Artificial Intelligence
Formal, Executable and Explainable Runtime Monitoring of Spoken Air Traffic Control Operational Procedures
Roberto Luvini, Giacomo Longo, Alessandro Armando et al. (+1 more)
Air traffic control procedures are executed through spoken exchanges between controllers and pilots. These interactions are essential to the safety of air transportation: failures in their execution can create severe operational hazards, as evidenced by past fatal accidents. Assessing whether an instruction has been followed requires relating what was said to the aircraft concerned, its state, and the obligations that pilots must meet. We present a runtime verification framework that monitors such procedures by checking controller-pilot exchanges, surveillance data, and onboard observations. The framework parses
radio communications into events linked to the entities they concern and merges them with surveillance and onboard observations into a time-stamped trace. The ICAO-derived obligations as formalized as temporal formulas with explicit time bounds and evaluated over execution traces. Every violation is reported along with the breached obligations and the observations that support the verdict. With real traffic, the complete pipeline reaches an F1 of 0.85 against blind human-annotated violations; in 1,495 synthetic situations derived from two public corpora, the monitor logic returns the expected verdict in every case. In two historical accidents reconstructed from official investigation reports, the monitor identifies the same procedural deviations documented by the investigators.
Read the full abstract ▾
All authors Roberto Luvini, Giacomo Longo, Alessandro Armando, Enrico Russo
Artificial Intelligence · Cross-listed from cs.CL
Query-Side Attacks on GNN-Based KGQA: Tracing Failures from Entity Linking to Answer Generation
Pankaj Kumar and Subhankar Mishra
GNN-based Knowledge Graph Question Answering (KGQA) pipelines process queries through four discrete stages: entity linking, subgraph
retrieval, GNN
reasoning, and answer generation. Standard robustness evaluations conflate stage-level failures into a single end-to-end metric, obscuring both the source of brittleness and the appropriate mitigation target. We ask which stage fails, and why, when the pipeline is subjected to
adversarial perturbations on the input question. We introduce a stage-isolation protocol with two answer-preserving
adversarial perturbations verified against the knowledge graph: Compositional Restructuring (CR) and Relation Synonym Swap (RS) target distinct stages while leaving entity seeds intact. Evaluated across ComplexWebQuestions and WebQSP, the results run counter to prevailing assumptions: the GNN
reasoning stage retains near-baseline accuracy when the subgraph is intact, while subgraph construction accounts for over 99% of the end-to-end collapse under CR, occurring even when the gold answer is present in 74% of retrieved subgraphs. This exposes a fundamental distinction between answer presence and answer reachability that end-to-end metrics cannot detect, and places the mitigation target firmly at the subgraph construction stage rather than the
reasoning model. Perturbed
datasets and evaluation infrastructure are released at https://anonymous.4open.science/r/atkgrag-E85C .
Read the full abstract ▾
Artificial Intelligence
Repair or Resample? Rethinking Failure Debugging in LLM Multi-Agent Systems
Zhongwen Luan, Xiaoyu Zhang, Ming Hu et al. (+3 more)
As large
language model (LLM)-based multi-
agent systems (MASs) are increasingly applied to long-horizon complex tasks, their reliability has emerged as the core bottleneck hindering their real-world deployment. Existing MAS debugging and repair methods typically rely on rerunning and resampling the entire execution trajectory. However, a fundamental question remains to be answered: do these methods causally repair MAS failures or merely stochastically repair by leveraging the randomness of LLM sampling? To evaluate the effectiveness of MAS repair methods, we introduce SymTrace, a controlled evaluation framework that records the MAS execution trajectory and establishes intervention anchors. During replay, it effectively reconstructs the execution before the anchor using recorded logs and only regenerates the downstream trajectory, thereby enabling the reliable reproduction of MAS failures. We further construct the
dataset SymFail, comprising 536 human-annotated failure trajectories with graph-linked locations, categories, and trace evidence. Based on these foundations, we conduct a large-scale empirical study across three mainstream MAS frameworks. Our findings reveal that existing unguided rerun methods are highly unreliable, exhibiting low failure reproduction and repair rates (only 67.97% and 6.90%, respectively). Building upon these findings, we further explore the effectiveness of a symptom-driven intervention method, which successfully repairs 20.15% of the failed cases (a 191.89% improvement to state-of-the-art repair methods). This study aims to provide actionable insights for MAS debugging and repair research, paving the way for the robust deployment of multi-
agent systems.
Read the full abstract ▾
All authors Zhongwen Luan, Xiaoyu Zhang, Ming Hu, Yue Yang, Jiongchi Yu, Xiaohong Chen
Artificial Intelligence
Choose Your Game Wisely: Measuring Game-Theoretic Structures in Real-World Vehicle Interactions
Yueyuan Li, Rongcheng Nie, Weijie Xi et al. (+4 more)
Game-theoretic models provide principled frameworks for modeling vehicle interactions, but their underlying temporal assumptions have not been systematically examined against real-world driving behavior. In particular, it remains unclear how simultaneous, sequential, and asymmetric interaction structures can be measured from vehicle trajectories. This paper develops a trajectory-based interaction measurement framework to identify interaction events and quantify behavioral change onset, temporal organization, post-onset response dynamics, and ordering stability. The framework uses behavioral deviations to verify candidate interactions. We evaluate the framework on six real-world trajectory
datasets, including INTERACTION, highD, inD, rounD, Waymo Open Motion, and nuPlan, covering diverse road geometries, traffic environments, and interaction types. The results show that concurrent and sequential behavioral changes both constitute substantial proportions of observed following, merging, and conflicting interactions. Among sequential interactions, stable ordering is more prevalent than alternating ordering, indicating that persistent asymmetric roles are a common interaction structure. Importantly, temporal precedence does not necessarily coincide with a measurable behavioral response, indicating that temporal ordering alone may not be sufficient to characterize behavioral dependence. These findings show that real-world interactions exhibit concurrent, sequential, and persistently ordered temporal structures. Different game-theoretic formulations are therefore better regarded as complementary modeling abstractions for different interaction regimes rather than as a universal structure governing all vehicle interactions.
Read the full abstract ▾
All authors Yueyuan Li, Rongcheng Nie, Weijie Xi, Mingyang Jiang, Songan Zhang, Hanyang Zhuang, Ming Yang
Artificial Intelligence · Cross-listed from cs.LG
Towards A Unified Information Bottleneck Framework for Time Series Explanations
Xu Zheng, Zichuan Liu, Zhuomin Chen et al. (+7 more)
Explaining deep learning models operating on time series data is crucial in various applications that require transparent and interpretable insights into model behavior. {Existing explanation methods generally fall into two categories: attribution-based explanations, which identify the temporal regions most responsible for a prediction, and counterfactual explanations, which reveal how an input should be modified to alter the model's decision.} {Despite valuable insights, these two fields are largely studied independently. This disconnect leaves attribution methods lacking causal validation, while counterfactual methods suffer from severe instability, producing
adversarial-like noise instead of meaningful explanations.} In this work, we revisit time-series explainability from an information-theoretic perspective and show that existing explainers are vulnerable to trivial solutions and distributional shifts. To address these limitations, we propose a unified objective function for explainable time series learning that bridges attribution and counterfactual
reasoning within a single framework. Building upon the Information Bottleneck principle, our formulation explicitly prevents trivial explanations and out-of-distribution counterfactuals. {Based on this objective function, we introduce {\modelname}, a novel explanation framework that learns a parametric transformation network to construct explanation-embedded instances, where preserved information yields attribution explanations and controlled information removal produces stable counterfactual explanations.} We evaluate {\modelname} on synthetic and real-world
benchmarks against state-of-the-art baselines. Extensive quantitative and qualitative results show that {\modelname} consistently outperforms competing methods, yielding faithful attributions and stable counterfactual explanations.
Read the full abstract ▾
All authors Xu Zheng, Zichuan Liu, Zhuomin Chen, Mayur Akewar, Janki Bhimani, Jason Liu, Mo Sha, Jingchao Ni, Wei Cheng, Dongsheng Luo
Artificial Intelligence · Cross-listed from cs.CE
Yi Zhou, Qipeng Wang, Yunqing Liu et al. (+3 more)
Multimodal protein language models (pLMs) learn joint
protein sequence-structure distributions, and their generation performance should also depend critically on inference-time sampling strategies. Yet prior work has focused more on model training than on how inference-time strategies behave. In this paper, we establish a three-stage investigation framework to empirically study the inference design space of
multimodal pLMs across three representative pLMs and four fundamental tasks. We evaluate vanilla sampling, task-specific classifier-free guidance, and reward-guided beam search on
multimodal pLMs, corresponding to controls over sampling distributions, per-step logits, and parallel trajectories. Throughout the complementary advancements centered on exploration-exploitation trade-off, we (1) reveal the suboptimality of default inference protocols and identify task-oriented sampling preferences; (2) observe substantial quantitative gains across tasks, consistently boosting the upper bound performance of
multimodal pLMs without updating model parameters; (3) derive conclusions about base models that differ from prior consensus.
Read the full abstract ▾
All authors Yi Zhou, Qipeng Wang, Yunqing Liu, Jun Xia, Qing Li, Wenqi Fan
Artificial Intelligence · Cross-listed from eess.AS
Why ML-based cough models do not generalize: a systematic cross-dataset evaluation for tuberculosis screening
Wensi Zhang, Tomas Teijeiro, Jérôme Thevenot et al. (+1 more)
Cough acoustics are promising for non-invasive tuberculosis (TB) screening, yet whether machine learning (ML) models capture disease-related acoustics or artifacts of data collection remains unresolved. We evaluated the cross-
dataset generalizability of classical ML and deep learning (DL) cough-based TB classifiers across three independent
datasets. Despite moderate within-
dataset performance (ROC-AUC up to $0.755 \pm 0.056$), both pipelines fail to generalize, with external performance frequently below 0.6, indicating a possible limitation of the data. We further observed audio representations are organized by recording device and
dataset rather than TB status, predicted TB probability tracks country-level prevalence in CODA, and device mismatch degrades transfer while device-diverse training improves it. Additionally, a clinical-variable baseline generalizes more consistently (ROC-AUC $0.655 - 0.711$), indicating acquisition-specific variability is a stronger driver of poor generalizability than population shift. High within-
dataset performance is not enough. External validation is essential before cough-based TB models are clinically ready.
Read the full abstract ▾
All authors Wensi Zhang, Tomas Teijeiro, Jérôme Thevenot, David Atienza
Artificial Intelligence · Cross-listed from cs.LG
VINCENT: Validated Interaction Network for Cross-drug Explanation of Therapeutics
Fan-Sheng Chuang, Xuchen Li, Yujing Bian et al. (+1 more)
Drug synergy prediction estimates whether two drugs produce a stronger joint effect than expected from their individual activities. For drug combination discovery, a single synergy score is often not enough: researchers also need to know which molecular regions jointly drive the prediction. We study motif-pair synergy explanation, which identifies pairs of chemically coherent regions, one from each drug, that jointly contribute to predicted synergy. Existing interpretable synergy models expose atom- or substructure-level signals, but their explanations are built into the predictor architecture, and none validates cross-drug region scores under repeated perturbations or feeds that evidence back to refine the explanation. A reliable motif-pair explanation should instead be chemically coherent, perturbation-stable, and aligned with predictor behavior. We introduce VINCENT (Validated Interaction Network for Cross-drug Explanation of Therapeutics), a post-training framework for a fixed interaction-aware synergy predictor. VINCENT extracts atom-pair evidence from
attention and gradient signals, groups atoms into chemically coherent motifs, and validates candidate motif pairs through repeated local perturbations. The validated evidence is fed back to refine motif assignments, yielding explanations that satisfy these three criteria. On a 25-pair literature-annotated subset, VINCENT achieves a mean motif recall of 0.826 (95% CI: 0.78-0.87), compared with 0.49-0.66 for baselines. Across all 71 test pairs, its validated interaction scores yield a TP/TN separation of 3.36. These results show that closed-loop perturbation validation recovers literature-supported molecular regions more accurately than existing alternatives while producing cross-drug interaction scores that better reflect predictor behavior.
Read the full abstract ▾
All authors Fan-Sheng Chuang, Xuchen Li, Yujing Bian, Kaixiong Zhou
Artificial Intelligence · Cross-listed from physics.ao-ph
Missing the Butterfly and Predicting the Past: Features or Bugs of Accurate AI Weather Models?
Pedram Hassanzadeh, Weidong Li, Y. Qiang Sun et al. (+4 more)
AI weather prediction (AIWP) models rival physics-based models, yet the sources of their unexpected forecast accuracy and the degree of their physical fidelity remain unclear. Here, across a hierarchy spanning observation-based reanalysis, a general circulation model, and the multi-scale Lorenz system, we show that AI models can be trained to skillfully predict the past (backcast), though backcasts are systematically less accurate than forecasts. However, skillful backcasting appears to violate the second law of thermodynamics, and all these
forecasting and backcasting models miss the butterfly effect. We trace the surprising forecast accuracy, missing butterfly, and skillful backcasting to a single cause: inevitable coarse-graining of training data, which removes fast, small scales and/or some variables. From the Lorenz system to official Pangu-Weather models, reducing coarse-graining makes AI predictions more physics-like (arrow of time and butterfly-like effects emerge), but forecast accuracy declines. Results offer an explanation for AIWP models' forecast skill: unlike physics-based models, they implicitly learn how fast, small scales affect large scales without inheriting their rapid error growth. Broader implications are that AI models' proliferation calls for revisiting predictability theories and long-term
climate emulation strategies, and backcasting offers a useful, new lens for such analyses.
Read the full abstract ▾
All authors Pedram Hassanzadeh, Weidong Li, Y. Qiang Sun, Jiangdi Wang, Alexander Wikner, Justin Finkel, Jonathan Q. Weare
Artificial Intelligence · Cross-listed from cs.CL
Skill Issue: Are Skills Language-Invariant in LLMs?
Bobby Cheng, Adam Gaber, Zhengyuan Liu et al. (+4 more)
Large
language models access knowledge inconsistently across
languages, but to what extent do they differ in their skill sets when interacting with different
languages? This work quantifies cross-lingual skill inconsistency orthogonally from knowledge and general
benchmark performance. We do this via
multilingual self-play: two instances of the same model compete in a text-based game, each interacting through a different
language interface. Since the model, opponent, rules, state space, and available actions remain fixed, this setting isolates the effect of
language on the model's realized behavior. We build a
multilingual extension to TextArena and evaluate three open-weight models across eight
languages and six games covering spatial
reasoning, imperfect information, resource allocation, and repeated interaction. We find that the same model can exhibit markedly different playing strength across
languages, with systematic variation in win–loss margins, invalid actions, and strategic tendencies. Detailed analyses reveal
language-specific failures in spatial
reasoning, card-conditioned decisions, and optimal move selection. In some settings, changing only the intermediate
reasoning language recovers much of the lost performance, suggesting that
language can affect different stages of the decision process. These results show that skill discrepancies are a measurable major roadblock in the development of truly
multilingual models. Better understanding these discrepancies can help us design models that perform more equitably across
languages.
Read the full abstract ▾
All authors Bobby Cheng, Adam Gaber, Zhengyuan Liu, Catherine Arnett, Omer Goldman, Cheston Tan, Leshem Choshen
Artificial Intelligence · Cross-listed from cs.CL
Unfolding Scientific Papers into Multi-Turn Generation Trajectories for Continued Pre-Training
Qiankai Xu, Qiguang Chen, Zixin Su et al. (+4 more)
A recent line of synthetic-data work reconstructs the thinking behind existing text rather than rewriting the text itself, but it operates on short web passages, recovers only local thoughts, and leaves the structure of whole documents untouched. Scientific papers are written to a clear and largely uniform structure and make a natural substrate for lifting this paradigm to the document level. We present a pipeline that unfolds each paper into a multi-turn generation trajectory in which a teacher model reconstructs the writing process of the whole paper: a writing request, a global plan, and pre-writing deliberation for each section. All section texts and the abstract are kept verbatim from the source paper. We apply the pipeline to 1.8M quality-filtered arXiv papers and obtain a 60B-
token corpus for continued pre-training (CPT) that is roughly twice the source text. The same reverse construction extends to instruction data and evaluation. We build an SFT
dataset of 200K samples using answers derived from paper text. We also use held-out papers to construct PAW-Bench, a
benchmark of 2,940 academic writing tasks with per-task rubrics and checklists. In controlled experiments, CPT on our corpus followed by SFT on public
datasets improves writing performance while preserving general
reasoning and improving long document reading. Replacing part of the writing SFT data with our synthetic instruction data further improves performance on PAW-Bench.
Read the full abstract ▾
All authors Qiankai Xu, Qiguang Chen, Zixin Su, Wenhao Huang, Yue Gao, Jiaheng Liu, Ge Zhang
Artificial Intelligence
LocalLSTC: A Long Short-Term Control Architecture for Locally Deployed GUI Agents
Weiming Li, Helen Paik and Yulei Sui
Modern GUI-
agent frameworks achieve strong desktop task performance with frontier API models, yet persistent control information often remains implicit in growing interaction trajectories. At each step, the planner reconstructs the active task stage, accumulated evidence, and runtime feedback before deciding the next action. This dependence becomes more pronounced under weaker local
reasoning backbones. Across four representative state-of-the-art frameworks, replacing GPT-5 with Qwen3.5-9B reduces average OSWorld SR-100 from 60.9% to 35.2%. Trajectory annotation further identifies at least one control failure in 94.7% of failed trajectories. To address this problem, we introduce LocalLSTC, a training-free architecture that organizes control by temporal scope, maintaining persistent cross-step state to guide short-term execution commitments. The framework comprises two complementary mechanisms. Long-to-Short Planning forms each commitment from persistent state, while Short-to-Long Control integrates execution outcomes back into that state for progress assessment, recovery, and termination. With Qwen3.8-27B, LocalLSTC reaches 73.7% SR-100 on OSWorld and 68.5% on WindowsAgentArena, achieving the strongest local OSWorld result and a new state of the art on WindowsAgentArena. Ablations further support contributions from both mechanisms. Together, these results show that temporal organization of control information can reduce cross-step control failures and complement backbone scaling in locally deployed GUI
agents.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CR
EVOMAL: Self-Poisoning in Self-Evolving Coding Agents
Xiaodong Wu, Yu Shi, Qi Li et al. (+5 more)
Self-evolving LLM coding
agents write their own tools by imitating retrieved skills from shared skill libraries. We identify a vulnerability in this loop: during authoring, a retrieved malicious skill can become the template for a new skill that preserves the payload. We call this self-poisoning: the
agent authors, stores, and runs the resulting malicious skill. We exploit it through EvoMal, an attack that amplifies self-poisoning by wrapping an interchangeable payload in a banner, a set of benign-looking structural elements that induces an imitating
agent to reproduce the enclosed code. The attacker plants malicious skills in the library without invoking them. The
agent then authors and executes new skills carrying the harmful code. Each authored copy can re-enter the library and be imitated again, forming a self-propagating worm that persists after the planted skills are removed. We define the
agent self-poisoning rate (ASPR) as the fraction of tasks that add a newly authored malicious skill to the library. Across six models on 153 tool-relevant SWE-bench Verified tasks, ASPR ranges from 20.3% to 41.8%, and the poisoned libraries hold 4.9 to 9.0 times as many malicious skills as were planted. The vulnerability also appears without a banner: DeepSeek-V4-Pro reaches 11.1% ASPR with the payload alone. Tailoring the planted skill descriptions to one task family raises ASPR to 86.7%. After the planted skills are removed, Qwen3 retains a round-5 ASPR of 68% because
agent-authored copies remain. These copies evade existing defenses, which focus on attacker-submitted names, code, and signatures. We propose counter-
prompt, a defense that discourages banner-style copying and reduces EvoMal's ASPR to at most 6.7% with no significant task-completion loss.
Read the full abstract ▾
All authors Xiaodong Wu, Yu Shi, Qi Li, Zhimin Zhao, Xiangman Li, Bram Adams, Ahmed E. Hassan, Jianbing Ni
Artificial Intelligence
ToST: A Tree-of-Thought Socratic Teaching Framework for Multi-Path Guidance and Parallel Thinking
Feng Ling and Heng Yu
Large
Language Models (LLMs) exhibit strong problem-solving abilities, positioning them as promising
agents for Socratic teaching to guide students through step-by-step heuristic questioning. However, existing approaches typically adopt a one-problem-one-solution paradigm, restricting the teaching guidance to a single linear
reasoning path. This design limits instructional flexibility, weakens error recovery, and restricts students' ability to engage in parallel thinking to explore multiple valid solutions. To overcome these, we propose ToST, a Tree-of-Thought Socratic Teaching framework that explicitly supports multi-path guidance under a one-problem-multiple-solutions paradigm. ToST employs Parallel Sowing, a parallel-thinking-oriented questioning strategy to encourage students to approach problems from diverse perspectives, and a Multi-Path Adaptive Guidance mechanism to provide more robust and non-linear instructions across alternative solution trajectories. Concurrently, to fill the void in systematically evaluating such non-linear instructional capabilities, we advance the task of multi-path Socratic guidance by establishing MPSG-Bench, a comprehensive
benchmark that includes a
dataset of 31K multi-path teaching dialogues and a five-dimensional evaluation framework grounded in the SOLO (Structure of Observed Learning Outcomes) theory to assess parallel-thinking guidance. Experimental results demonstrate that ToST significantly enhances guidance success rates while empowering students to navigate and explore multiple solution paths more effectively under both automatic and human metrics.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
MoganBert-TR: A Turkish Encoder Foundation Model Trained from Scratch with a CLM-to-MLM Curriculum
Furkan Yilmaz, Habibe Aleyna Tasdemir and Muhammed Faruk Gozay
Turkish encoder models have adopted modern architectures while leaving the pretraining objective fixed at masked
language modelling. This paper introduces MoganBert-TR, a 149M-parameter Turkish encoder foundation model trained from scratch on a
language-specifically filtered corpus, together with an
embedding model derived from it (MoganBert-Embed). MoganBert-TR is trained over 237.3B
tokens with a two-stage CLM-to-MLM curriculum: causal
language modelling first, masked
language modelling for the remainder, with the transition made inside the stable phase of a WSD schedule. In a controlled ablation under an equal step budget, this design outperforms pure MLM by 2.7-3.7x on Turkish MS MARCO
retrieval; the measured mechanism is
embedding geometry, where a single direction absorbs 28.1% of the variance under pure MLM against 11.9% under the curriculum. Long-context extension and learning-rate decay are then split into two branches after a shared prefix: running the final portion of decay at 1024 context improves the TrGLUE average by 0.49 +/- 0.26 points across five paired seeds (p = 0.013) and beats a model-soup alternative by 0.75 points at ~4.3% additional cost. MoganBert-TR attains 78.41 on TrGLUE, the best among the Turkish ModernBERT models compared, and 77.73 on TabiBench, where it leads two of the eight categories with the largest margin on code
retrieval (+3.62 points over TabiBERT). MoganBert-Embed, produced through teacher
distillation and multi-signal contrastive fine-tuning, ranks first among student models on the MTEB(Turkish) overall average with 68.30 and reaches 99.5% of its 7.57B-parameter teacher's score with a 51x smaller backbone. The accompanying 50,048-
token tokenizer outperforms all compared Turkish tokenizers on compression and fertility across two independent test sets. Weights, tokenizer,
embedding model and evaluation code: https://huggingface.co/moganai
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
Beam Search, Self-Consistency, and the Limits of Inference-Time Scaling for Grammar-Constrained Text-to-SQL in Small Language Models
Ty Chermsirivatana and John MacCormick
One common trade-off in the use of large
language models involves reducing the size of the model while increasing the amount of computation at inference time, for example by using a wider beam search. In this paper, we examine the constrained case of this "model size vs. inference compute" trade-off, in which the model outputs are constrained by a strict grammar at inference time. Our results demonstrate that the constrained trade-off behaves differently from the unconstrained trade-off. We investigate the task of converting a prose query into an equivalent SQL query (text-to-SQL). Performance is evaluated on the Spider text-to-SQL
benchmark, using the Qwen2.5-Instruct model family ranging in size from 0.5B to 7B parameters, all at 4-bit precision. We experiment with two approaches to varying inference compute: (i) beam search with a variable number of beams; and (ii) sample+vote, i.e., sampling several constrained outputs and then voting on their execution results, where the number of samples is varied. On the 1034-example development set, we find that: (a) both beam search and sample+vote improve accuracy, especially on smaller model sizes; (b) the "model size vs.\ inference compute" trade-off is not advantageous in this experiment, because moving to a larger model size typically results in higher accuracy than increasing inference compute on the same model size; (c) beam search outperforms sample+vote at a matched inference budget. This latter result is of particular interest since it contrasts with the findings of the unconstrained trade-off.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
TailSFT: Filtered Fine-Tuning Improves Post-Training Performance
Sadhika Malladi, Samy Jelassi, Dylan Foster et al. (+2 more)
Reinforcement learning post-training drives
reasoning and agentic capabilities in modern AI systems, yet a growing body of work shows that it is most effective when used to fine-tune an already capable base model. We question whether existing pipelines yield models that are most suitable for reinforcement learning. Building on prior work highlighting the role of coverage and pass@K as predictors of post-RL performance, we design a simple modification to supervised fine-tuning, TailSFT, which filters out already fit sequences during training, thereby focusing learning on under-modeled regions, or the tail, of the data distribution. We justify and validate the design choices in TailSFT, particularly the specific filtering criteria, through a combination of controlled experiments and theoretical analysis. On OLMo-3 7B, TailSFT often improves pass@16 performance on math and coding evaluations, with gains up to 17% absolute, while incurring minimal computational overhead. These higher-coverage checkpoints consistently translate to up to 4% absolute pass@1 gains in subsequent GRPO runs, demonstrating that TailSFT checkpoints serve as better initializations for RL. We further introduce a lightweight diagnostic for identifying settings where TailSFT is most likely to help. More broadly, our results motivate a principled, stage-aware approach to model development, in which intermediate checkpoints are judged by how effectively they support subsequent training.
Read the full abstract ▾
All authors Sadhika Malladi, Samy Jelassi, Dylan Foster, Jordan T. Ash, Akshay Krishnamurthy
Artificial Intelligence · Cross-listed from cs.CR
MeMark: Membrane-Space Watermarking for Spiking Neural Networks
Roberto Riaño, Gorka Abad, Stjepan Picek et al. (+1 more)
Spiking Neural Networks (SNNs) are increasingly distributed as pretrained checkpoints and reused as backbones for new tasks. However, current SNN watermarks are mainly verified against the model output. Thus, a user who replaces the output head can keep most of the original network while removing the evidence used for verification. We present MeMark, a watermark designed for the checkpoint-reuse setting. Instead of storing the watermark in the output head, MeMark embeds a multi-bit identifier in the internal membrane state of selected Leaky Integrate-and-Fire (LIF)
neurons. A secret input drives each selected
neuron to the chosen side of its own firing threshold, and the same threshold is later used to recover the secret bit, so the verifier does not need a learned decoder. We evaluate MeMark across recurrent, convolutional, residual, and
transformer SNNs. On a 215.4M-parameter SpikeGPT checkpoint, all 20 independent 64-bit keys pass the fixed 51/64 verification rule, while none of the $30\,000$ fresh random keys pass when tested against all 20 protected checkpoints and the clean model. All 20 genuine keys also remain above the threshold after fine-tuning, 90%
pruning, int8 quantization, and output-head replacement. Under our stated threat model, adaptive attacks can weaken the watermark but do not remove the ownership evidence in the settings we test. Additionally, we study false ownership claims, key-aware and key-agnostic removal, partial key disclosure, rollback, and extraction into a student. The results show that MeMark can provide evidence of checkpoint derivatives, while being resistant to the adversary's attacks and complete head replacement.
Read the full abstract ▾
All authors Roberto Riaño, Gorka Abad, Stjepan Picek, Aitor Urbieta
Artificial Intelligence · Cross-listed from cs.CR
Pointing the Way, Hiding the Destination: Practical Private Dense Retrieval at Scale
Peichun Hua, Danyang Chen, Junan Zhang et al. (+5 more)
Hosted
retrieval-augmented generation (RAG) and semantic search allow users to query valuable provider-held corpora, raising two competing demands: to hide each query and chosen result, yet reveal only the documents that the user is authorized to receive. Existing cryptographic approaches either make this costly by processing the entire corpus for every query, or sacrifice quality for efficiency by scanning a few clusters. We repurpose learned deep hashing as a private filter: a randomized binary code points the provider to a short candidate list, while encrypted reranking and oblivious key transfer protect the precise query and final selection. This shortlist short-
circuits full-corpus cryptographic search without sacrificing
retrieval quality: with 200-500 candidates, it closely matches full-corpus
retrieval across five zero-shot corpora spanning 25K to 5.4M documents. On the full 2.68M-passage NQ corpus over a 10-Gbps link, our protocol only adds 0.73 seconds, or 10 percent, to a 128-
token Qwen3-32B RAG pipeline. The released code satisfies directional metric differential
privacy (DP) and substantially reduces
embedding-inversion and property-inference leakage, demonstrating that a carefully learned shortlist can make private dense
retrieval both accurate and practical.
Read the full abstract ▾
All authors Peichun Hua, Danyang Chen, Junan Zhang, Haifeng Sun, Jingyu Wang, Diwen Xue, Mingyu Li, Yunming Xiao
Artificial Intelligence · Cross-listed from cs.LG
It's a matter of timescale: non-linear utility in successor features and multi-objective planning and learning
Liam P.H. Mertens, Lucas N. Alegre, Florent Delgrange et al. (+3 more)
Time is of the essence when dealing with multiple reward signals and non-linear utility. In this paper we argue that the current main approaches in multi-objective RL (SER and ESR), and successor features, are insufficient. While each approach deals with non-linear effects on user utility on different timescales, none of them take into account that different effects happening on different timescales can happen within the same decision problem. We motivate that this can indeed be the case by an example, both intuitively and numerically, leading to a new perspective, and a significant and non-trivial gap in the literature.
Read the full abstract ▾
All authors Liam P.H. Mertens, Lucas N. Alegre, Florent Delgrange, Diederik M. Roijers, Ann Nowé, Peter Vamplew
Artificial Intelligence · Cross-listed from cs.CL
When RAG Fails to Equalize: Geo-bias in Factual Question Answering over Public Companies
Abhinav Havaldar and Enrico Santus
Retrieval-augmented generation (RAG) is widely assumed to mitigate factual errors in large
language models (LLMs), but it remains unclear whether
retrieval uniformly compensates for missing knowledge. We study this question in a controlled factual QA setting over public companies, constructing a
benchmark of approximately 2,000 firms across global equity indices. We evaluate six LLMs on four atomic attributes under four conditions: no-context, perfect context, misleading context, and distraction context. We find strong geographic disparities in no-context accuracy, indicating uneven parametric knowledge. While perfect context improves performance, it does not eliminate these gaps: gains are correlated with baseline accuracy, suggesting
retrieval effectiveness is coupled to internal representations. Under misleading context, models frequently copy incorrect information. Larger models improve overall performance but do not remove these structural effects. These results challenge the view of RAG as a universal corrective and highlight the interaction between model knowledge, context quality, and entity representation.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Difficulty-Aware Sample Allocation for Adaptive Data Augmentation in Semantic Segmentation
Olasimbo Ayodeji Arigbabu and Abimbola Ismail Arigbabu
Data augmentation is a standard component of modern semantic
segmentation pipelines, but most augmentation techniques allocate transformations uniformly across training samples or adapt to a single difficulty signal such as loss. This ignores the fact that
segmentation difficulty is multi-factorial, since ambiguous predictions, persistent optimization errors, rare classes, and complex object boundaries can each make a sample informative in different ways. This paper introduces Difficulty-Aware Sample Allocation (DASA), an architecture-agnostic framework that assigns stronger augmentation to samples estimated to be more difficult. DASA combines prediction ambiguity, training loss, class rarity, and boundary complexity into a normalized difficulty score, then maps that score to sample-specific augmentation strength during iterative training. Experiments on Oxford-IIIT Pet and binary Pascal VOC
segmentation with U-Net, DeepLabV3, and SegFormer-B0 show that DASA improves over standard training and is competitive with or stronger than single-signal adaptive baselines. On Oxford-IIIT Pet, DASA improves DeepLabV3 from 0.633 to 0.740 mIoU. On binary Pascal VOC, DASA obtains the best foreground IoU for all three evaluated architectures. These results attest to the value of multi-factor difficulty estimation as a practical mechanism for directing augmentation where it is most useful.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Unsupervised Anatomical Feature Learning via Diffusion Models: Enhanced Medical Image Segmentation with Denoising Diffusion Probabilistic Models
Akshat G, Divyansh Gupta, Shaleen Bhatnagar et al. (+2 more)
Acquiring pixel-level annotations for medical image
segmentation is a severe bottleneck. Traditional U-Net architectures, while effective, learn local texture patterns and lack awareness of global anatomical structures, leading to boundary delineation failures in low-data regimes. This research paper proposes utilizing unsupervised Denoising
Diffusion Probabilistic Models (DDPMs) to extract anatomical features. We train a DDPM on 21 unlabeled abdominal CT scans to learn structural representations, transferring the encoder weights to a downstream
segmentation task evaluated on the BTCV multi-organ
dataset.
Diffusion pretraining significantly improved liver
segmentation: Dice increased from $0.75\pm0.36$ to $0.93\pm0.16$ ($p < 5.33\times10^{-26}$, 0.529 Cohen's d), Average Surface Distance (ASD) decreased by 66%, and 95th-percentile Hausdorff Distance (HD95) reduced by 45%. For kidney
segmentation, Dice improved from $0.90\pm0.19$ to $0.95\pm0.10$ ($p < 4.01\times10^{-11}$). Multi-organ pooled performance showed a 68% variance reduction and a 74% improvement in boundary precision (Dice $0.95\pm0.07$). Crucially, frozen encoder models retained > 80% of fine-tuned performance without exposure to
segmentation labels, proving the existence of learned anatomical priors. In low-data scenarios,
diffusion-pretrained models maintained robust performance with only 50% (Dice: 0.92 liver, 0.94 kidney), 25%, and even 10% (Dice: 0.89 liver, 0.71 kidney) of labeled data. Using unlabeled images for
diffusion-based pretraining successfully embeds robust anatomical features prior to human supervision, transforming U-Nets into anatomy-aware systems.
Read the full abstract ▾
All authors Akshat G, Divyansh Gupta, Shaleen Bhatnagar, Shilpa Ankalaki, Tusar Kanti Mishra
Artificial Intelligence · Cross-listed from cs.CL
Learning New Facts with QLoRA: An Acquisition-Retention Frontier
Estelle Zheng, Sébastien Warichet, Emmanuel Helbert et al. (+1 more)
Parameter-efficient fine-tuning is often assumed to preserve pretrained capabilities because it updates only a small number of parameters. We show that this assumption depends strongly on adapter capacity. We study factual acquisition in a controlled OpenStreetMap-derived
benchmark where Qwen3-4B must acquire anonymized geographic associations while retaining unrelated capabilities. Comparing full fine-tuning (FFT) with quantized low-rank adaptation (QLoRA) at ranks 8, 16, 32, and 64, we find that rank induces a clear acquisition–retention frontier. Low-rank QLoRA preserves out-of-domain (OOD) performance but acquires fewer facts, whereas higher ranks improve same-fact paraphrase generalization at an increasing cost in performance on unrelated
benchmarks. FFT behaves as a conservative baseline: it retains general capabilities well, but does not reach the highest factual-acquisition regime. Distributional, weight-space, and spectral diagnostics mirror this behavioral trade-off, with higher-rank QLoRA moving farther from the pretrained model. A separate math adaptation experiment shows a weaker frontier, suggesting that the effect is most pronounced when adaptation must install new factual associations rather than reinforce skills already supported by pretraining. Code and data are available at https://github.com/zhngstl/new_facts_forgetting.
Read the full abstract ▾
All authors Estelle Zheng, Sébastien Warichet, Emmanuel Helbert, Christophe Cerisara
Artificial Intelligence · Cross-listed from cs.CR
AI Slop and Hallucinations in Vulnerability Assessment: A Survey on Reasoning Failures and Trustworthy Mitigation
Junchen Ding, Jialiang Dong, Yichen Zhu et al. (+5 more)
The integration of Large
Language Models (LLMs) into cybersecurity has transformed vulnerability assessment, but it has also produced a trustworthiness crisis driven by the unchecked proliferation of "AI slop." These artifacts, hallucinated vulnerabilities, plausible but incorrect patches, and semantically repackaged bug reports, impose a cognitive burden on human triage pipelines that mirrors a denial-of-service attack. This paper surveys the empirical evidence, identifies a unifying mechanism, and traces a path toward trustworthy triage. We formalize a taxonomy of AI slop grounded in a structured literature review and dissect its root cause: the gap between the causal deductive
reasoning of security experts and the autoregressive probabilistic generation of current LLMs. We operationalize this gap through a measurable proxy, the Deductive Coverage Score, and show that chain-of-thought prompting and tool-using
agents narrow but do not close it. We review mitigation strategies and argue that passive detection and watermarking target provenance rather than correctness, facing fundamental
entropy constraints. We instead advocate for active neuro-symbolic verification, mapping each pipeline component to prior systems with documented limits on security inputs. Finally, we specify two evaluation instruments, CVE-Bench and Slop-Score, including
dataset construction, metric formulas, and anti-gaming provisions. By shifting evaluation from linguistic fluency to mathematical verifiability, this survey provides a roadmap for securing emerging AI-driven triage systems.
Read the full abstract ▾
All authors Junchen Ding, Jialiang Dong, Yichen Zhu, Yi Liu, Gelei Deng, Willy Susilo, Siqi Ma, Yuekang Li
Artificial Intelligence · Cross-listed from cs.IR
Data Citation for Large Language Models: A Challenge
Gianmaria Silvello
Large
language models increasingly mediate access to information, and a growing body of work asks whether they cite the sources behind their outputs. That work treats citation as a verification device and applies it to textual documents. Scholarly citation serves two further functions, credit and provenance, and it applies to data as much as to text. This paper argues that data citation for large
language models is an open challenge, distinct from document-level citation grounding and harder to solve. We ask how such models should cite data so that outputs stay verifiable, provenance stays traceable, and credit reaches data creators and curators. We set out three research directions. Training data attribution has to turn influence estimates into references for corpora absorbed into model parameters. Data citation at inference time has to identify
datasets, subsets, and query results at the right granularity and fixity. Citing knowledge graph facts has to define what a reference to a single triple denotes and how credit propagates along provenance. Progress on all three depends on joint work across the database, information
retrieval, knowledge representation, and artificial intelligence communities.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.SE
From General Agents to RCA Experts: A Self-Evolving Harness for Root Cause Analysis
Haiyu Huang, Jiewei Lyu, Zhihan Jiang et al. (+5 more)
Automated root cause analysis (RCA) with large
language models (LLMs) has drawn growing
attention. Today, SREs typically automate RCA with LLMs in one of two ways: directly using a general-purpose
agent (e.g., Codex or Claude Code) for diagnosis, or building a specialized RCA
agent from scratch. As mainstream general
agents grow more capable and iterate quickly, our quantitative study finds that the former now often surpasses the latter. Its accuracy, however, still falls short of production needs, and this gap stems mainly from the external adaptation layer outside the
agent's general capabilities, namely the harness. We therefore argue that LLM-based RCA should focus on this external harness, reusing the strong general capabilities of a modern
agent rather than rebuilding an
agent from scratch. A key capability of such a harness is to self-evolve, accumulating system-specific experience from past diagnoses so that it gets better the more it is used. We introduce OpsHarness, a self-evolving RCA harness that turns diagnosis experience into reusable expertise. Its data plane combines layered operational knowledge with an idea-card tool library, while its control plane coordinates setup, diagnosis,
evolution, and verification. During
evolution, OpsHarness contrasts successful and failed trajectories, converts their evidence into atomic proposals, and admits updates only through a dual-gate verification process designed to prevent overfitting and regression. Across two public
benchmarks and an industrial deployment, OpsHarness achieves 59.0% top-1 accuracy, improving over a bare general
agent by 63.4% and over baseline RCA
agents by 4.02$\times$.
Read the full abstract ▾
All authors Haiyu Huang, Jiewei Lyu, Zhihan Jiang, Jinyang Liu, Xiao He, Tieying Zhang, Wu Xiang, Michael R. Lyu
Artificial Intelligence · Cross-listed from cs.CL
Think-Probe-Respond: Improving Large Language Models as Judges of Research Idea Novelty
Tim Schopf, Tobias Schreieder and Akiko Aizawa
Automated novelty judgment can accelerate scientific discovery by enabling efficient evaluation, refinement, and comparison of research ideas. While large
language models are increasingly adopted for this task, we investigate a previously overlooked limitation in their judgment capabilities: despite generating
reasoning rationales that closely mirror those of human experts, their final novelty judgments often diverge substantially. We demonstrate that this miscalibration stems from a systematic bias towards judging ideas as "medium novel". To mitigate this, we propose Think-Probe-Respond (TPR), a lightweight approach that probes latent novelty judgments from hidden states during the
reasoning phase and uses the probed judgments to condition the final response. Across strong baselines, TPR improves novelty judgment performance by 22.30% and successfully mitigates the prevalent "medium novelty" bias.
Read the full abstract ▾
Artificial Intelligence
Narcissus: Program Synthesis Using Context-Aware LLM Approximations
Tilman Hinnerichs, Sebastijan Dumancic and Neil Yorke-Smith
Large
language models (LLMs) excel at programming, but not when the task fixes the target
language: prompted with a grammar rare in their training data, their programs usually break the grammar or fail the given specification. Enumerative synthesizers search the space of syntactically correct programs systematically guided by LLMs; the state of the art guides them by approximating LLM proposals into rule frequencies, which loses where each construct belongs and prunes every rule the proposals miss, exactly when the proposals are wrong. We present Narcissus, a synthesizer that keeps the proposals as syntax trees and scores each expansion of a candidate program in its context: does a proposal with the same surrounding structure continue the same way, and does the expansion rebuild a fragment the proposals repeat? A regularization term keeps every rule reachable, so wrong proposals delay the solution but cannot hide it. Across five domains and two search backends, Narcissus beats static guidance at every budget and consistently outperforms re-prompting the LLM to fix its own proposals; it reaches proposal-like programs an order of magnitude sooner and solves $40\%$ of ARC tasks where the raw proposals solve $13\%$, all without a single LLM call during search.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
Reconstructing the Right Episode: Evaluating Interleaved Conversational Memory Beyond Long Context
Zhexi Feng, Ruiyi Zhang, Yongbo Yang et al. (+1 more)
Conversations with chat assistants increasingly span many topics in a single long-running thread, challenging
memory systems. Existing long-context and
memory benchmarks often expose session or topic boundaries, or probe direct personal-
memory questions. These settings understate a harder assistant-
memory regime: a flat mixed-topic thread where the system must infer which earlier episode makes a later task decision valid. We introduce SCALE-QA, a constraint-grounded task QA
benchmark for flat unsegmented threads targeting episode integrity failure. The
dataset contains 3,000 audited questions across 10 domains, uses deterministic four-way multiple-choice grading, and includes a deterministic runtime builder; experiments use all 3,000 questions through 128k and a stratified 400-question diagnostic at 1M. SCALE-QA questions are ordinary task-oriented requests whose correct answer depends on causally related evidence introduced earlier in the conversation. We also propose Temporal-Semantic Interleaved
Memory Reconstruction (TSIM), which segments the turn stream into coherent episodes and indexes them through a hierarchical multi-view
memory stack with deterministic episode-level summary and cluster-routing views. Experiments show that SCALE-QA challenges strong RAG baselines and long-context LLMs alike; across three open-source and proprietary LLM backends, TSIM achieves the highest accuracy in every backend setting, gaining 5.6-17.6 accuracy points over the strongest corresponding baseline.
Read the full abstract ▾
All authors Zhexi Feng, Ruiyi Zhang, Yongbo Yang, Pengtao Xie