaction through executable reward decomposition and suite-level oracle-conversion measurement. Our generator jointly emits five input--output tests in one response. During training, audited reference programs provide correctness feedback, while a fixed bank of faulty programs provides two utility signals: potential input kill and effective kill after checking the generated output. An additive GRPO objective preserves both signals without requiring execution at inference time. On an audited TC-Bench split with 506 training and 142 evaluation tasks, three independently trained Qwen3.5-9B runs at step 75 increase full-test correctness from 28.59\% to 42.54\%, input kill from 24.06\% to 25.27\%, and effective full kill from 12.23\% to 14.15\%. Matched 50-step ablations reveal a trade-off: removing kill rewards yields higher correctness and slightly higher full kill, but lowers input kill to 21.60\%. A fixed-input source--oracle crossover on 64 training-pool tasks attributes the principal NoKill-to-FullKill difference to harder input selection rather than worse output prediction on identical inputs. These results identify oracle conversion as a measurable bottleneck and show the benefits and limits of preserving input-utility feedback in joint test generation.

cs.SE↗

arXiv2026

How Output Format Confounds Data Quality and Capability in Instruction Tuning

Instruction-tuning data are judged by quality metrics, and tuned models are judged by benchmarks, but both judgments pass through an output interface: the surface format in which an answer is written. Using gradient signatures across 12 tasks, four semantically equivalent interfaces, three model families, and controlled corruptions, we show that this interface confounds both measurements. Spectral statistics such as effective rank are provably invariant to interface rotation and empirically blind to semantic corruption, while the direction of the update carries the quality signal. The interface-varying residual is not noise: it identifies each unit's own target task perfectly across all three families. Capability itself is stored relative to the training interface: a skill that raises accuracy by more than 40 points under the training format can be nearly invisible under every other, and correcting a single generation budget flips the measured effect of fine-tuning on GSM8K from a gain into a large loss. Pre-registered interventions delimit where this geometry stops short of control. Data quality and model capability are interface-conditioned quantities, and current practice often reports the interface instead of the content.

cs.CL↗

arXiv2026

Joint Training Is Not Enough: Conditioned Cross-Granularity Training for Multimodal Document Understanding

The Mutual Reinforcement Effect (MRE) asks whether a fine, span-level and a coarse, document-level task help each other when one model handles both. We test it in multimodal document understanding on three corpora, two of receipts and one of scanned business forms, comparing single-task, joint and conditioned training, which puts one granularity's gold output in the other's prompt during training only. We build Doc-MRE, an annotation layer pairing gold field extraction (point) with four document-level facets (line), from a three-judge LLM committee under a pre-registration, validated by blind re-annotation. One predicate, fixed in advance: at a shared recipe, a regime reinforces if it beats the matched single-task model on both granularities. Mixed joint training, the arrangement prior MRE work assumes, reinforces on no corpus at the main scale: it is below both single-task models on CORD and trades one granularity for the other on the two others, as single-task tuning does. Conditioned training reinforces on two of the three, CORD (+0.5 point, +4.8 line) and the forms corpus (+7.2 point, +11.0 line), resolvably on the coarse side and directionally on the fine one, and trades on WildReceipt; at that recipe no alternative measurably beats it on either side anywhere. Two byte-identical-prompt controls separate content from format: shuffled conditioning destroys the coarse-side skill but costs the fine side far less, and a neutral-content control reproduces the whole fine-side gain on WildReceipt, which is therefore prompt structure but buys nothing resolvable on the other two. On the forms corpus conditioning buys collapse avoidance: mixed training and the neutral control both assign the majority semantic label to all 50 test documents; only conditioning recovers the gold distribution. Probes find the information decodable under every regime with no resolvable increase under conditioning.

cs.CL↗

arXiv2026

Auditing and Decomposing Feedback-Driven Evolution in LLM Test Generation under the Oracle Problem

Execution feedback is often treated as a self-verifying signal for improving LLM-generated tests. However, when generated inputs are executed on a single accepted program and its outputs are used as ground truth, invalid or underspecified inputs can create spurious fault detections and apparent evolutionary gains. We audit this failure mode in feedback-driven test generation using 142 development tasks, 114 locked external tasks, and 138 held-out tasks, with two code models, three seeds, and fault-cross-fitted real submissions. On external inputs for which three accepted implementations agree, generated outputs match the panel on only 27.79% and 50.12% of cases. A single-reference oracle inflates the measured gain from evolution by 9.46-14.85 percentage points; after auditing, equal-budget independent resampling outperforms mutation-based evolution by 6.01-18.83 points. We further compare a genuine three-round feedback loop with a density-matched placebo. External Real-Placebo differences are +0.13 and -0.50 points, while held-out differences are +1.99 and +0.28 points and do not provide robust evidence of fine-grained feedback benefit. A blinded semantic audit by two software engineering doctoral students classifies 94.41% of panel-disconfirmed inputs as invalid but 3.60% as valid, showing that panel disagreement is informative but not semantic proof. We propose an audit-and-placebo protocol that separates verifier artifacts, interaction scaffolding, and grounded feedback credit in evaluations of self-evolving test generators.

cs.SE↗

arXiv2026

Security Tests as Executable Specifications for LLM Code Generation: Benefits, Trade-offs, and Coverage Limits

Large language models (LLMs) can generate functionally useful code that remains vulnerable, while security-focused interventions may break intended behavior. We investigate security tests as executable specifications both before generation and during iterative repair. We develop SecTDD, a controlled test-feedback scaffold that separates three factors: whether tests are shown upfront, whether failed executions trigger revision, and how failures are selected and represented. The evaluation uses behavior-partitioned visible and hidden tests and byte-identical initial candidates for repair comparisons. Across 2,705 trajectories, 31 task instances, three secure-code benchmarks, 16 CWE categories, and two model families, showing all visible tests upfront increases hidden functional-and-security joint success by 19.3 percentage points on average, but improves only seven of nine benchmark-model conditions and harms two. In shared-candidate comparisons, structured feedback repairs 80 initially unsuccessful candidates with no joint regressions; fixed raw feedback repairs 83 but causes three regressions. Structured and raw feedback are otherwise nearly indistinguishable head-to-head (six wins, six losses, and 453 ties). Candidates that pass all visible tests still fail hidden behavior families under every common regime. These results show that executable feedback can repair secure-code generation, but its benefits depend on the model, task, feedback entry point, and especially test coverage.

cs.SE↗

arXiv2026

Do Code Language Models Follow Tests? Paired Interventions on Program Behavior

Visible tests specify concrete program behavior, but an improvement in benchmark accuracy does not establish that a model follows the rule expressed by those tests. We study test utilization through matched prompting controls, paired semantic interventions, and test suites selected by fault detection. Our semantic intervention holds an underspecified description and its example inputs fixed while changing the correct outputs to express one of two valid rules. Evaluation on unseen inputs measures whether both generated programs follow their respective rules. Across five models and three runs of 120 paired instances from 20 specification families, mean switching rates range from 11.1\% to 65.8\%. Qwen3.8-27B has the highest point estimate, followed by Qwen3.6-27B at 60.6\%; their paired difference remains uncertain. Explicit descriptions elicit both rules from these two models on every instance, exposing a gap between implementation capability and adoption of test-specified rules. Correct expected outputs improve MBPP+ accuracy beyond inputs alone for all five models. On 180 tasks with fixed three-test suites, high-detection suites detect 30.3 percentage points more errors in a held-out pool dominated by reference mutants. The corresponding generation differences range from $-0.6$ to $+1.1$ points; all intervals include zero and remain compatible with some benefit. Paired interventions make test-specified rule changes measurable alongside implementation capability and benchmark correctness.

cs.SE↗

arXiv2026

A Learning-Rate-Gated Failure of GRPO in a Small Language and Vision-Language Model Web Agent: A Controlled Null and Its Mechanism

Reinforcement learning with verifiable rewards, and Group Relative Policy Optimization (GRPO) in particular, is now run routinely on a supervised checkpoint in the hope of producing a stronger agent. We ask whether it adds skill to a small language and vision-language model web agent at the 4B to 8B scale, or whether it mostly reshapes behavior the supervised model already has. Across a control grid of 18 runs that varies learning rate, KL weight, seed, initialization, and clipping, no configuration credibly improves the success rate of a strong supervised baseline on tasks the agent has largely mastered. On the text track, moderate to high learning rates make it credibly worse. The null holds under paired testing, 25 evaluation seeds, 6 training seeds, changes to the recipe, both text and Set-of-Marks screenshot observations, and scaling the backbone to 8B; the credible harm is a text-track finding and is only nominal under Set-of-Marks. To show that the null reflects the setting and not a broken pipeline, we run the identical harness, reward, and recipe on tasks whose reward is reachable by sampling, and there the success rate rises by 22 points with a paired interval that excludes zero. GRPO therefore helps only when there is headroom to climb, meaning the sampled policy already succeeds more often than the greedy one. We then explain the failure. A middle learning rate degrades the agent and a high one collapses it, and the two regimes form a double dissociation: grafting localizes the degrade regime to the attention and MLP blocks, while the collapse regime cannot be traced to any single group, and the embedding change that dominates the weight movement is causally inert. At 4B, effective rank in the late layers tracks capability in both directions; at 8B the two come apart. This coupling is specific to the smaller model, so we report it as scale-dependent.

cs.AI↗

arXiv2026

MAG: A Web-Agent Benchmark and Harness for Multimodal Action and Guide Generation

Digital Adoption Platforms (DAPs) are embedded overlays widely used on web systems to guide users through operations inside a page, helping them get started with unfamiliar interfaces quickly. Completing a real task, however, rarely means clicking a few buttons on a single page: it takes a sequence of actions that unfolds across changing page states. Prior studies have also treated automated web agent actions and guide text generation as two separate problems, and most of them feed models textual page representations such as the DOM or accessibility trees rather than the rendered screens that humans actually operate on. In this work we introduce MAG, the first benchmark that unifies task execution and guide writing into a single Multimodal Action and Guide task, with two grounding schemes over screenshots: Set-of-Mark element selection and raw pixel coordinates. We further build a complete harness for this compound task, covering annotation with LLM assistance and human verification, training, evaluation in live environments, and joint metrics for actions and guides. With this harness we evaluate frontier API models and open multimodal models, and report detailed analyses. Finally, we design a GRPO training method augmented with expert trajectories, which nearly doubles the success rate of a supervised 9B agent (from 6.9% to 13.2%) and improves guide quality at the same time. Even the strongest model completes fewer than 40% of the tasks, leaving ample room for future research.

cs.AI↗

arXiv2026

AutoPPA: Automated Circuit PPA Optimization via Contrastive Code-based Rule Library Learning

Performance, power, and area (PPA) optimization is a fundamental task in RTL design, requiring a precise understanding of circuit functionality and the relationship between circuit structures and PPA metrics. Recent studies attempt to automate this process using LLMs, but neither feedback-based nor knowledge-based methods are efficient enough, as they either design without any prior knowledge or rely heavily on human-summarized optimization rules. In this paper, we propose AutoPPA, a fully automated PPA optimization framework. The key idea is to automatically generate optimization rules that enhance the search for optimal solutions. To do this, AutoPPA employs an Explore-Evaluate-Induce ($E^2I$) workflow that contrasts and abstracts rules from diverse generated code pairs rather than manually defined prior knowledge, yielding better optimization patterns. To make the abstracted rules more generalizable, AutoPPA employs an adaptive multi-step search framework that adopts the most effective rules for a given circuit. Experiments show that AutoPPA outperforms both the manual optimization and the state-of-the-art methods SymRTLO and RTLRewriter.

cs.LG↗

arXiv2024

A Multilingual Dataset and Empirical Validation for the Mutual Reinforcement Effect in Information Extraction

The Mutual Reinforcement Effect (MRE) describes a phenomenon in information extraction where word-level and sentence-level tasks can mutually improve each other when jointly modeled. While prior work has reported MRE in Japanese, its generality across languages and task settings has not been empirically validated, largely due to the lack of multilingual MRE datasets. To address this limitation, we introduce the Multilingual MRE Mix dataset (MMM), which consists of 21 sub-datasets covering English, Japanese, and Chinese. We propose an LLM-assisted dataset translation and alignment framework that significantly reduces manual annotation effort while preserving the structural requirements of MRE tasks. Building on MMM, we adopt a unified input-output framework to train an open-domain information extraction model and conduct extensive empirical studies, including full fine-tuning ablations and the construction of knowledgeable verbalizers based on MRE-mix data. Experimental results show that 76 percent of the MMM sub-datasets consistently exhibit the Mutual Reinforcement Effect across languages. These findings provide systematic empirical validation of MRE in multilingual settings and demonstrate its practical value for information extraction.

cs.CL↗