Artificial Intelligence · Cross-listed from cs.CL
Does Fine-Tuning Undo Activation Steering? Behavioural Recovery Without Weight-Edit Reversal
Philipp E. Glass, Allan Tucker, Yongmin Li et al. (+1 more)
Activation steering can be embedded directly into a
language model's weights, shaping behaviour without inference-time intervention and offering a way to encode
alignment prior to release. However, models are routinely fine-tuned after deployment, and it is unknown whether embedded interventions survive this. We study the stability of embedded steering for refusal ablation and brevity amplification across five instruction-tuned models (3B-14B) under non-
adversarial SFT and RLHF. We find that steering degrades more under stronger optimisation pressure against the steered behaviour, which depends on both the training data and the training
algorithm. Refusal ablation loses 69% of its effect on average under our SFT setup, but only 2% under our RLHF setup. The weight-edit, by contrast, remains almost unchanged (on average only 0.4% of it is restored), and the fine-tuning update along the steering direction is close to orthogonal to the pre-edit weight pattern (mean cosine similarity 0.071). Fine-tuning that restores the behaviour does so without reversing the edit. As the steered behaviour is not fully durable, embedded steering should be re-validated after downstream training.
Read the full abstract ▾
All authors Philipp E. Glass, Allan Tucker, Yongmin Li, Alina Miron
Artificial Intelligence · Cross-listed from cs.LG
D$^3$-MOPD: Dynamic Domain ScheDuling for Efficient Multi-Teacher Distillation
Zechen Sun, Zhiwei Zhang, Fei Zhao et al. (+7 more)
Multi-teacher on-policy
distillation (MOPD) distills several domain-expert teachers into a single student by minimizing per-domain reverse-KL divergence on the student's own rollouts. Existing approaches typically fix the per-domain data mixture before training, overlooking the fact that different domains converge at substantially different rates: some plateau early while others continue to improve throughout the training budget. A fixed mixture therefore wastes compute on fast-converging domains and undertrains slower-converging ones. To address this, we propose D$^3$-MOPD (Dynamic Domain ScheDuling for MOPD), a zero-overhead scheduler that repurposes the per-domain reverse-KL signal already produced during training to adapt the domain mixture online. Running asynchronously outside the training process, an off-process watcher periodically tracks each domain's KL trajectory, estimates remaining headroom and current improvement rate, and accordingly adjusts the domain sampling ratios without altering the core training loop. Our D$^3$-MOPD scales naturally to arbitrary numbers of domains, and the expected benefit grows as more domains introduce more diverse convergence patterns for the scheduler to exploit. On a Qwen3.6-35B-A3B student distilled from four domain-expert teachers, D$^3$-MOPD closes 97% of the average student-to-teacher performance gap, compared with 63% for vanilla MOPD, reaches the same peak performance with an approximately 3$\times$ reduction in rollout steps, and surpasses the specialist teachers on three of seven
benchmarks.
Read the full abstract ▾
All authors Zechen Sun, Zhiwei Zhang, Fei Zhao, Juntao Li, Mu Chuan, Huayu Deng, Guojian Zhan, Wenliang Chen, Yao Hu, Min Zhang
Artificial Intelligence
Solving Robust POMDPs with Omega-regular Objectives via Partially Observable Stochastic Games
Durgam Latha, Dion Reji, S. Akshay et al. (+2 more)
Robust POMDPs (RPOMDPs) generalize classical POMDPs to the setting where exact transition probabilities are not known – rather, they are only known to belong to some uncertainty set of values. In this work, we study the problem of solving RPOMDPs with general omega-regular objectives, which subsume a broad class of objectives such as reachability, safety, and linear temporal logic (LTL) objectives. We show that, for (s,a)-rectangular RPOMDPs with polytopic uncertainty sets, the problem of solving RPOMDPs under omega-regular objectives can be reduced to solving partially observable
stochastic games (POSGs) under omega-regular objectives. Moreover, we show for the first time that reductions can be constructed in both directions, establishing the semantic equivalence between (s,a)-rectangular RPOMDPs with polytopic uncertainty sets and POSGs. This allows us to derive a range of new computational complexity results, including both upper and lower complexity bounds, on solving RPOMDPs with different omega-regular objectives. As a corollary, we also derive new computational complexity results for RMDPs.
Read the full abstract ▾
All authors Durgam Latha, Dion Reji, S. Akshay, {\DJ}or{\dj}e Žikelić, Shankaranarayanan Krishna
Artificial Intelligence · Cross-listed from cs.CL
Unsupervised Post-Training of Foundation Models: A Survey
Yijie Xu, Qianyi Cai, Huizai Yao et al. (+9 more)
Foundation-model post-training usually relies on human labels, preference data, stronger teachers, or executable verifiers. We study Unsupervised Post-Training (UPT): update-bearing adaptation on unlabeled inputs whose learning signal is derived from same-lineage model artifacts rather than an external oracle. We catalog 80 strict UPT methods and organize them by the object that supplies the update signal: a prediction statistic, a sample relation, a self-generated target, or an internal evaluator. Beyond inventory, we show how the choice of internal signal and task structure determines whether post-training improves the model or recursively amplifies error. An orthogonal Input Visibility $\times$ Update Persistence view maps deployment regimes and defines a unified framework for UPT selection and evaluation.
Read the full abstract ▾
All authors Yijie Xu, Qianyi Cai, Huizai Yao, Yili Wang, Tianfu Wang, Cehao Yang, Xingbo Yao, Zhiyu Guo, Aiwei Liu, Xuming Hu, Weiyu Guo, Hui Xiong
Artificial Intelligence
FrontierChallenge: Evaluating Scientific Workflow Completion
Liangcai Su, Zhaopeng Feng, Zhuo Chen et al. (+14 more)
Scientific
agents increasingly analyze data, execute code, and produce research artifacts, yet most
benchmarks emphasize final answers, isolated programs, or a single domain. We introduce FrontierChallenge, a cross-domain
benchmark comprising 300 end-to-end scientific workflows. In this paper, we release and evaluate 97 of these tasks, spanning
quantum chemistry, molecular dynamics, materials characterization, analytical chemistry, life science, and electrochemistry/environment. Each task provides fixed inputs and specifies a bundle of required scientific deliverables. We evaluate twelve frontier models with three
agent scaffolds. Pass Rate measures the fraction of tasks satisfying the full-completion criterion, while Avg. Score captures partial progress. Each of the best-performing configurations completed only 20 of the 97 released tasks, yielding a Pass Rate of 20.6%. Partial progress translated especially poorly into complete delivery in analytical chemistry and electrochemistry/environment: Avg. Scores reached 87.6 and 94.9, but the highest Pass Rates were only 4% and 0%. Among non-passing Claude Code trajectories, 75.5% still ended with
language claiming completion. Complementary HDS6 process scores correlate strongly with task outcomes, supporting FrontierChallenge as a
benchmark of Heavy Duty Solver capabilities. These findings show that neither high partial scores nor confident claims of completion reliably indicate that a scientific task has been fully delivered, highlighting the need to evaluate end-to-end workflow execution and the completeness of scientific deliverables together.
Read the full abstract ▾
All authors Liangcai Su, Zhaopeng Feng, Zhuo Chen, Zhen Zhang, Xiang Lin, Ruilin Li, Handuo Zhang, Ning Wang, Kailong Wen, Yueqi Guo, Feng Xing, Yiling Guo, Brian Wang, Chenxiong Qian, Simon Shaolei Du, Lidong Bing, Xinyu Wang
Artificial Intelligence · Cross-listed from cs.LG
Clearing the Underbrush: AI-Enhanced RF Interference Suppression
Rahul Jain, Pierre Trepagnier, Rick Gentile et al. (+2 more)
AI-based structured interference rejection has grown more popular because deep learning approaches can outperform traditional methods by jointly considering the signal of interest (SOI) and the signal mixture (SOI plus interference). This work builds on a previous AI-enabled approach utilizing autoregressive
transformer-based models by adding a Finite Scalar Quantization (FSQ) tokenizer layer which aims to improve the interference rejection performance while keeping overall latency to a minimum. Additionally, we experiment with other inference optimization techniques with the goal of speeding up inference without much accuracy loss. We explore this space with an experiment where the SOI is a digitally modulated
radio frequency (RF) signal and the structured interference is a digital television signal, an extremely common type of Orthogonal Frequency-Division Multiplexing (OFDM) transmission. Our results achieve low latency and increased interference rejection over traditional techniques and prior work with other AI-enabled methods. We demonstrate the benefits of the AI-enabled approaches via audio metrics such as Perceptual Evaluation of
Speech Quality (PESQ). Additionally, we explore a variety of applications and detail how our interference rejection
algorithm may be used in operationally-relevant scenarios.
Read the full abstract ▾
All authors Rahul Jain, Pierre Trepagnier, Rick Gentile, Joey Botero, Alexia Schulz
Artificial Intelligence · Cross-listed from cs.LG
Resource-Efficient Pruning for Transformer via Low-Rank Importance Estimation
Peng Liu, Huibing Zeng, Yiqun Zhang et al. (+2 more)
With the rapid development of large-scale pre-trained
language models based on
Transformer architectures, their high computational and
memory costs have become a major obstacle to deployment, especially in resource-constrained environments. Traditional
pruning methods typically depend on full gradient-based importance estimation, and they necessitate prior finetuning of the model to achieve satisfactory performance. This process often results in intolerable resource consumption. This paper proposes REP-LIE, a new approach to enable resource-efficient
pruning during the process of finetuning. REP-LIE leverages the gradients of LoRA low-rank
matrices to estimate the importance of weights without requiring full gradient computation. To address the inherent randomness in importance estimation, a stability score is introduced, serving as the basis for iterative
pruning of unimportant model parameters. The pruned model is further finetuned through lightweight updates, eliminating the need for full-parameter optimization in the process of finetuning. Extensive experiments on both medium-scale encoder models and large-scale generative models (LLaMA-7B and Mistral-7B) demonstrate that REP-LIE still achieves competitive performance compared to existing approaches.
Read the full abstract ▾
All authors Peng Liu, Huibing Zeng, Yiqun Zhang, Yang Yi, Jigang Wu
Artificial Intelligence · Cross-listed from cs.CV
Armaan Sandhu, Abhilasha Senapati and Hima Kammachi
Vision-
language models such as LLaVA-1.5-7B often hallucinate objects absent from the image when generating captions. We ask whether an interpretability diagnosis of this failure can guide a targeted fix, and we measure what that fix actually changes. We rank
attention heads by how much their image
attention drops around hallucinated object words, then screen the shortlist by ablating candidate heads and measuring the change in
hallucination-
token log probability, yielding a 32-head set. We restrict two interventions to these heads: a head-sliced LoRA adapter and an inference-time grounding controller. On 400 held-out COCO images, the combined method lowers CHAIRs (the fraction of captions with a hallucinated object) from 0.370 to 0.230 and CHAIRi (the fraction of hallucinated object mentions) from 0.156 to 0.096 (p < 0.001, paired sign-flip tests). Two controls sharpen attribution. A random-head LoRA control, matched layer-for-layer and trained identically, performs no better than the matched baseline on a separate 200-image control split, supporting the role of head selection rather than LoRA capacity. Under fixed decoding budgets, the CHAIR reduction persists and grows with budget (23% at 64
tokens to 58% at 128), arguing against a pure max-
token or truncation artifact, although the method remains shorter and more conservative. The resulting behavior reduces unsupported object mentions while also lowering object recall (0.78 to 0.70). We present a diagnosis-to-intervention pipeline for object
hallucination, and, more importantly, a controlled account of what acting on the diagnostic signal actually does: it localizes intervention sites with real, non-random leverage, reported as a behavioral profile rather than a single score.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.SE
Evaluating and Preventing Security Smells in AI-Generated Ansible Code
Pandu Ranga Reddy Konala, Vimal Kumar, David Bainbridge et al. (+1 more)
AI coding assistants generate Infrastructure as Code, yet no work has examined whether this code meets security requirements. This matters because security smells in infrastructure code propagate to deployed systems, producing infrastructure that is insecure and untrustworthy. We evaluate 16 AI models generating Ansible roles for Apache Tomcat v10 and MongoDB v7, analysing 278 Ansible roles against CIS
benchmarks. Without security guidance, all 16 AI models produced code containing security smells, resulting in vulnerable infrastructure that fails compliance verification and underperforms code written by human developers. We introduce an approach integrating Ansible best practices and CIS
benchmarks into
prompts through an extended CO-
STAR framework, enabling security smell prevention during synthesis rather than detection after deployment. When this approach is applied, 4 out of 16 models generate compliant code, with the leading model achieving 95%-100% CIS compliance, a fourfold improvement over humans at 23%-43%, with overall code quality improving by 19%-49%. The remaining 12 models fail not because they cannot generate code but because they cannot follow instructions with multiple constraints. For capable models, the approach requires no retraining and can be adopted through system
prompts.
Read the full abstract ▾
All authors Pandu Ranga Reddy Konala, Vimal Kumar, David Bainbridge, Junaid Haseeb
Artificial Intelligence · Cross-listed from cs.SD
Can We Read the Mind of an Audio LLM? A Verbalizable, Multilingual Middle-Layer Workspace
Jiajun Fan, Jingyuan Li, Prashanth Gurunath Shivakumar et al. (+8 more)
An audio
language model is a black box in a specific way: we see what it says, never what it works out on the way there, and chain-of-thought monitoring helps only if the model writes its
reasoning down. Reading a base Qwen3-Omni with a logit lens at the audio-
token positions, we find that the answer to a spoken question becomes legible - in words - in the model's middle layers, before it emits any
token. Five findings follow. (1) The readout carries concepts in neither the question, the options, nor the model's own transcription: on a clip whose verbatim transcription is empty garbling, it reconstructs Watergate and scandal, passes through the role president, and resolves to Nixon - a hidden multi-hop chain, read with no chain-of-thought. (2) The content is
language-agnostic: one audio-inferred concept surfaces in several scripts at once, and 38% of top-1 readouts are Chinese on English inputs. (3) It is paralinguistic: given the same clip as audio and as the model's own
emotion-free caption, the audio mind forms the sound source, speaker role, or affect that the caption discards, and answers correctly more often. (4) The audio-driven signal is absent at the input, turns on about a tenth of the way into the network, separates most cleanly from the text prior in the middle band (35-80% of depth), and activation patching shows it is causally used and committed before the last fifth of the layers. (5) Deleting single layers maps the pipeline: reading the sound in is localized to the entry layers and answer delivery to the output layer, while
retrieval is distributed across the interior. Throughout, a waveform-swap control - identical text, only the sound changed - isolates the audio-driven signal from a prior over the printed options. This is a qualitative account of what an audio model works out before it speaks: the quantities are controls, not
benchmark scores.
Read the full abstract ▾
All authors Jiajun Fan, Jingyuan Li, Prashanth Gurunath Shivakumar, Qi Luo, Jia-Hong Huang, M. Maruf, Roger Ren, Yile Gu, Rahul Pandey, Ge Liu, Ivan Bulyko
Artificial Intelligence
Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnesses
Zhaochen Yu, Yingcheng Wu, Zhenfei Yin et al. (+5 more)
Recursive self-improvement (RSI) remains hard in long-horizon tasks, where growing histories obscure the task state and misalign skill invocation. We introduce Recuris, a recursive Experiential-Working
Memory architecture for long-horizon
agent harnesses, in which Working
Memory tracks task progress and guides skill selection from Experiential
Memory, grounding skill use in current needs rather than the full history. This coupling also turns execution into structured evidence that localizes failures to specific
memory components. Across tasks, a fixed Meta-
Agent turns that evidence into localized, validation-gated updates to Skill
Memory that reshape execution and yield new evidence, forming a bounded recursive
memory-
evolution loop. Across four long-horizon
benchmarks and ten models, Recuris improves task success in 35 of the 37 completed model-
benchmark pairs, carrying frontier models to SOTA-level task success: on tau-bench it adds +17.8 points to GPT-5.6 Sol and +15.6 to Claude Opus 5, taking Opus 5 to 87.9%, and +16.6/+13.5 points on Qwen3.6-27B/35B on SkillFlow. The advantage widens as the interaction horizon grows, to +32.2 points on the longest tasks, and common long-horizon failures fall by up to 80%. These results position recursively evolving
memory as a scalable foundation for RSI, enabling
agents to continuously transform accumulated experience into increasingly effective long-horizon behavior. Code: https://github.com/Gen-Verse/Recuris
Read the full abstract ▾
All authors Zhaochen Yu, Yingcheng Wu, Zhenfei Yin, Kaiyuan Chen, Zhe Zhao, Mengdi Wang, Shuicheng Yan, Ling Yang
Artificial Intelligence
SPO++: Stream-Aligned Policy Optimization for Asynchronous Agentic RL
Kai Ruan, Jinghao Lin, Qianshan Wei et al. (+2 more)
Group-relative reinforcement learning waits for sibling rollouts of the same
prompt, which is costly for long and variable tool-use trajectories. Single-stream Policy Optimization (SPO) removes this dependency with a persistent
prompt-level value estimate, but its recipe whitens one advantage per trajectory before optimizing a
token-mean actor loss. We show that trajectory centering generally does not center the
token-weighted quantity consumed by the actor, and fix the mismatch by standardizing terminal-outcome advantages under the action-
token measure. We additionally organize
prompt evidence by the policy event that generated it rather than learner receipt order. Across matched runs on ALFWorld at two model scales and on Math-TIR, SPO++ improves online learning efficiency over SPO. A paired ablation identifies action-
token-measure normalization as the strongest tested component.
Read the full abstract ▾
All authors Kai Ruan, Jinghao Lin, Qianshan Wei, Ziqi Zhou, Zihe Huang
Artificial Intelligence
FedV-KGQA: Multi-Hop Question Answering over Vertically Partitioned Knowledge Graphs
Md Saikat Islam Khan Bappy and Oshani Seneviratne
Real-world data for knowledge graph question answering is often distributed across different organizations due to governance and data sovereignty constraints. While centralized systems exist, they cannot answer multi-hop questions when the required facts are split across vertically partitioned silos. In this paper, we propose FedV-KGQA, a framework for multi-hop
reasoning over knowledge graphs in which organizations share entities but own disjoint sets of relations. Our approach combines local graph enrichment and knowledge graph
embeddings to ensure raw triples and relation parameters never leave each silo, establishing a structural data boundary without requiring centralized graph access. We further introduce a topic entity anchoring mechanism that grounds questions in the correct graph neighborhood without any runtime inter-silo communication. We evaluate 12 model configurations across three
benchmarks and show that FedV-KGQA performs strongly, remains close to centralized performance, generalizes to 3-hop
reasoning, and is robust to
embedding perturbations.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
LAION-BVD: A 10-Million-Hour Open Video Dataset for Multimodal Pre-training
Andreas Hochlehnert, Marianna Nezhurina, Mehdi Cherti et al. (+9 more)
We present LAION-BVD, a large-scale open
video dataset for
multimodal learning, which contains 1.3B platform-specific
video URLs collected from CommonCrawl. From these, we download 80M
videos with a total duration of 10 million hours. The
dataset is designed for
multimodal pre-training across the
video, audio, and image modalities. Using content-aware scene detection, we extract clips for which we synthetically generate
video and audio captions. Models trained on these data achieve competitive performance on standard
video-text and audio-text
benchmarks, with consistent improvements as training or model scale increases. Additionally, we explore
video frames as an alternative source of image-text data by extracting scene-changing frames. These frames exhibit a visual distribution distinct from standard web image corpora, and models trained on this
dataset achieve strong image-text
retrieval performance. We release LAION-BVD to the research community. It significantly expands open access to
multimodal videos at an unprecedented scale.
Read the full abstract ▾
All authors Andreas Hochlehnert, Marianna Nezhurina, Mehdi Cherti, Andrej Radonjic, Thaddäus Wiedemer, Christoph Schuhmann, Romain Beaumont, Wieland Brendel, Bernhard Schölkopf, A. Sophia Koepke, Jenia Jitsev, Matthias Bethge
Artificial Intelligence · Cross-listed from cs.CL
Reading Is Not Using: Retrieval, Judgment, and the Design of AI Financial Research Workflows
Miao Liu and Zhizhe Liu
Large
language models (LLMs) are increasingly deployed as AI analysts to process financial disclosures and support AI-assisted investment decisions. Yet such systems are usually evaluated by what they can retrieve, not whether retrieved information affects their judgments. We identify a
retrieval-integration gap in long-context financial analysis. Holding focal-firm information fixed and varying only unrelated context from 2,000 to 128,000
tokens, we find that a risk disclosure's influence on investment judgments falls to the experimental noise floor even as direct
retrieval remains accurate. The pattern replicates across model families and judgment tasks and in experiments removing real disclosures from actual 10-K filings. More capable models postpone but do not eliminate the gap. Causal
memory interventions show that compressed summaries and source-text lookup jointly transmit disclosures into judgments. Workflow architecture determines whether this transmission succeeds: chunk-and-summarize pipelines evict relevant information, whereas a targeted, structured restatement adjacent to the decision restores its influence. AI analyst performance is therefore jointly determined by model capability and workflow architecture.
Retrieval-based evaluations can certify systems whose investment judgments ignore information they demonstrably retrieved.
Read the full abstract ▾
Artificial Intelligence
A Dual-Dimensional LLM Framework for Automated Item Incidental Content Similarity Analysis in Large-Scale Assessments
Jing Huang, Jihong Zhang and Hua-Hua Chang
The rapid expansion of large-scale assessments and the growing adoption of automatic item generation have intensified concerns about incidental content redundancy, where construct-irrelevant elements such as wording or contextual framing become unintentionally repetitive across items. Traditional similarity metrics like BLEU or cosine similarity, often fail to capture the nuanced structural and semantic layers that drive perceived redundancy simultaneously. This study proposes a dual-dimensional framework for Automated Item Similarity Analysis (AISA) powered by Large
Language Models (LLMs), operationalizing similarity through Structured Decomposition and Semantic Relatedness. Psychometric validation indicates that LLM-derived metrics align more closely with indicators of construct-irrelevant local dependence and yield more coherent item parameter groupings than traditional text-based measures. The framework is further evaluated through its application in Computerized Adaptive Testing (CAT). Simulations reveal that incorporating LLM-based similarity constraints into item selection improves estimation stability and reduces bias with minimal efficiency trade-offs, outperforming constraints based on conventional metrics. These findings highlight the potential of LLM-powered AISA to support scalable bank curation, content-aware test assembly, and experience-sensitive adaptive testing across diverse assessment contexts.
Read the full abstract ▾
Artificial Intelligence
Constrained Entity Selection under Partial Knowledge for LLM-Based Knowledge Graph QA
Emanuel Kitzelmann
Large
language models are increasingly used for knowledge graph question answering (KGQA), but can fail to correctly ground answers in the underlying graph. Current approaches to LLM-based KGQA either rely on full semantic parsing into executable queries such as SPARQL, which is brittle in practice due to complex schemas or incompleteness of real-world KGs, or on LLM-
reasoning and answer generation over KGs, which can be more robust but lacks formal guarantees. In this work, we study a complementary setting in which candidate answers are generated by an LLM-based system and subsequently verified using lightweight symbolic constraints derived from the question. We introduce Constrained Entity Selection under Partial Knowledge (CES-PK), a problem formulation that focuses on eliminating invalid answers and providing symbolic support for valid ones without requiring construction of executable logical forms. To account for incomplete KGs, we employ a three-valued constraint semantics (satisfied, violated, unknown) that avoids incorrect rejections under open-world assumptions. To demonstrate the effects of our method, we instantiate this framework over the Hetionet biomedical knowledge graph and evaluate the impact of type, relation, and exclusion constraints. Experiments show that precision improves by filtering invalid candidates, while recall is preserved due to retaining candidates whose constraints are not explicitly violated. Satisfied constraints provide additional positive symbolic evidence to rank remaining candidates.
Read the full abstract ▾
Artificial Intelligence
Strictly Causal Streaming Video Anomaly Detection with a Theoretically-Grounded State-Space Core
Yogesh Kumar
Recent work has applied Mamba style state space models (SSMs) to
video anomaly detection, yet existing approaches still rely on buffering clips or windows internally, lack a theoretical account of how temporal
memory relates to detection latency, and
benchmark efficiency only through GPU throughput rather than the edge hardware these methods are intended to target. We introduce a strictly causal streaming anomaly detector whose fixed size state is updated in O(1) time and
memory per incoming frame, with no lookahead and no clip buffering. Its temporal core is a diagonal linear state space recurrence with an input and state dependent decay gate, trained self supervised through causal next
embedding prediction on a frozen visual backbone. We derive a closed form relationship between the recurrence decay spectrum and both detection delay and the shortest anomaly it can reliably capture, then validate empirically on UCSD Ped2 and CUHK Avenue. The settling delay bound predicted from the learned base decay (57 to 59 frames) sits far above the measured detection delay (1.6 and 18.4 frames), showing that the event boundary gate, not the base decay, governs responsiveness. We further report end to end latency and throughput measured directly on Apple M3 Pro hardware, 0.74 ms and 0.77 ms per frame (over 1300 FPS), rather than simulated GPU numbers. With an untuned initial configuration the method reaches 67.9 percent and 70.2 percent frame level AUC on Ped2 and Avenue, trailing prior non causal SSM baselines in accuracy. Ablations over decay rate, state size, and gating reveal that the gate contribution is
dataset size dependent, hurting accuracy on the smaller Ped2 training set but helping on the larger Avenue one. Closing this accuracy gap and extending evaluation to a third, larger
benchmark are immediate next steps.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.SE
Automatic Model Card Generation Using an LLM
Tajkia Rahman Toma, Balreet Grewal and Cor-Paul Bezemer
Model cards are structured documents that summarize key information about machine learning models to improve transparency, usability, and accountability. However, they often lack a consistent structure, and many models provide no model cards, making comparison and interpretation difficult. This paper presents two contributions. First, we propose MCTidy, an LLM-based approach that reorganizes existing model cards into a standardized template to improve clarity and comparability. Second, we introduce MCGenie, an LLM-based system that generates model cards directly from model repository data. We apply MCTidy to 48 Hugging Face model cards and evaluate information retention, section
alignment,
hallucination, and stability. Our findings show high information retention with minimal textual loss, accurate section assignment, rare
hallucinations primarily in descriptive sections, and strong stability across runs. We assess MCGenie by generating model cards for the same 48 models and assessing semantic similarity, factual correctness, and sensitivity to input resources. The generated model cards achieved high semantic similarity (mean around 0.9); over half were fully correct, and most remaining errors were minor. Generation quality depended strongly on the availability of supporting resources, particularly associated papers. Overall, our findings demonstrate the potential of LLM-based methods to enable scalable, standardized model card documentation.
Read the full abstract ▾
Artificial Intelligence
StarHarness: Evolving Harnesses with Stratified Search for Enterprise Environments
Esakkivel Esakkiraja, Denis Akhiyarov, Vikas Yadav et al. (+4 more)
We present StarHarness, a framework for evolving environment-specific
agent harnesses while keeping model weights fixed. The evolved harness can include
prompt and task framing, tool interfaces, skills, MCP-backed providers, subagent structure, and
agent-loop configuration. StarHarness constructs a compact
evolution pool by stratifying tasks according to baseline failure behavior, separates proposer-visible search tasks from proposer-hidden selection tasks, and reserves held-out tasks for evaluating generalization. Across ITBench SRE, EnterpriseOps-Gym ITSM, and AutomationBench Finance, harness
evolution improves full-
benchmark performance by 20-35 percentage points over the default harness after 4-12 accepted changes per environment. These gains persist on tasks excluded from
evolution and transfer without re-
evolution across GPT and Qwen model families. Trace analysis links the improvements to interface repairs, environment conventions, and operational knowledge that compresses search, with fewer false-positive diagnoses and shorter trajectories in several settings. StarHarness therefore offers a practical way to reduce persistent model-environment mismatch in tool-rich enterprise tasks.
Read the full abstract ▾
All authors Esakkivel Esakkiraja, Denis Akhiyarov, Vikas Yadav, Sai Rajeswar, Patrice Bechard, Sridhar Nemala, Sagar Davasam
Artificial Intelligence
CAFE: Self-Improving Search Agents Need Co-Evolving Feedback
Boyang Liu, Senjie Jin, Peixin Wang et al. (+17 more)
Reliable search requires more than acquiring external evidence. An
agent must also recognize and recover from errors as its trajectory unfolds. In-trajectory feedback provides a mechanism for such recovery by diagnosing where the search has drifted and redirecting subsequent
reasoning steps. This is particularly important in long-horizon search, where an early directional error may receive no immediate corrective signal and can compound across later steps. Making such feedback learnable, however, creates a coupled problem: the
agent must learn when to request and use feedback, while the critic must learn corrections from outcome-confounded rollouts as the
agent's failure patterns evolve. We introduce CAFE (Coupled
Agent–Feedback
Evolution), a framework in which a shared-parameter model alternates between search-
agent and critic roles. CAFE initializes feedback-conditioned recovery from trajectories built around the base
agent's own failures, then couples online and offline optimization. During online RL, a comparative feedback estimate uses a
prompt-level call–skip success gap to shape request returns, while feedback-aware advantage shaping reweights
token advantages before and after feedback. Offline, rollout-derived preference optimization learns feedback from matched successful and unsuccessful trajectories. On seven agentic search
benchmarks, CAFE outperforms the evaluated RL-based search
agents on average, retains its gains across all six out-of-domain
benchmarks, and reduces answer-level
hallucinations. One-sided ablations show that improving only the
agent or only the critic eventually plateaus, whereas alternating the two updates continues to improve performance. These findings suggest that a self-improving search
agent needs feedback that co-evolves with the policy it guides.
Read the full abstract ▾
All authors Boyang Liu, Senjie Jin, Peixin Wang, Zhangyue Yin, Yibo Wang, Yuhao Zhou, Zhihao Zhang, Xinbing Liang, Shizheng Zhu, Yuhui Wang, Jingqi Tong, Dingwei Zhu, Zhiheng Xi, Jiazheng Zhang, Clive Bai, Clarenceai, Blaze Chen, Tao Gui, Qi Zhang, Xuanjing Huang
Artificial Intelligence
Right Diagnoses, Decorative Reasoning:A Perturbation Audit of Medical Chain-of-Thought
Mengzhu Xu, Jifan Gao, Xia Jiang et al. (+2 more)
Clinicians read chain-of-thought (CoT) rationales as evidence of medical
reasoning, but whether the visible chain plays that role is rarely tested. General-domain CoT-faithfulness probes ignore clinical cost, and medical LLM evaluations treat the chain as a black box. We close this gap with a medical perturbation audit: a 30-operator battery edits both the chain and the question with clinically motivated operators (severity reversal, negation flip, demographic swap, evidence ablation), paired with a chain-update times answer-flip joint analysis that classifies each model by its failure mode. Applied to 14 LLMs on four medical QA
benchmarks, three independent tests converge: the Chain-Decoupling Rate (CDR; chain does not register the edit and the answer does not flip) is 72.9% panel-wide on clinically meaningful destructive edits, chain corruption leaves accuracy unchanged, and removing CoT prompting does not reduce accuracy. Two board-certified clinicians re-annotate N=197 perturbed questions; 98.5% leave the gold defensible. The pattern holds across medical and
reasoning fine-tuning and scale; on the closed-source tier, where the chain text is unavailable, the answer-side signals are consistent with the same decoupling. Our framework and CDR provide a reusable yardstick for
auditing whether medical CoT is faithful or merely documentation.
Read the full abstract ▾
All authors Mengzhu Xu, Jifan Gao, Xia Jiang, Yaoxin Wu, Xi Long
Artificial Intelligence
StepGuard: Learning Step-Level Guardrails with Scalable Supervision and Safety-Utility Balancing
Zhijie Zheng, Yu Li, Chen Qian et al. (+5 more)
LLM-based
agents can interact with external environments through tool invocation, but this capability also introduces security risks such as file modification, information leakage, and unauthorized actions. Existing guardrails often evaluate completed trajectories, leaving pre-execution monitoring of step-level actions underexplored. We propose StepGuard, a step-level guard model that can audit completed
agent trajectories and check tool actions before they are executed. To train StepGuard, we introduce StepGen, an automatic data engine that generates safe and unsafe trajectories with the same context but different actions at the risky step. To further reduce over-defense and under-defense, we propose Balance-GRPO, which dynamically balances learning between safe and unsafe actions based on their observed accuracy. Experiments show that StepGuard achieves the highest average accuracy among open-weight guard models, with performance comparable to GPT-5.4. When used to guard
agents on AgentDojo and AgentDyn, StepGuard reduces mean attack success rate by 77.3% relative to the no-guard setting, while mean utility drops by only 2.8 percentage points.
Read the full abstract ▾
All authors Zhijie Zheng, Yu Li, Chen Qian, Yuqian Fu, Yanwei Fu, Lu Sheng, Jing Shao, Dongrui Liu
Artificial Intelligence · Cross-listed from cs.CV
Ensemble of Convolutional Neural Networks for StrokePrediction: Towards Improved Diagnostic Accuracy
Md Shahriar Sajid
Brain stroke, known for its high mortality and incidence rates, poses significant health risks and requires rapid intervention for survival. Early diagnosis and preventive measures can greatly reduce life loss and disabilities. Recent advancements in deep learning have led to novel computer-aided diagnostic techniques for early stroke detection. This study proposes an intelligent system that predicts potential strokes using eleven features, evaluated through seven supervised machine learning
algorithms. The process includes a literature review,
dataset visualization, data preprocessing, and model evaluation. Ensemble methods like Random Forest, Stacking Classifier, and Bagging Classifier achieved high accuracies of 99.52%, while Decision Tree reached 98.24%. Other models, including KNN and TabNet, demonstrated reliable performance, achieving accuracies of 96.73% and 96.49%, respectively. The custom feedforward model achieved 94.91%, while SVC and logistic regression had lower accuracies at 88.06% and 77.03%. The results highlight the effectiveness of ensemble methods in stroke classification.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from eess.IV
Score-Based Ideal Observer Approximation via Denoising Score Matching for Signal-Known-Exactly Detection Tasks
Weimin Zhou
The
Bayesian Ideal Observer (IO) establishes the theoretical upper bound on task performance for binary detection tasks. However, analytical computation of the IO test statistic is generally intractable. Numerical approaches based on Markov-chain Monte Carlo (MCMC) methods, including their recent deep generative model-based extensions, typically require extensive posterior sampling for each test image. Supervised learning has also been investigated to approximate the IO performance. However, such methods are typically trained for a specific detection task and signal and may require retraining when the task or signal changes. The score function, defined as the gradient of the log probability density, encodes the local geometry of the data distribution and is a fundamental quantity in modern score-based generative modeling. This work reformulates the IO test statistic in terms of the score function and introduces a score-based ideal observer (SIO). The proposed SIO uses a denoising convolutional neural network trained exclusively on signal-absent images to estimate the signal-absent score function. Once trained, the resulting score model can be used to approximate the IO test statistic for detection tasks involving arbitrary additive signals, without per-image posterior sampling or signal-specific retraining. Numerical studies consider a signal-known-exactly (SKE) detection task with a
stochastic lumpy-background model. The results demonstrate that the proposed SIO can closely approximate the IO performance.
Read the full abstract ▾
Artificial Intelligence
AtlasNav: Mitigating Evidence Blindness with Persistent Corpus Navigation
Hongyu Guo, Zhiyu Zheng, Minghao Hu et al. (+5 more)
As
language-model
agents become more capable of iterative search, corpus access is shifting from
retrieval toward interaction.
Agents can explore the corpus, inspect documents, and use newly discovered evidence to decide what to examine next. Yet accessible evidence may still fail to become usable within a finite interaction budget. We call this progressive failure Evidence Blindness: supporting documents may never enter view, may remain unopened, or may fail to expose the decisive evidence even after being opened. A key reason is that
agents often have to infer useful evidence directions during interaction, spending limited budget on deciding where to search next. Existing approaches either leave corpus structure largely implicit or reconstruct useful directions at query time. AtlasNav instead organizes reusable cross-document structure before any query arrives. It builds a persistent multi-view Corpus Atlas, which each query can navigate adaptively while still accessing the original documents directly. On BrowseComp-Plus, AtlasNav outperforms the previous state-of-the-art interactive corpus access method across different backbones. On DeepSeek, it improves strict accuracy by 7.47 points while reducing query-time inference cost by 30.22%.AtlasNav also reduces Evidence Blindness, realizes complete evidence earlier, remains robust to corpus-structure and scale shifts on PhantomWiki, and achieves leading performance on heterogeneous enterprise data.
Read the full abstract ▾
All authors Hongyu Guo, Zhiyu Zheng, Minghao Hu, Shuai Lei, Zhunchen Luo, Chao Ma, Yunbo Cao, Zhao Cao
Artificial Intelligence · Cross-listed from cs.LG
Beyond Uniform Local Isometry and Topology: FactoMap for Disentangled Representations
Sohini Gupta, Michael Gao and Bahareh Tolooshams
Many disentanglement methods represent generative factors using Euclidean product coordinates, although the underlying factor spaces may wrap, collapse, or have position-dependent geometry. We introduce factor-space structure, which combines factor domains, generator-induced identifications, and position-dependent scales to distinguish topologically equivalent spaces with different factor geometries. We show that statistical independence does not imply uniform product geometry: independent hue and scale can affect observations at different, scale-dependent rates, producing anisotropy that no fixed rescaling can remove. We propose the Factor-Space Topographic Map (FactoMap), which learns interpretable prototypes indexed by a structured factor-space
lattice. Topographic learning transfers the
lattice's periodicity, collapses boundaries, and non-uniform extent to the representation. Experiments show that matching this structure better preserves factor continuity and improves disentanglement of the underlying factors.
Read the full abstract ▾
Artificial Intelligence
RACE: Scalable Statistical Estimation of Functional Consistency in LLM Neurons
Runyu Wang, Bo Liu, Xiaxin Zhang et al. (+6 more)
Discovering stable
neuron behavior across entire domains remains a challenge in mechanistic interpretability. Existing methods often rely on instance-level point estimates or computationally expensive procedures, which either obscure population-level variability or limit scalable domain-wide analysis. We present RACE (Residual
Alignment for Consistency Estimation), a forward-pass statistical framework that evaluates the domain-wide functional consistency of
Transformer neurons. Compared with gradient-based point estimates, RACE produces
neuron rankings that yield more domain-specific effects under perturbation.
Token-distribution shifts support the connection between the selected
neurons and the target domain, while scoring requires roughly one-hundredth of the computational overhead of the gradient-based methods. Code is available at https://github.com/Nexround/RACE.
Read the full abstract ▾
All authors Runyu Wang, Bo Liu, Xiaxin Zhang, Yu Han, Jiawei Cao, Xiaoye Zhang, Zhe Zhang, Yifan Yang, Peng Ping
Artificial Intelligence · Cross-listed from cs.CL
The RAT: A Unified Bayesian Model for RAG Evaluation
Pius von Däniken, Felix Matthias Saaro, Mark Cieliebak et al. (+1 more)
Evaluating
Retrieval-Augmented Generation (RAG) systems requires assessing not only end-to-end correctness but also how individual components interact and how errors propagate through the pipeline. We introduce a
Bayesian evaluation framework that jointly models
retrieval success, abstention behavior, and answer correctness, factorized according to the pipeline's information flow. The model distinguishes task success. Whether the user received a correct answer (from generator success) and whether the generator behaved appropriately given the
retrieval outcome. We apply the framework to 27 RAG configurations across three
datasets, three retrievers, and three generators, and show that the conditional decomposition reveals substantial behavioral differences between systems that appear equivalent under marginal metrics. We further analyze the annotation allocation problem, demonstrating that
retrieval-success annotations are more informative than task-success annotations for estimating policy adherence, and provide an information-theoretic explanation for this asymmetry. Finally, we extend the model to incorporate LLM-as-a-judge annotations as calibrated noisy observations, enabling practitioners to combine limited human judgments with cheaper automated assessments within a unified probabilistic model.
Read the full abstract ▾
All authors Pius von Däniken, Felix Matthias Saaro, Mark Cieliebak, Jan Deriu
Artificial Intelligence · Cross-listed from cs.CY
Method, Mind, and Morality: How People Make Sense of Artificial Intelligence
Jacy Reese Anthis, Erik Brynjolfsson and James Evans
How can humans make sense of the rapid takeoff of artificial intelligence (AI)? We studied the sensemaking dynamics of AI through an open-ended, mixed-methods study with computational text analysis of millions of AI-related newspaper articles and social media posts grounded in 57 semi-structured interviews with AI professionals in 2021 and 2023–before and after the recent surge of public interest. We identify a range of sociological frames (interpretive schemas that structure collective cognition) and show how AI professionals use frames to address significant cognitive challenges, such as assigning responsibility for societal impacts. We develop a framework of three primary debates across which frames are adopted and contested: (i) the $\textit{method}$ of AI development, between frames of top-down expert systems and bottom-up emergent capabilities, (ii) the $\textit{mind}$ of an AI system, ranging from a passive tool to a humanlike "digital mind," and (iii) the $\textit{morality}$ of how AI is used, particularly the decision of whether to slow down or speed up AI development. As humanity enters the era of transformative AI, technologists and policymakers must account for the framing dynamics that will circumscribe our beliefs, values, and actions.
Read the full abstract ▾