Software Engineering
Rethinking SZZ Search Strategies: Lessons from Claude Code
Inase Kondo, Masanari Kondo, Daniel M. German et al. (+3 more)
Identifying bug-inducing commits (BICs) is important for studying software bugs and maintaining software, yet the accuracy of existing SZZ methods remains limited. Although various improvements have been proposed, many SZZ methods still rely on code tracing, which searches for BICs by tracing code changed in a bug-fixing commit (BFC) back to earlier commits. However, this approach may miss the actual BIC when the code responsible for introducing a bug differs from the code modified to fix it. To overcome this limitation, we investigate whether BIC identification can be improved by exploring search strategies that are not constrained to start with code tracing. We use Claude Code, a coding
agent that has demonstrated high BIC identification accuracy in prior research, to explore such strategies. Rather than prescribing a search process or providing predefined candidate commits, we allow Claude Code to independently investigate a Git repository. We evaluate its identification accuracy and search behavior on 79 Java cases from 70 repositories. In 79.7% of runs, Claude Code reviewed commit histories before inspecting individual code diffs. It used commit messages to select changes for closer inspection. With this approach, Claude Code achieves an F1 score of 0.771, significantly outperforming all ten evaluated SZZ baselines. Our failure analysis also reveals incorrect oracle labels and ambiguities in BIC definitions in the studied evaluation
dataset. After reconstructing the evaluation
dataset to address these issues, Claude Code achieves an F1 score of 0.938. A key lesson from Claude Code for improving SZZ search strategies is to use semantic information to find relevant commits and then examine their code changes, rather than starting with code tracing.
Read the full abstract ▾
All authors Inase Kondo, Masanari Kondo, Daniel M. German, Olivier Nourry, Yasutaka Kamei, Yoshiki Higo
Software Engineering
Re-executing Coding-Agent Evaluations: Unchanged Decisions and Unresolved Policy Risk
Tianyu Ding, Yaocheng Tong, Muzhi Yang et al. (+3 more)
Executable tests grade large
language model (LLM) coding-
agent patches for leaderboards, rewards and self-improvement. Two preregistered re-execution studies returned negative results. SWE-bench Pro v1's offline option rejected none of 59 accepted Go patches whose grading configuration changed. Their exploratory, unweighted upper confidence limit is 4.95% under candidate independence, leaving a 3% exposed-patch risk unresolved; the preregistered
estimator uses inverse sampling-probability weights. An extension was inconclusive. In a selected stratum, a reconstructed module cache built from the reference solution's dependencies rejected accepted alternatives from four models that passed with their own dependencies. Re-executing 1,929 selected
agent-version/task evaluations from the Darwin Gödel Machine's archive preserved best-
agent selection and system-variant ranking, with search history and scores of evaluations not rerun fixed. Exploratory host, image and adapted-grader comparisons also preserved them. Seven of 23 disagreements with archived verdicts did not recur on a second host; rebuilt images changed 16 three-run majority verdicts (0.83%) under four-CPU execution. We provide an evidence-to-claim summary, lessons for grader audits and an anonymous replication package. These results concern accepted patches and fixed-history decisions; general policy safety and adaptive-learning robustness require broader evaluations.
Read the full abstract ▾
All authors Tianyu Ding, Yaocheng Tong, Muzhi Yang, Fei Jiang, Lei Yang, Boya Yu
Numerical Analysis
Convergence of Least Squares Methods for PDEs on R^d with Shallow ReLU^k Networks
Tong Mao, Lei Shi and Hanfei Zhou
We establish inverse inequalities in Gaussian Sobolev norms for shallow $\mathrm{ReLU}^k$ trial spaces. The estimates identify the sharp regularity threshold and quantify the dependence on parameter separation and bias magnitude. Based on these estimates, we prove convergence of weighted least squares discretizations of linear PDEs on $\mathbb R^d$ using shallow networks with prescribed inner parameters and finitely many residual samples in an expanding ball. Under suitable stability and regularity assumptions, we obtain an error bound of order $h^{k+(d+1)/2-r}\delta_\pm^{-(S-r)}$ in the Gaussian Sobolev norm of order $S$, up to logarithmic factors, where $r$ is the PDE order, $h$ is the parameter fill distance, and $\delta_\pm$ is the antipodal separation. The convergence results cover deterministic and random sampling and extend to fixed bounded regions by restriction. We construct parameter sets with $\delta_\pm\asymp h$, yielding a convergence rate in terms of the network width that matches a lower bound up to logarithmic factors. Numerical experiments support the theoretical results and provide practical guidance on balancing accuracy and stability.
Read the full abstract ▾
Machine Learning
Learning to Extrapolate in Depth with Looped Transformers
Huitao Yang, Jianhao Huang, Zixuan Wang et al. (+1 more)
Looped
transformers reuse a single block across iterations, raising a natural question: how far can a block trained at one depth be safely extrapolated to greater depths? We study this question for all-pairs graph connectivity, where harder graphs require longer-range information propagation. We show that under exchangeability and symmetric positive initialization, population training at depth K converges to an update rule governed by a single effective parameter that balances graph propagation against fitting structure unresolved at training depth. This trade-off creates a finite extrapolation window: too few test-time loops provide insufficient propagation, while too many eventually create false connections. We derive explicit endpoints for this window and bound the graph hardness solvable beyond training as a function of training depth and hardness. In particular, a test depth chosen solely from the training distribution can guarantee recovery on substantially harder graphs, with a certified depth gain that grows exponentially as training depth outpaces training hardness. Experiments validate the predicted windows and show how compute budget and initialization affect the optimal training depth.
Read the full abstract ▾
All authors Huitao Yang, Jianhao Huang, Zixuan Wang, Baharan Mirzasoleiman
Cryptography and Security
SecReason: Vulnerability Detection and In-Stream Self-Repair for LLM Code Generation
Ruidong Han, Zhensu Sun, Chengyan Ma et al. (+4 more)
Large
language models (LLMs) may introduce security vulnerabilities into generated code, which can persist into production when verification focuses on functional correctness. Existing defenses act before, during, or after generation, but none inspects the code during generation. Security
prompts and retrieved security knowledge act before any code exists, constrained decoding limits
token choices but cannot guide repair, and post-hoc repair must regenerate the full response.
Reasoning LLMs draft code early in their streamed chain of thought, and in this pre-delivery window the code exists only inside the
reasoning stream. We present SecReason, an in-stream defense that monitors this window. Dual-track incremental scanning applies security rules, checking each statement as it is emitted and tracing dataflows across the accumulated code. When a security rule fires, SecReason interrupts generation, inserts an in-stream warning, and resumes decoding, so the model repairs the draft within the same
reasoning trace without regenerating the full response. On tasks where unassisted generation introduces vulnerabilities, \system raises the share of runs delivering secure and functionally correct code from below 15% to 72.8%–98.1% on \tool{CWEval} and \tool{SecCodeBench}. \system consumes fewer
tokens than post-hoc repair, and when security rules misfire on secure code, it limits the functional regressions from false warnings.
Read the full abstract ▾
All authors Ruidong Han, Zhensu Sun, Chengyan Ma, Yuqing Niu, Zhou Yang, Siqi Ma, David Lo
Multiagent Systems
Jevolution: A Framework for Studying Communication and Collective Dynamics in AI Agents
Xirui Huang, Nikhil Hooda and Utkarsh Gupta
Experiments with remote decision-making
agents depend on more than the policy: the world may change during inference, the simulator determines which actions are available, and births and immigration alter who can act. We present Jevolution, an instrumented spatial predator-prey framework that makes these dependencies explicit. Its reference implementation separates the evolving world, asynchronous request scheduling, controller adapters, and experiment records. The model combines local observations, energy and resource constraints, predefined signals, and inherited scalar traits. We describe these mechanisms using the ODD protocol and distinguish implemented controls from research questions requiring additional interventions. Free synthetic fixtures exercise scheduling, signaling, and inheritance against the pinned implementation; they validate specified software behavior rather than model intelligence or ecological realism. A completed communication case study illustrates the end-to-end workflow using Jev to control both species. Across 6 complete habitat-seed pairs, the mean signals-on minus signals-off difference in normalized rabbit abundance was -0.0095 (nominal 95% pair-bootstrap interval [-0.0772, 0.0602]). This small study does not resolve the direction of the signal-system effect. The contribution is an inspectable experimental system and its evidence boundaries, not a new policy-learning
algorithm or a demonstration of emergent
language, adaptive selection, or biological predictive validity.
Read the full abstract ▾
Machine Learning
KV4-RL: Unlocking Faster Asynchronous Rollouts for RLVR with INT4 KV Cache Quantization
Sihwan Park, Sung-Yub Kim, Doohyuk Jang et al. (+1 more)
Asynchronous rollout improves the efficiency of reinforcement learning with verifiable rewards (RLVR) by reducing under-utilization during long-tail generation. Sustained concurrency also concentrates context processing into fewer decode steps, increasing the KV workload per step. We characterize this KV concentration and find that KV cache quantization delivers substantially greater acceleration than weight-only and weight-activation quantization in our matched-workload comparisons. However, INT4 KV rollout can degrade learning even with
token-level truncated importance sampling (TIS). We propose KV4-RL, which combines calibration-free INT4 KV quantization with selective INT8 protection of
attention sinks and recent context. Protecting a bounded number of positions reduces sampler mismatch while retaining most of the speedup from INT4. Across 400 iterations of Qwen3-8B-Base GRPO training, KV4-RL achieves $1.80\times$ cumulative rollout speedup and $1.27\times$ cumulative full-iteration speedup over BF16 rollout, reaching $1.97\times$ rollout speedup over the final 50 iterations. Under a common BF16 evaluator, its final six-
benchmark mean accuracy is within 0.5 percentage points of BF16-rollout training for both Qwen3-4B-Base and Qwen3-8B-Base.
Read the full abstract ▾
All authors Sihwan Park, Sung-Yub Kim, Doohyuk Jang, Eunho Yang
Numerical Analysis
Symmetric two-level preconditioning for the method of reflections
Jongho Park
We develop and analyze a symmetric two-level preconditioner for the method of reflections for Laplace problems in perforated domains. Using constant boundary modes, we define a coarse correction through a symmetric coercive dual formulation. Combining this coarse correction with parallel reflection corrections gives a symmetric positive definite preconditioner for solving the dual system by the conjugate gradient method. Under a
geometric separation condition, we prove a condition number bound independent of the number and sizes of the holes and the diameter of the ambient domain. We also derive geometry-dependent convergence estimates for the one-level methods that explain the need for a coarse correction.
Read the full abstract ▾
Computer Vision
FreeCHROMA: Generative Chroma Keying from Unaligned Background References
Jiayi Wu, Tianfu Wang, Rui Zhao et al. (+6 more)
In film production, chroma keying composites an approved foreground performance into a new environment, but conventional workflows require coordinated background plates and dedicated harmonization. Recent generative methods often require pre-aligned backgrounds, focus on background-conditioned foreground relighting, or represent the environment only through an edited first frame. These restrictions limit background selection, scene composition, and camera motion while adding preparation or editing effort. We present FreeCHROMA, which adapts a pretrained
video diffusion model in a parameter-efficient manner for generative
video compositing from one to three unaligned background references. The model integrates the foreground into the referenced environment, preserving foreground identity, motion, and fine visual details while generating a spatiotemporally coherent background. Foreground-background harmonization occurs within the same generation process, without a separate relighting stage. Optional text instructions help disambiguate complex spatial relationships and camera behavior. To train the model, we construct pseudo-paired data from readily available real monocular
videos through foreground-background separation and augmentation with existing foundation models. The original
videos serve as training targets, while automated processing and quality verification enable scalable data construction. Across reference fidelity, foreground preservation, scene integration, harmonization, and overall
video quality, FreeCHROMA consistently outperforms recent compositing and conditional
video-generation baselines, with particularly clear gains under camera motion. FreeCHROMA relaxes the constraints of existing tools to enable end-to-end generative chroma keying from unaligned inputs, with exploratory experiments demonstrating its potential in robotics.
Read the full abstract ▾
All authors Jiayi Wu, Tianfu Wang, Rui Zhao, Florian Schiffers, Zhimin Chen, Cornelia Fermuller, Yezhou Yang, Christopher Metzler, Yiannis Aloimonos
Software Engineering
Taylor-Approximation-Based Repair of High Floating-Point Errors
Xin Yi, Liqian Chen, Hengbiao Yu et al. (+5 more)
Numerical libraries can still lose many bits of accuracy on localized ill-conditioned inputs, such as roots, poles, cancellation points, and branch boundaries. This paper presents NPTaylor, a Taylor-approximation-based framework for repairing localized high floating-point errors in numerical C routines. Given a high-error input, a localized repair domain, a high-precision oracle, and an error threshold, NPTaylor searches over Taylor degree, expansion center, segmentation, and floating-point evaluation strategy. It emits guarded C patches that use a generated Taylor evaluator inside the repair domain and fall back to the original routine outside it. Candidate patches are accepted only after validating the emitted C code on recorded local samples, guard endpoints, and the pre-repair peak input. The generated evaluator uses coefficient splitting and compensated Horner evaluation to reduce rounding error introduced by the patch itself. We evaluate NPTaylor on GSL
benchmark workloads. On 38 one-input functions, both NPTaylor and AutoRNP repair all 114 configurations across three accuracy thresholds. NPTaylor is 3.33x faster by
geometric-mean offline repair time and emits 0.162x as many C bytes. In the strictest setting, its median repair time is 3.74s versus 81.97s for AutoRNP. NPTaylor also repairs localized multi-input
benchmark cases beyond AutoRNP's implemented one-input workflow. These results show that Taylor-based guarded patches can provide compact, efficient local repairs, while the claims remain validation-relative rather than full-domain proofs.
Read the full abstract ▾
All authors Xin Yi, Liqian Chen, Hengbiao Yu, Shangwen Wang, Tao Tang, Chun Huang, Xiaoguang Mao, Ji Wang
Software Engineering
Specification-Based Testing of Large Language Models
Kausar Moshood, Jace Bolante, Roshan Aditya Murali et al. (+1 more)
Model cards, system cards, and safety reports increasingly document LLM safety behaviors, yet safety evaluations typically start from predefined
benchmarks rather than asking which documented claims those
benchmarks actually test. We introduce LEST (LLM Evaluation through Specification-driven Testing), a framework that treats documented safety claims as specifications for black-box testing. In LEST, each claim determines which
benchmark prompt tests it and whether a Refuse-to-Comply transition, where a model refuses a
prompt but complies with its mutated version, counts as evidence against it. LEST mutates these
prompts to search for counterexamples, manually validates each candidate, and traces validated counterexamples back to the claims they contradict. We evaluate LEST using the system cards of Claude Opus 4.8 and GPT-5.5 with 97 seed
prompts from SORRY-Bench across Mental Health and Self-Harm, Harmful and Violent Content, and
Fairness and Bias. Of 56 identified safety claims, 29 (51.8%) are
prompt-testable, but only 17 (58.6%) are exercised by an applicable
benchmark prompt. Both models refuse >95% of
benchmark prompts. Evaluating 1,836 mutated
prompts on both models reveals 312 candidate Refuse-to-Comply transitions flagged by automated response classifiers. However, human validation confirms only 19 (6.1%) as both intent-preserving and genuinely compliant, showing automated evaluation substantially overestimates behavioral failures. Tracing these 19 transitions back to the claims reveals counterexamples for 6 of 9 covered claims for which refusal is an applicable oracle. Our results show that
benchmark prompts may not be sufficient to validate all documented LLM safety behavior, and automated failure detection requires manual validation. LEST provides end-to-end traceability from natural-
language safety documentation to executable tests and human-validated counterexamples.
Read the full abstract ▾
All authors Kausar Moshood, Jace Bolante, Roshan Aditya Murali, Manish Motwani
Computation and Language
Evaluating Semantic Relation Knowledge through Bidirectional Relation Prediction from Gloss Pairs
Zhihan Cao, Adam Nohejl and Hitomi Yanaka
Semantic relations organise word senses and are fundamental to lexical semantics. In order to evaluate semantic relation knowledge of large
language models (LLMs), we propose a challenging task in which an LLM predicts the relation between two glosses (definitions of senses) presented in two different orders. The predictions for the two orders are evaluated for consistency with the
symmetry or asymmetry of semantic relations. Our task is designed for both monolingual and cross-lingual evaluation, allowing us to examine whether relation knowledge remains accessible when the same senses are verbalised through glosses in different
languages. We construct a
dataset of 3,069 sense pairs, with each sense verbalised in English, Greek, Romanian, Turkish, and Japanese. Experiments with 17 LLMs in zero-shot and five-shot settings reveal generally poor performance. In each setting, only eight LLMs achieve a macro-averaged F1 score significantly above a random baseline, and only one (zero-shot) and two (five-shot) significantly outperform a neural baseline. In particular, LLMs often fail to generate bidirectionally consistent predictions for hypernymy and to make correct predictions for holonymy in either direction. Our results suggest limitations in current LLMs' semantic relation knowledge, both in identifying relations and in respecting asymmetry.
Read the full abstract ▾
Machine Learning
Target-ESS Tempered Policy Optimization (TETPO): Smooth Variance Control via Bridge Importance Sampling
Shayan Mohajer Hamidi, Kayhan Behdin, Wenhui Zhu et al. (+4 more)
Asynchronous reinforcement-learning post-training of large
language models is computationally efficient but inherently off-policy: the learner updates on rollouts generated by a stale policy, while correcting this mismatch requires importance weights that can be extremely heavy-tailed. A small number of trajectories may then dominate an update, collapsing the effective sample size (ESS) and increasing the variance and instability of the resulting gradient estimates. Existing stabilizers apply fixed interventions regardless of the realized severity of weight concentration, either discarding selected samples or reweighting them without adapting the correction strength. We introduce Target–ESS Tempered Policy Optimization (TETPO), which replaces each importance weight $\rho$ by $\rho^\alpha$ for a data-adaptive exponent $\alpha\in[0,1]$: $\alpha=1$ preserves the original importance weights, whereas $\alpha=0$ assigns uniform coefficients. For each
prompt group, TETPO selects the largest $\alpha$ whose tempered weights satisfy a target ESS fraction $\kappa$, applying little tempering to healthy groups and stronger tempering when weight degeneracy is severe. At the population level, the tempered coefficients are exact importance weights for a
geometric bridge between the sampler and learner policies. The exponent is efficiently found by one-dimensional bisection, while the resulting weights satisfy deterministic bounds on normalized-weight dispersion and weighted-gradient norm that are independent of policy drift, together with a fixed-$\alpha$ bound on bridge-target discrepancy. Power tempering also introduces no explicit zero-weight mask. On mathematical-
reasoning benchmarks under high staleness, TETPO outperforms strong on- and off-policy baselines.
Read the full abstract ▾
All authors Shayan Mohajer Hamidi, Kayhan Behdin, Wenhui Zhu, Aida Rahmattalabi, Jincheng Cao, Jelena Markovic-Voronov, Alborz Geramifard
Computer Vision
SceneForesee: Learning Scene Evolution for Spatiotemporal Reasoning
Chaoyue Li, Shoudong Han, Haoyang Wu et al. (+4 more)
Large
multimodal models (LMMs) need to understand how entities move and interact as a scene develops. This requires following the same entities over time and relating their observed motion to subsequent changes. We formulate Scene
Evolution Understanding (SEU), a task for predicting and interpreting this change. Given observed
video, a model estimates entity histories and predicts one scene continuation through future trajectories and Events, accompanied by Visual Evidence from observed motion and a scene description. We construct SceneForesee, a
benchmark for evaluating entity continuity and scene
evolution reasoning through paired observed and future scenes with shared entity identities. It contains 144.57K temporal pairs, 1.05M entity correspondences, and 272.49K Events paired with observed evidence. We propose a spatiotemporal
reasoning framework, EvoSee, that learns future geometry and Event semantics through shared candidate states and joint assignment. It selects one continuation per entity from observation and uses the selected changes for entity refinement, retention, and scene representation. On SceneForesee, EvoSee outperforms Qwen3.5-9B by 10.45 points in Combined Point-F1 and 17.24 points in Event Global F1. On the 4D
reasoning benchmark Dyn-Bench, it improves question answering accuracy and grounding J&F by 4.8 and 3.58 points over their respective base systems. These results support scene
evolution as both a prediction target and a dynamic representation that brings predicted entity changes into spatiotemporal
reasoning.The project is available at https://github.com/mikubaka88/SceneForesee-Spatiotemporal-
Reasoning.
Read the full abstract ▾
All authors Chaoyue Li, Shoudong Han, Haoyang Wu, Boxue Yang, Sijia Chen, Yufan Chen, Ruping Zhang
Computation and Language
Neither True nor False: Do LLMs Represent Truth-Value Gaps in Plural Predication?
Duaa Nakshbandi, Zhiyu An, Yiping Li et al. (+2 more)
Large
Language Models (LLMs) are increasingly being used to summarize and verify claims in critical sources that inform consequential decisions. Such claims are full of plural definites. If three of five patients improved after taking drug A, the claim the patients improved after drug A is not true, since two did not, yet its negation, the patients didn't improve after drug A, is not true either, since three did. In formal semantics, this truth-value gap is known as the Homogeneity Gap: both the plural definite and its negation are neither true nor false when the property holds for only a fraction of the plural referent. A model that cannot represent this gap turns mixed evidence into a clean verdict, an error that can be costly in high-stakes use. We introduce HomogeneityNLI, a diagnostic
dataset of 1,000 minimal pair items crossing determiner, polarity, and group composition across ten logical conditions. Evaluating seven open-weight models, we uncover a pervasive Bivalence Bias: models assign plural definites their homogeneous truth conditions. In the zero-shot setting, no model recognizes the gap for both polarities in more than 15% of scenarios, and negated definites are judged False in 84% of cases. Explicit linguistic rules, chain-of-thought, and enumeration
prompts produce unstable, model-specific effects that often entrench the bias. Our findings indicate that current open-weight LLMs acquire the truth conditions of plural predication but not its trivalent logic, and cannot yet be trusted to summarize or verify claims whose evidence is mixed.
Read the full abstract ▾
All authors Duaa Nakshbandi, Zhiyu An, Yiping Li, Sachin Giri, Wan Du
Machine Learning
From Transfer Probes to Expert Grouping: Evidence from LoRA Post-Training
Xueyang Wu
A platform that post-trains one base model for many business lines often has more lines than experts it can maintain, so lines must share experts, yet lines seldom come with a taxonomy saying which should share. We ask whether transfer probes (train on one source, measure paired changes on all sources) can discover a grouping when the standard one is unknown. To test probes against a reference, we use seven public sources that do have a label tree (five mathematics subfields and two kinds of programming, standing in for business lines) and treat the tree's grouping as a label reference that the evaluator holds and the method does not. With four LoRA experts under fixed per-source exposure and per-expert budgets, we compare a purely probe-derived grouping and an uninformed uniform default (whose tied routing serves every line from one expert) against this reference. Trained once for one interval from a shared warm-up state and routed by a rule fixed by each allocation, neither reached the prespecified practical gain of 2 percentage points, and both had lower overall utility than the reference ($-2.43$ and $-2.54$ pp; 95% intervals below zero). In a post hoc comparison, the probe-derived grouping was indistinguishable from the uniform default ($+0.11$ pp, $[-1.25,+1.54]$). In fixed-budget LoRA post-training, a grouping built from initial-state single-source probes thus did not deliver the advantage predicted from the probes once carried to a later training state, a finite budget, and specified routing.
Read the full abstract ▾
Machine Learning
Design Choices for Multimodal Transformer Learning with Missing and Longitudinal Healthcare Data
Rita Cordeiro Mendes, Maria Manuel Pereira, Carlos Santiago et al. (+1 more)
Multimodal learning offers the potential to improve predictions by integrating complementary information from heterogeneous data sources. However,
multimodal datasets are frequently incomplete, raising important questions about how models should handle missing information. Although recent approaches increasingly rely on
Transformer-based architectures for
multimodal fusion, incomplete
multimodal data introduces challenges such as missing modalities and intra-modal missingness, which motivate key architectural design choices, such as tokenization granularity. In addition, many
datasets are longitudinal, with observations collected across multiple time points. The sequential nature of the
Transformer architectures provides a natural framework for modeling such data, but introduces additional considerations, such as how temporal information should be represented. In this study, we systematically investigate these design choices using three different cancer
datasets. We compare modality-level and feature-level tokenization and evaluate
attention masking and imputation as strategies for handling missing information, both naturally occurring in the
datasets and synthetically induced. We further investigate approaches for incorporating temporal information in our training process and how to model it. Experiments are conducted with unimodal and
multimodal configurations, as well as different levels of missingness for binary survival classification and multiple time encoding strategies for discrete-time survival prediction. Our results show that while
multimodal outperforms unimodal results, missing data heavily impacts predictions and thus effective design choices such as tokenization granularity, and intra-missing handling is essential for reliable prediction.
Read the full abstract ▾
All authors Rita Cordeiro Mendes, Maria Manuel Pereira, Carlos Santiago, Catarina Barata
Information Theory
DS and AMDS Symbol-Pair Codes from Three Families of Simple Root Cyclic Codes
Jiawei He, Zihan Zhang, Xiaoqiang Wang et al. (+1 more)
Symbol-pair distances of simple-root cyclic codes are important for evaluating error correction performance under overlapping pair read channels. In this paper, we construct three families of simple-root cyclic codes over finite fields of odd characteristic via generator
polynomials. For length \(2q+2\), the minimum symbol-pair distance is \(10\) for every odd
prime power \(q\ge 7\), established by excluding invalid support configurations. For length \(4q-4\), when \(q\equiv 3\pmod 4\) and finite field constraints hold, it is \(9\) or \(10\). For length \(2(q-1)\), reciprocal-
polynomial analysis shows it is \(11\) or \(12\). All obtained codes are MDS or AMDS symbol-pair codes.
Read the full abstract ▾
All authors Jiawei He, Zihan Zhang, Xiaoqiang Wang, Zhao Lin
Cryptography and Security
MemForm: Benchmarking Memory Formation Poisoning in LLM Agents
Haowen Pan, Pengyang Shao, Yunshan Ma et al. (+4 more)
Long-term
memory enables LLM
agents to learn from past interactions but exposes
memory formation to
adversarial influence. Existing studies primarily organize
memory poisoning by attack channels, corruption patterns, or lifecycle stages, leaving formation interfaces insufficiently characterized. We formulate
Memory Formation Poisoning as
adversarial manipulation of the interfaces through which persistent
agent memory is produced and committed, and introduce MemForm, a controlled diagnostic
benchmark covering five interfaces: Content, Evidence, Scope, Selection, and Path Poisoning. We introduce Selection and Path Poisoning as controlled intervention categories that isolate retention and consolidation order effects, respectively. Each category pairs clean and poisoned conditions with interface-specific controls. Evaluations across six LLMs and two response formats reveal broad susceptibility at all five interfaces under the evaluated
memory protocols and implementations. Crucially, authentic experiences with successful outcomes do not guarantee reliable behavior after
memory formation: changes to contextual support, retention, or consolidation order can induce undesirable downstream behavior. In particular, consolidation order can alter behavior even with identical retained experiences, depending on the
memory formation procedure. Additional analyses show that interface applicability depends on
memory architecture and that Path Poisoning susceptibility depends on the updater. The evaluated defenses provide incomplete mitigation that varies by interface. These findings motivate protecting both what is committed to persistent
memory and how
memory is formed from experiences. Code and data are available at https://github.com/opanhw/memform-code.
Read the full abstract ▾
All authors Haowen Pan, Pengyang Shao, Yunshan Ma, Yanzheng Jin, Naixin Zhai, Xiang Wang, Xun Yang
Artificial Intelligence
Frustratingly Easy Agentic RAG via Portable Skills: A Case Study in Customer Support
Istok Bako, Bonan Min, Tiffany Shao et al. (+2 more)
Enterprise workflow automation typically requires retrieving a complete and accurate set of relevant information from large operational document corpora (SOPs, policy documents) given a specific scenario or request. In customer support (CS), for example, human specialists must determine the correct sequence of resolution steps for each case, a task that demands precise grounding in policy documentation. Meeting this bar in production typically requires complex document chunking, indexing, and
retrieval pipelines, often layered with learned re-rankers, query rewriters, and bespoke agentic RAG infrastructure. We report a deployment case study of a simpler alternative: a portable skill consisting of a natural-
language instruction, lightweight tools (a
retrieval API, format-checking scripts), and a corpus enriched with an LLM-generated navigation layer, which is a structured "Wikipedia-style" index over the underlying documents. This agentic RAG approach is straightforward to implement (1-2 engineer days), portable across capable agentic harnesses (e.g., Claude Code), and performs strongly on the challenging task of CS resolution workflow generation, achieving 99.2% procedural equivalence to human-approved ground truth and 83.3% evidence sufficiency. It is also roughly an order of magnitude slower per case than our deployed production assistant (~90 s vs. ~8-9 s), so we claim no latency advantage. Our claim is scoped to that setting: a mature, well-curated corpus, a latency-tolerant workflow, and human review of every case. There, the skill did the work of a complex RAG stack, and maintenance became a matter of editing text and data rather than retraining models.
Read the full abstract ▾
All authors Istok Bako, Bonan Min, Tiffany Shao, Claire Cheng, Yashar Mehdad
Cryptography and Security
ByteMark: A Unified Byte-Level Watermark for Detection Across Language Models
Xiaopu Wang and Runze Li
As watermarking of LLM-generated text enters deployment, users increasingly need to check text whose source is unknown. Existing detectors read the watermark through a specific tokenizer or
embedding pipeline, and even if all providers adopted the same watermarking method, differences in these representations would leave their watermarks incompatible, and the text alone does not reveal which representation produced it. We propose ByteMark, a unified watermarking scheme that defines its signal on the UTF-8 bytes of published text. Models with different tokenizers embed this signal under one public specification and key, and a single detector verifies the text from the text and key alone. When the tokenizer or
embedding model of a baseline detector is replaced, its detection degrades sharply, whereas ByteMark, which uses neither, retains its detection rate; ByteMark also remains detectable when participating models continue or rewrite the text.
Read the full abstract ▾
Computation and Language
Scaling Laws for Multimodal Data Mixtures
Aditi Khandelwal, Ayush K. Tarun, Yixuan Xu et al. (+5 more)
Frontier AI systems are increasingly natively
multimodal, jointly pretrained on multiple modalities, such as text,
vision, and audio. However, the scientific understanding of the
multimodal data mixtures used to pretrain these systems — how much of each modality to mix, and at what potential interference cost to the others — is largely absent or gatekept. In this work, we derive data mixing scaling laws for three modalities: text,
vision, and audio.
Multimodal Large
Language Models (MLLMs) increasingly adopt Mixture-of-Experts (MoE) architectures, as MoEs scale efficiently and partially limit cross-modal interference. We therefore use MoEs to conduct 268 experiments ranging from 457M to 8.3B parameters, on up to 150 billion
tokens. Our work leads to multiple actionable insights into
multimodal data mixing for training MLLMs. First, compute optima are modality-specific: audio modality is model-heavy, favoring scaling parameters over
tokens, while text and
vision require balanced scaling of model size and data. Second, repeating
vision or audio data beyond 2x yields negligible benefits. Finally, cross-modal interactions are highly asymmetric:
vision strongly interferes with audio, whereas audio's interference with learning text and
vision is negligible. Overall, we provide a principled foundation for understanding the
multimodal data mixtures needed to train frontier MLLMs.
Read the full abstract ▾
All authors Aditi Khandelwal, Ayush K. Tarun, Yixuan Xu, Imanol Schlag, Golnoosh Farnadi, Siva Reddy, Luke Zettlemoyer, Antoine Bosselut
Software Engineering
HoldSpec: A Machine-Checked Model and Conformance Suite for the Payment Authorization Hold Lifecycle
Abhishek Sharma
When a merchant authorizes a card and captures the funds later, the money sits in a state that neither party fully controls: held on the cardholder's account, not yet taken, and due to lapse on a deadline set by the card network. What a merchant may do to that hold, capture part of it, capture again, void it, raise it, let it expire, is business logic that every payment service provider implements slightly differently and none of them specifies formally. We give the lifecycle a state machine in TLA+, parameterized by a provider capability profile, and check eight safety invariants and three liveness properties over 6 profiles, five of them built from Stripe's and Adyen's published documentation. From the same machine we generate a conformance suite that runs black-box against a provider API. Against 61 seeded defects that are distinguishishable from a correct implementation, the generated suite detects 100%, where random sequences with the same call budget reach 56% and a hand-written integration suite reaches 69%; random sequences given ten times the budget still reach only 67%. Running the same suite between two providers turns the comparison into a search, and it returns short executable witnesses for divergences the two documentation sets imply but neither states, including one that breaks the common assumption that a single adapter interface can sit over both, because closing a hold and releasing its remainder is a capture on one provider and a cancel on the other. We report what we could not do: no provider sandbox credentials were available, so every result here concerns documented behavior, and the suite that would test the providers themselves is part of what we release.
Read the full abstract ▾
Robotics
Red-Teaming of Vision-Language-Action Models via Quality Diversity Environment Generation
Shihan Zhao, Henry Chen, Ya-Chuan Hsu et al. (+7 more)
A long-standing goal in robotics is to develop generalist
robots that can perform tasks across a wide range of settings, flexibly specified with images and text.
Vision-
Language-Action (VLA) models offer a promising path toward this goal by training on large collections of
robot demonstrations. However, while VLAs perform well in-distribution, they often fail under minor test-time shifts, such as changes in object positions, lighting, textures, and camera poses. To address this, we propose Quality Diversity for Diverse Environment Generation (Q-DEG), a method for improving VLA robustness by generating
adversarial environments and fine-tuning the VLA on its own successful rollouts. Q-DEG uses Quality Diversity (QD) optimization to find a set of high-failure environments, while promoting diversity using policy
embeddings extracted from the VLA. These environments expose vulnerabilities that can be mitigated through self-imitation fine-tuning, thereby improving the VLA's robustness. In simulation, we conduct experiments across three representative VLA models, and our results indicate that Q-DEG improves robustness to out-of-distribution (OOD)
adversarial environments compared to the base VLA and VLAs fine-tuned using data collected from two red-teaming baselines. Furthermore, we demonstrate that improving VLA robustness through Q-DEG facilitates sim-to-real transfer. Our anonymous project website is at: https://qd-env.github.io/qdeg/.
Read the full abstract ▾
All authors Shihan Zhao, Henry Chen, Ya-Chuan Hsu, Minjune Hwang, Siddharth Srikanth, Freddie Liang, Akanksha Saran, Aaquib Tabrez, Stefanos Nikolaidis, Daniel Seita
Machine Learning
Coarse-Graining Recursive Expert Computation: Continuation-Relative Interfaces and Failure Modes
Shihua Yu, Yanzhi Wang and Tianchi Chen
Computational coarse-graining aims to replace a sequence of updates with a cheaper module while preserving task performance. We present a continuation-relative evaluation framework that assesses replacements through the computation that follows them, using downstream task quality and total execution cost as joint criteria. The framework distinguishes boundary representations, summaries of skipped computation, executed operations, and downstream loss. It makes interfaces and permitted deployment information explicit, combines fine-path references with directly trained controls using the same shortened architecture, and accounts for selection overhead. An exact loss decomposition separates replacement effects at a fixed downstream action from effects of changing that action. A finite construction shows how retained information can reduce the stipulated cost of zero-error prediction under fixed information and controller restrictions. Experiments in two frozen pretrained
language models show that representation fidelity and task loss can favor different fitting objectives. In a prespecified comparison on a 1.7-billion-parameter model, next-
token-loss training lowers in-distribution negative log-likelihood by 0.1901 nats per scored
token compared with reconstructing the skipped blocks' output, using the same optimizer and update count. This ranking reverses in all nine paired comparisons under distribution shift. In a recursive expert prototype, the jointly adapted candidate lowers task error relative to frozen-bank and router-only baselines, but trails directly trained controls, and the tested input-only selectors fail the joint quality-cost criteria. Together, the protocol and studies provide explicit criteria and diagnostics for distinguishing useful computational replacement from local approximation gains within specified interfaces and evaluation settings.
Read the full abstract ▾
Networking
RADIUS-Assisted Companion PSK Discovery: Enabling WPA3-SAE in Externally Authenticated Multi-PSK (ePSK / MPSK / DPSK / iPSK / PPSK) Deployments
Azif Abdul Salam Kolisam Beevi, Anil Kumar Reddy and Niraj Lochan Mahapatra
Large multi-dwelling unit (MDU), student-housing and hospitality networks rarely store resident pre-shared keys (PSKs) on the access point (AP). Instead, the per-resident keys of ePSK, MPSK, DPSK, iPSK or PPSK services are held in an external RADIUS server or cloud database synchronised with the property-management system. Our earlier work, Companion-BSSID-Assisted PSK Discovery (CAPD), brought WPA3-SAE to multi-PSK networks by learning the client's PSK on a WPA2-only companion BSSID and steering the client with IEEE 802.11v to a hidden WPA2/WPA3 primary BSSID of the same SSID. CAPD assumes that the AP can test every PSK itself. This paper removes that assumption. We propose RADIUS-Assisted Companion PSK Discovery (RA-CAPD). The AP forwards the ANonce, the raw EAPOL-Key message 2 (SNonce, MIC, RSNE), the SSID, the client MAC, the BSSID and the AP MAC to the external server in RADIUS vendor-specific attributes (VSAs). The server validates the MIC against all provisioned keys, identifies the matching PSK, and returns it encrypted under the RADIUS shared secret (or a per-AP key for cloud databases), together with the unit, room or user identity and the VLAN. The AP binds the client to this PSK and identity, synchronises the binding across all APs in the domain, and moves the client to the configured profile: 802.11v-capable clients via a BSS Transition Management request, and other clients by disconnection and reconnection. On that profile, SAE-capable clients complete WPA3-SAE and WPA2-only clients complete WPA2-PSK, both with the learned key and no further search, so the companion BSSID serves only for onboarding. We present the design, attribute dictionary,
algorithms, complexity and security properties, together with laboratory validation on commercial access points.
Read the full abstract ▾
Machine Learning
PotentialEP: Backprop-Free Training of CIFAR-Scale Generative Models via Equilibrium Propagation
Alex Gower
Generating an image with a
diffusion or flow-matching model typically involves integrating a velocity field for hundreds of sequential steps. That computation suits a GPU poorly and an analog neuromorphic substrate well, where one fast, low-power physical relaxation could replace the whole sequence. Two things are needed: a generative
algorithm whose computation is a relaxation, and a way to train it without backpropagation, whose global gradient transport is hard to realise in analog. Energy Matching supplies the first, sampling by gradient-descent relaxation on a time-independent potential - but obtaining the gradient that descent follows is itself a backward pass, once per integration step. We prove that a predictive coding network with a single linear injection term added to its energy relaxes to a state whose visible layer carries that gradient inherently, with an error that vanishes for small injection strengths. An Energy Matching model trained by backpropagation can therefore be loaded into this network unchanged and sampled by relaxation alone, matching the original model's FID to within 0.04 at CIFAR-10 and ImageNet-32 scale. The network can also be trained without backpropagation:
Equilibrium Propagation reproduces backpropagation's parameter updates to a cosine similarity of 0.9998, and training end to end with those updates reaches an FID of 3.64 on unconditional CIFAR-10 against 3.54 for backpropagation. To our knowledge this is the first CIFAR-10 generative model trained with
Equilibrium Propagation, and the first at competitive quality by any backpropagation-free rule. This quality does not require group normalisation or
attention: an architecture of only convolutions and pointwise nonlinearities, both native to an analog crossbar, reaches an FID of 3.51 when trained by backpropagation.
Read the full abstract ▾