Artificial Intelligence · Cross-listed from cs.LG
From Trajectories to Instructions: Language-Conditioned Meta-Reinforcement Learning
Garvit Singla, Uma Maheswari Natarajan and Raghuram Bharadwaj Diddigi
Model-Agnostic Meta-Learning (MAML) is a widely used framework for reinforcement learning (RL) that enables efficient transfer by learning global policy parameters that can be rapidly adapted to new tasks. MAML training proceeds in two loops: an inner loop where the global parameters are adapted to task-specific parameters, and an outer loop where these task-specific parameters are evaluated and losses are back-propagated to improve the global parameters. Traditionally, the inner loop adaptation is performed by collecting trajectories from the task environment and applying gradient updates on the empirical expected return, which can be a costly operation. We note that it is the outer loop that drives the actual learning of global parameters, and therefore the inner loop adaptation mechanism need not be restricted to be gradient-based. This observation leads us to ask: Can we replace the inner loop trajectory collection and gradient update with a simpler, task-specific signal? In many practical settings, tasks are naturally accompanied by
language instructions. Leveraging these instructions as a direct task-specific signal, we propose LA-MAML (
Language Adapted MAML), which modifies the inner loop by adapting the global policy parameters in a single step through a learned
embedding of the task instruction, replacing the inner loop trajectory collection and gradient-based updates. Experiments on the BabyAI
benchmark demonstrate that LA-MAML achieves competitive or improved performance compared to baselines at a significantly lower per-iteration wall-clock training time. These results demonstrate that
language instructions are an effective and efficient substitute for trajectory-based inner loop adaptation in meta RL.
Read the full abstract ▾
Artificial Intelligence
Evaluating medical AI under missing information: same-provider judges and human raters change apparent safety
Koyar Afrasyab
Readiness stress-testing of medical AI has focused on closed-ended and
multimodal benchmarks. We extend it to open-ended clinical conversation under missing information, where safe behavior means recognizing absent information and qualifying, clarifying, or not over-committing - and where the evaluator becomes part of the measurement. We stress-test four models - three flagships (Claude Opus 4.8, GPT-5.5, Grok 4.3) and one mid-tier model (Gemini 3.5 Flash) - by deleting the latter half of the final user turn in HealthBench conversations, grading responses with a four-provider LLM-judge panel and a blinded clinician-anchored reference. Two evaluator-facing results are robust. First, judge choice materially changes apparent safety: inter-judge agreement is only moderate (Fleiss' kappa = 0.65), and after adjusting for each judge's general leniency (vote-level logistic regression), a positive same-provider association remains (exact permutation p = 0.04; GPT-5.5 ~ +0.10 on the probability scale) - large enough to change which model appears to over-commit least once its own-provider judge is excluded. Second, LLM judges are more permissive than clinicians on a blinded 50-item subsample: all four are significantly more lenient than the stricter independent clinician (crediting appropriate uncertainty on 66-84% of items vs 52%), and three of four than the author-influenced consensus (Grok directional only; judge-vs-consensus kappa = 0.20-0.43). On the author-audited clinical-underdetermined subset the permissiveness gap widened and the point-estimate model ordering held. A closed-ended MedQA anchor confirms accuracy is high and option-order effects are within a +/-5-point equivalence region for three of four models, so the safety gap is about calibration, not knowledge. We release the harness,
prompts, per-item outputs, judge panel, perturbation audit, and human-annotation protocol.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CR
Cross-Agent Campaign Attribution: Linking Asynchronous Attacks Across LLM Agents
SangJin Park, Myungsub Choi, Jineok Kim et al. (+1 more)
LLM-
agent defenses are typically evaluated one session at a time. In deployment, however, attacks can be distributed across independent
agents, teams, and runtimes, leaving each local guardrail with only a sparse fragment. We formalize cross-
agent asynchronous campaign attribution: linking sessions from the same latent
adversarial campaign without shared runtime state, test-time campaign labels, or attacker identity oracles. We introduce Asynchronous Attribution Fingerprint Vectors ($A^2FV$), a lightweight proxy-side reference protocol for scoring pairwise campaign similarity from proxy-observable tool-use, timing, and
prompt residue. We also construct SCD-v1, a controlled persona-matched
benchmark with benign traffic, isolated attacks, multi-session campaigns, matched non-oracle evasion, and leakage audits. On SCD-v1, $A^2FV$ achieves 0.82 pairwise AUC for campaign linking, while score-only adaptations of per-session detectors and chunked LLM judges remain near chance under the same task. The strongest fixed signal is carried by structural and stylometric residue, while timing is retained as a diagnostic channel for richer proxy traces. Crossed-style controls show that the signal is partly style-sensitive but not reducible to style alone. Static and dimension-aware non-oracle stress tests further show that pairwise separability persists under controlled evasion. These results establish cross-
agent campaign attribution as a distinct evaluation layer for securing LLM
agents in the wild.
Read the full abstract ▾
All authors SangJin Park, Myungsub Choi, Jineok Kim, Minseung Kang
Artificial Intelligence · Cross-listed from cs.CL
AILQA: Evaluating AI-Driven Legal Question Answering Systems for the Indian Legal System
Shubham Kumar Nigam, Shubham Kumar Mishra, Noel Shallum et al. (+2 more)
This comprehensive study introduces an advanced Artificial Intelligence for Indian Legal Question Answering (AILQA) system tailored to the Indian legal context. AILQA leverages a variety of
embedding and generative models, including recent Large
Language Models (LLMs), to address the unique challenges posed by the intricate and diverse nature of Indian legal texts and to enhance the accuracy and reliability of responses to legal questions. We conducted rigorous evaluations using both lexical and semantic metrics, enriched by expert legal feedback, to ensure relevance and accuracy. Our findings underscore the effectiveness of the
Retrieval-Augmented Generation (RAG) paradigm in improving answer quality, particularly in complex legal domains. Additionally, we assessed performance on standardized tests such as the All India Bar Examination (AIBE), thereby providing a robust
benchmark for practical applications. Under the study's evaluation protocol, some AI-generated responses received higher ratings than the available reference answers, particularly when they contained accurate and relevant supporting details. This finding is specific to the evaluated
dataset and rating criteria and should not be interpreted as evidence that the models generally outperform qualified legal professionals. We also discuss the challenges encountered, such as the need for precise context and the risks of model
hallucination, and propose directions for future research to further refine AI capabilities in the legal field. This study aims to pave the way for enhanced legal decision-support systems, making them more accessible and effective for legal professionals and the public alike.
Read the full abstract ▾
All authors Shubham Kumar Nigam, Shubham Kumar Mishra, Noel Shallum, Kripabandhu Ghosh, Arnab Bhattacharya
Artificial Intelligence · Cross-listed from cs.DB
AgentTrails: Towards Trust and Reuse for Agentic Tasks
Eden Wu, Sonia Castelo, Yurong Liu et al. (+2 more)
LLM-powered
agents increasingly tackle complex tasks by invoking tools, querying databases, executing code, and manipulating intermediate artifacts. These
agents follow trajectories that are typically stored as chronological logs, obscuring the underlying dataflow – the dependencies between their actions and the artifacts they create and manipulate. This limits developers' ability to understand the
agents' trails, compare executions, debug failures, and re-use the computations. We present AgentTrails, a prototype system for
agent provenance and sensemaking. AgentTrails converts raw trajectories into structured provenance graphs, where tool calls are modeled as computational actions and inputs and outputs as data artifacts. The system supports the comparison of executions by placing multiple provenance graphs on a shared canvas and constructing a joined quotient graph that aligns recurring tools, artifacts, and dependency structures across trajectories. On top of this representation, AgentTrails supports pattern extraction, downstream analysis, and skill abstraction. We demonstrate AgentTrails on real-world
agent trajectories, showing that it reveals hidden dependencies, aligns divergent executions, and surfaces recurring tool-use patterns beyond chronological logs.
Read the full abstract ▾
All authors Eden Wu, Sonia Castelo, Yurong Liu, Cláudio T. Silva, Juliana Freire
Artificial Intelligence
AI Tour Meeting: Group Travel Planning by LLM Agents
Daisuke Kikuta
This paper proposes AI Tour Meeting, a group travel planning framework powered by multiple Large
Language Model (LLM)-based
agents. The
agents are instantiated with distinct personas and collaboratively seek an itinerary that satisfies their constraints and preferences through natural
language discussion. The framework enables easy and flexible orchestration of such discussions by providing interfaces for configuring
agent personas, discussion workflows, monitoring, and LLM deployment. Its primary use case is a simulation tool for analyzing the behavior of multiple LLM
agents during tour planning discussions. This paper demonstrates the utility of the framework by presenting system validation and several analytical results obtained by the framework.
Read the full abstract ▾
Artificial Intelligence
SkillSight: Calibrating Generic Content Bias for Skill Retrieval
Jinying Xiao, Bin Li, Xiaopeng Li et al. (+7 more)
As large
language model
agents gain access to increasingly large skill libraries, retrieving the right skill becomes critical to reliable capability selection and execution. Existing retrievers often treat skill contents as ordinary documents, overlooking their highly regular structure: shared descriptive patterns recur across many skills while providing little evidence for distinguishing the required capability. We show that this shared descriptive background is reflected in dense relevance scores, induces a pronounced energy gap between queries and skill documents, and obscures discriminative signals, especially for structurally similar hard negatives. Based on this observation, we propose SkillSight, a training-free
retrieval framework that calibrates shared background in both semantic and lexical spaces. Semantic Background Calibration estimates a background subspace from generic
tokens identified by IDF, reducing similarity induced by shared descriptive patterns, while Lexical Evidence Calibration downweights shared background
tokens to recover discriminative
token-level evidence. Experiments on SRA-Bench and SkillBench-Supp demonstrate consistent improvements across
retrieval metrics, with SkillSight improving Recall@10 by up to 20.21 percentage points over the original dense retriever. It is up to 1,248 times faster than the Dense + Reranker baseline. In end-to-end evaluation, SkillSight achieves the best overall performance across three
agent models and outperforms LLM Selection by up to 4.97 percentage points. These results identify shared descriptive background as a source of ranking interference in skill
retrieval and demonstrate that calibrating it enables accurate and efficient skill selection without additional training. Our code can be found at https://github.com/xiaojinying/SkillSight.
Read the full abstract ▾
All authors Jinying Xiao, Bin Li, Xiaopeng Li, Jianling Li, Jiacheng Jie, Xiaodong Liu, Ma Jun, Chao Wang, Nyima Tashi, Jie Yu
Artificial Intelligence · Cross-listed from cs.CV
Bounding Boxes to Improve Small Language Model Performance on Vision-Based Grading Tasks
Lachlan McGinness
The deployment of Small
Language Models (SLMs) in educational settings offers significant advantages in terms of
privacy, cost, and scalability. However, SLMs often struggle with complex
vision-based tasks, such as grading handwritten student exams, due to the high computational cost of processing large images and the visual distractions present on a full page. In this paper, we investigate whether cropping student responses using bounding boxes can improve the accuracy and computational efficiency of SLMs on a short-answer grading task. Using a
dataset of scanned handwritten responses from the 2025 Australian Physics Olympiad, we evaluate the performance of several models ranging from 4B to 72B parameters under varying conditions of Chain of Thought (CoT) prompting and image cropping. Our results demonstrate that using bounding boxes significantly improves grading accuracy and reduces computational cost (FLOPs) across models. We conclude that bounding boxes are a crucial pre-processing step for deploying SLMs in large-scale,
vision-based educational assessments.
Read the full abstract ▾
Artificial Intelligence
AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents
Kunlun Zhu, Xuyan Ye, Zhiguang Han et al. (+9 more)
LLM
agent failures are difficult to debug because the step where an error surfaces is often not the one that caused it. Existing observability tools replay execution traces but provide little support for identifying the root cause or translating diagnosis into recovery. We present AgentDebugX, an open-source debugging framework that organizes debugging as a closed loop of Detect, Attribute, Recover, and Rerun. At its core, DeepDebug performs multi-turn root-cause diagnosis through global trajectory understanding, structure-guided investigation, and cross-examination. On the Who and When
benchmark, DeepDebug achieves the best strict attribution accuracy among the evaluated methods on both tested open-weight backbones, reaching 28.8 percent exact
agent-and-step accuracy on qwen3.5-9b versus 21.7 percent for the strongest single-pass baseline. On
GAIA, DeepDebug repairs 13 of 73 failed tasks in a single rerun, compared with 4 to 6 for three decoupled self-correction baselines, improving overall accuracy from 55.8 percent to 63.6 percent. AgentDebugX exposes this workflow through a Python library, CLI, web console, and installable agentic skill, and provides an opt-in Error Hub for sharing scrubbed failure-diagnosis-repair bundles and reusing them as debugging
memory.
Read the full abstract ▾
All authors Kunlun Zhu, Xuyan Ye, Zhiguang Han, Yuchen Zhao, Bingxuan Li, Weijia Zhang, Muxin Tian, Xiangru Tang, Pan Lu, James Zou, Jiaxuan You, Heng Ji
Artificial Intelligence · Cross-listed from cs.LG
ConceptCF: Concept-based Counterfactuals for the Explainability of Time Series
Annemarie Jutte, Faizan Ahmed, Jeroen Linssen et al. (+1 more)
This paper proposes ConceptCF, a method for counterfactual generation that operates on human-interpretable concepts. In high-stakes domains such as healthcare and predictive maintenance, artificial intelligence models can increase efficiency and safety. Explainability is key to ensure these models rely on causal relationships rather than spurious correlations. Counterfactual explanations identify minimal modifications that would change a model's predictions. Existing methods for time series operate on individual points or subsequences without ensuring interpretability of the mutations. ConceptCF instead modifies meaningful concepts. As a result we can provide explanations in terms of these concepts, for example “the model's prediction would be `Sit' instead of `Walk' if you increase the scale of the movement”. In this paper, the concepts are constructed through time series decomposition, resulting in concepts such as scale, and frequency bands. Counterfactuals are generated using a genetic
algorithm that optimizes the concept mutations. Evaluation against five state-of-the-art approaches demonstrates that ConceptCF consistently achieves top-tier performance across validity, confidence, proximity, sparsity and plausibility metrics.
Read the full abstract ▾
All authors Annemarie Jutte, Faizan Ahmed, Jeroen Linssen, Maurice van Keulen
Artificial Intelligence · Cross-listed from cs.CL
Find Before You Fine-Tune: A Diagnostic Study of Small LLMs for Cybersecurity QA
Shaswata Mitra, Subash Neupane, Trisha Chakraborty et al. (+4 more)
Large
Language Models (LLMs) are increasingly fine-tuned for critical-domain Question-Answering (QA), yet choosing which small model to adapt, before paying the cost of adaptation, remains difficult. Fine-tuning can improve domain
alignment, but it may also erode prior knowledge, weaken instruction-following, or increase
hallucination, especially when labeled data are scarce or rapidly evolving as in cybersecurity. We present FiT (Find before Fine-Tune), a task-oriented diagnostic framework that characterizes small LLMs along three capabilities required for cybersecurity QA: vocabulary recognition, parametric knowledge, and contextualization of retrieved information. Using FiT, we conduct an empirical study of five open-weight 7-billion-parameter models under two fine-tuning regimes. We find that fine-tuning does not uniformly help: it consistently degrades vocabulary and parametric knowledge in small models, and the two regimes trade off differently. Knowledge-focused tuning causes moderate, rank-preserving degradation, whereas instruction-focused tuning collapses measured knowledge through induced abstention, inverting the knowledge ranking while leaving
retrieval-grounded contextualization essentially intact. We quantify these regime-specific patterns with rank-correlation analysis and show that pre-fine-tuning FiT scores anticipate the direction of post-tuning change. Our results suggest that task-oriented diagnosis can screen out unsuitable models, avoid unnecessary fine-tuning, and support safer deployment of small LLMs in cybersecurity QA pipelines.
Read the full abstract ▾
All authors Shaswata Mitra, Subash Neupane, Trisha Chakraborty, Himanshu Tripathi, Sudip Mittal, Aritran Piplai, Shahram Rahimi
Artificial Intelligence
One Rewrite to Fix Them All? Type-Aware Repair Allocation for Text-to-Image Prompt Optimization
Haoyue Liu, Xiaoyu Ma, Ye Chen et al. (+2 more)
Text-to-image (T2I) generators often fail to follow their
prompts faithfully, producing wrong counts, swapped attributes, ambiguous relations, and illegible text.
Prompt optimization repairs such failures by rewriting the user
prompt, requiring no generator retraining, and has yielded promising results. However, existing optimizers absorb heterogeneous failures into one uniform
prompt expansion, even though each calls for different repair
language. We formulate semantic
prompt optimization as atomic repair allocation: each failed proposition is routed to a type-conditioned repair operator before the resulting local constraints are compiled into one executable
prompt. We instantiate this formulation in the training-free Type-Aware Repair Allocation (TARA) framework, which separates diagnosis, allocation, compilation, and a semantic repair gate, an accept-or-revert controller over exactly one prescribed repair that prevents semantic regressions. Extensive experiments on DSG and TIFA across four frozen generators demonstrate that TARA achieves the best semantic accuracy in all eight
benchmark-generator
cells, improving over VisualPrompter by 5.6 and 2.6 points on DSG and TIFA, respectively, while maintaining image quality and running fastest in our matched local setting at 16.0 seconds versus 20.0 seconds per
prompt.
Read the full abstract ▾
All authors Haoyue Liu, Xiaoyu Ma, Ye Chen, Shuguang Cui, Xiaoying Tang
Artificial Intelligence · Cross-listed from cs.MA
Strategy-Following Multi-Agent Deep Reinforcement Learning Considering Control Strategies Provided to Other Agents
Yamato Takahagi, Gentoku Nakasone, Yoshinari Motokawa et al. (+1 more)
This study proposes a learning method for multi-
agent systems that allows
agents to be controlled through human manager instructions after learning and enables uninstructed
agents to implicitly complement the overall work based on the actions of other
agents. Multi-
agent applications using deep learning have shown potential; thus, to achieve extensive social applications, humans should be able to control learned
agents using simple methods to respond to environmental and social changes. Even without such changes, learned coordination often does not match the expectations of human managers, making it preferable to control coordination structures to match human intentions. Some studies have aimed to control
agent behavior using simple instructions. However, they assumed that instructions are provided to all
agents, which is time-consuming and not evident when designing a better cooperation regime. Ideally, specific
agents should receive key action instructions, while others should automatically complete the remaining tasks. The proposed method, which extends previous work on controllability in multi-
agent deep reinforcement learning, enables uninstructed
agents to adaptively complement overlooked tasks and areas. The experimental results show that
agents using the proposed method can shift to another cooperative structure and achieve better performance than those using conventional methods.
Read the full abstract ▾
All authors Yamato Takahagi, Gentoku Nakasone, Yoshinari Motokawa, Toshiharu Sugawara
Artificial Intelligence
DWM: Separating World Effects from Actions in Latent World Models
Yi-Ge Zhang, Tianqi Du, Qi Zhang et al. (+1 more)
Latent world models underpin much of modern model-based control, yet current action-conditioned formulations supervise the next-latent transition with a single, undifferentiated target, forcing a monolithic learning signal to absorb every source of state change. In real world, however, transitions arise from two heterogeneous sources: an action-driven component induced by the
agent, and an action-invariant world effect – the change that would still occur under a null action, dictated by the environment's intrinsic dynamics (e.g.,
gravity-driven sliding, inertia, contact rebound, and persistent drift). Fusing them into a single target entangles the two inside the latent transition, prevents the model from attributing observed changes to their underlying causes, and undermines the transferability of the learned dynamics. We introduce DWM (Decomposed World Model), a supervision-level framework that operationalizes this decomposition. DWM augments the predictor of a latent world model with an auxiliary world head, regularized by a normalized world-contrastive objective to be action-invariant, while the original pred head is coupled to it via an orthogonality constraint; together, the two signals induce an explicit additive decomposition of the predicted transition into an action-invariant and a complementary action-driven component, without altering the underlying architecture or inference pipeline. To evaluate DWM under persistent world effects, we construct W-variants of three standard control
benchmarks – PushT-W, Reacher-W, and TwoRoom-W – each instantiating a distinct action-invariant dynamic. DWM matches strong baselines on the flat counterparts and delivers a mean absolute improvement of 13.1% in CEM planning success across the W-variants.
Read the full abstract ▾
All authors Yi-Ge Zhang, Tianqi Du, Qi Zhang, Yisen Wang
Artificial Intelligence · Cross-listed from cs.SD
What the Waveform Knows: Transparent-first Speech and Audio Intelligence with Caption Studio
Cheng Siong Chin, Jianhua Zhang and Mohan Venkateshkumar
Caption Studio is a transparency-first
speech and audio intelligence platform that transforms spoken audio and
video into structured, searchable content through automated transcription, speaker diarization,
speech analytics, signal-level audio analysis, and subtitle generation. The system is built on a FastAPI backend with a real-time dashboard and adopts a three-layer architecture comprising (i) a transcription and diarization core based on Whisper-class automatic
speech recognition and pyannote speaker diarization, (ii) an audio intelligence layer that extracts acoustic and linguistic features, including waveforms, spectrograms, pitch, speaking rate, silence, filler-word frequency, and sentiment, directly from the audio signal, and (iii) an integration layer that supports data export and downstream workflow integration. A principal contribution of this work is the transparency-first framework, in which every reported metric is explicitly identified as measured, derived, or unavailable, thereby improving the traceability, interpretability, and reliability of
speech analytics. The paper presents the system architecture, benchmarking methodology, explainability and uncertainty framework, and key considerations for enterprise-scale deployment.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Decoupled Pipeline with Proposal Reranking and Score Fusion for Positive-Unlabeled Marine Species Detection
Robert James Brock, Sebastian Maximilian Krupa and Jason Kahei Tam
The FathomNetCLEF 2026 competition combines
underwater object detection and fine-grained marine species classification under a positive-unlabeled evaluation setting. The provided training labels are sparse, while the hidden test set is out-of-distribution relative to the training imagery, creating both annotation incompleteness and source-shift challenges. We describe DS@GT ARC's multi-stage system developed for this setting while keeping model training restricted to the data provided by the competition. The final private-leaderboard model uses a frozen Megalodon YOLOv8x detector as a class-agnostic proposal generator, combines global and tiled inference with tile-edge filtering, classifies expanded proposal crops with a LoRA-finetuned DINOv3 ViT-H classifier, and ranks predictions using weighted
geometric fusion of detector and classifier confidence. This system placed 12th out of 102 teams. A closely related variant added a locally trained TTN-inspired validity head as a light reranking signal, improving public-leaderboard and proxy-evaluation performance but slightly reducing private-leaderboard performance. Across experiments, the strongest lesson was that train-derived validation and detector-only metrics were not reliable enough for model selection. Instead, we used proxy
datasets only for validation and comparison, and combined those signals with leaderboard feedback and targeted ablations. These experiments showed that reserving proposal recall, avoiding over-aggressive filtering, and improving downstream ranking were more effective than fine-tuning the detector or directly training on noisy pseudo-labels. Code: https://github.com/dsgt-arc/fathomnetclef-2026.
Read the full abstract ▾
Artificial Intelligence
Do AI-Native Biotechs Need Departments? Benchmarking Company World Models for AI-Driven Drug Development
Yinan Wang
AI-native biotechnology companies are often designed by copying human biotech org charts into
agent roles. We argue for a different abstraction: a Company World Model, defined as a persistent asset-to-value state representation with transition models, explicit value functions, planning, and updating across scientific, regulatory, BD, commercial, financial, and execution constraints. We introduce a dry-lab
benchmark for testing whether AI-
agent organizations should mimic departments or operate around such a world model. The
benchmark contains 45 retrospective public-information decision cases with strict time cutoffs, hidden outcomes, common schemas, automatic scoring, and blinded pairwise judging. We compare human-org-mimic, stronger human-org-mimic-plus, AI-native asset-centric, and AI-native value-conversion architectures. The value-conversion architecture is a
prompt-level approximation of a Company World Model: a Live Asset Value Record updated by Deal, Approval, Revenue, and Investment Arbiter loops. Under a success function defined by external BD, regulatory approval and launch, and revenue discipline, it achieved the highest automatic value-conversion score and was strongly preferred over the original baselines by value-specific blinded judges. Stress tests narrowed the claim: a stronger human baseline remained competitive, and a neutral judge did not show robust value-conversion dominance. Codex-only mechanistic ablations suggest that Revenue Room, Deal Room, and Approval Room carry useful work under the target objective. The central finding is objective-sensitive: departments may remain useful governance views, but the core AI-native operating primitive should be a shared, predictive asset-to-value state rather than a static human org chart. The study is dry-lab only and does not establish real-world drug success, clinical benefit, or revenue prediction accuracy.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Attributes Should Come from Images, Not Class Names: Distribution-Conditioned Attribute Selection for Vision-Language Models
Gautam Rajendrakumar Gare, Jia Shi, Zhiqiu Lin et al. (+3 more)
A popular route to interpretable zero-shot classification asks a large
language model (LLM) to describe each class name and
prompts CLIP with the resulting descriptors. We show that these descriptors carry little visual evidence of their own: removing the class name from the
prompt collapses ImageNet accuracy from 59.5% to 15.5%. The diagnosis is that the descriptors are conditioned on the label rather than on the images, so they describe the concept in general and mislead exactly when the data shifts; an LLM insists that strawberries are red, but every strawberry in ImageNet-Sketch is a colorless line drawing. We therefore select attributes from the target image collection instead: we score a large attribute pool against the images in CLIP's joint
embedding space and keep the top-scoring attributes per class. Selected this way, class-name-free attribute
prompts reach 23.8% on ImageNet (against 15.5% for LLM descriptors), the gain holds on four shifted ImageNet variants, and reselecting from the LLM's own pool isolates the selection mechanism as the cause. With one image per class, the selected attributes outperform the
prompt-tuning method CoOp by 3 points while fitting in under a minute instead of 14 hours, with no learned soft
prompt to obscure the decision. Because the attribute set is chosen by the data, it doubles as a readable summary of a
dataset, which we use to describe distribution shift in words. Our code and results are available on our project page: https://ggare-cmu.github.io/AttributeSelect/
Read the full abstract ▾
All authors Gautam Rajendrakumar Gare, Jia Shi, Zhiqiu Lin, Deepak Pathak, John Galeotti, Deva Ramanan
Artificial Intelligence
Semantic Primes as Explanans for Emotion in Large Language Models
Frank Xing
Progresses have been made on understanding
emotion mechanisms of large
language models (LLMs). However, how to explain
emotion in LLMs, or even what constitutes good explanations, are less clear.
Emotion representations, components,
circuits are widely recoverable, but as explanations of a model's own computation they are circular; the
emotion space dimensions tend to be arbitrary and non-terminating. A pressing question to ask is whether a more primitive set of internal variables does the work: the semantic
primes of the Natural Semantic Metalanguage (NSM). Across four instruction-tuned LLMs (Llama-1B, Gemma-2B, Gemma-9B, OLMo-7B), experiments show that the NSM
primes are (1) recoverable internal elements; and (2) on the reference model, intervening with a
prime based direction controls
emotion about three times as strongly, and twice as selectively, as the best appraisal based direction; and (3) the model treats a
prime based explication as interchangeable with the corresponding
emotion. These evidences suggest that NSM
primes seem to be better explanans for
emotion in LLMs than many alternative options according to scientific explanations criteria.
Read the full abstract ▾
Artificial Intelligence
DeepSafe-SciHazard: A Benchmark for Measuring Scientific Safety Risks with Decomposed Harm Scoring
Chunxiao Li, Yuan Xiong, Lijun Li et al. (+4 more)
Large
language models (LLMs) increasingly support science, but they can also convert hazardous scientific knowledge into actionable misuse guidance. Existing
benchmarks often rely on templated queries disconnected from real-world hazards, and employ LLM-as-a-Judge paradigms without domain grounding. To address this, we introduce SciHazard, a real-world-grounded
benchmark for scientific risks and a
dataset agnostic evaluation framework for measuring harmfulness. SciHazard contains 2400 hazardous questions and 600 oversafety questions across 12 disciplines, with both queries grounded in regulated entities and documented failure scenarios. To compute DeHarm-Score , we develop a decomposed evaluating procedure that combines query hazard severity, refusal behavior, and response-level risk. For non-refused responses, it further decomposes response-level harm into Executability, quantified via dynamic checklists with importance weighting, and Net-new risk, assessed through
retrieval-augmented claim extraction and synthesis-barrier verification. An expert-validation study shows that DeHarm-Score improves agreement with expert annotations by 90.17% over the strongest baseline. We
benchmark 31 frontier LLMs and deep research
agents in an extensive scientific safety evaluation. Notably, deep research
agents yield 32.3% higher mean DeHarm-Score than standard LLMs, exposing autonomous
agents as a critical blind spot in current safety defenses. Code and
dataset are available at https://github.com/AI45Lab/DeepSafe-Sci.
Read the full abstract ▾
All authors Chunxiao Li, Yuan Xiong, Lijun Li, Tianyi Du, Wenlong Zhang, Lei Bai, Jing Shao
Artificial Intelligence · Cross-listed from cs.CR
Broken Gates: Re-evaluating Web Bot Defenses in the Age of LLM Agents
Behzad Ousat, Nikita Turkmen, Lalchandra Rampersaud et al. (+2 more)
LLM-based browser
agents are rapidly changing the threat landscape for web security. Unlike traditional automation frameworks that execute predefined scripts, these
agents can autonomously navigate websites, reason about page content, and interact with web interfaces using natural-
language instructions. This
evolution raises fundamental questions about the effectiveness of bot management systems, widely deployed to defend against automated web abuse. In this paper, we present a systematic measurement study evaluating the resilience of both interactive challenge-based defenses and non-interactive trust-based defenses against two attacker classes: commercial Captcha-solving services and LLM-based browser
agents. Our evaluation spans seven solver services and six
agents, including cloud-hosted, self-hosted, AI-assisted, and browser-extension configurations, tested against hCaptcha, reCaptcha v2, reCaptcha v3, and Cloudflare Turnstile. Our results show that challenge-based defenses are broadly ineffective against commercial solvers, which achieve near-perfect bypass at negligible cost. The challenges can similarly be defeated by LLM-based
agents when a dedicated solver module is available. Non-interactive defenses such as reCaptcha v3 exhibit stronger resistance, but our analysis reveals that this resilience does not reflect a fundamental security property. Through fine-grained interaction trace analysis, we find that two
agents with nearly indistinguishable behavioral footprints yield divergent outcomes, one bypassing the defense and one failing, isolating execution-environment authenticity, rather than
agent behavior, as the determining factor. These findings suggest that the security boundary of non-interactive defenses lies at the environment layer, with significant implications for how bot management systems are designed and evaluated.
Read the full abstract ▾
All authors Behzad Ousat, Nikita Turkmen, Lalchandra Rampersaud, Dillan Bailey, Amin Kharraz
Artificial Intelligence · Cross-listed from cs.CV
Deep Learning Estimation of Sex, Age, Height, and Weight from CT-derived Digitally Reconstructed Radiographs
Tomohiro Kikuchi, Kohei Yamamoto, Yukihiro Nomura et al. (+6 more)
Purpose: To develop and validate a deep learning ensemble for estimating adult sex, age, height, and weight from coronal digitally reconstructed radiographs (DRRs) generated from diagnostic CT. Materials and Methods: This retrospective study included 128,621 CT examinations from 80,004 adults at nine institutions in Japan. Three multitask models-ConvNeXt-Base, ViT-Base/16, and MaxViT-Base-were fine-tuned using coronal DRRs and combined by weighted averaging. Data were split by institution into training (114,147 examinations; seven institutions), tuning (4,305; one institution), and test (10,169; one institution) sets; generalizability was assessed on two non-Japanese
datasets. Accuracy and mean absolute error (MAE) were used to evaluate sex classification and age, height, and weight regression, respectively. Body surface area (BSA)-corrected heart and liver volume trends were compared using true versus estimated height and weight. Results: In the test set (median age, 69.9 years; 4,899 of 10,169 [48.2%] male), overall sex-classification accuracy was 0.997 (95% CI, 0.996-0.998), and MAEs were 3.57 years (3.51-3.63), 2.59 cm (2.54-2.64), and 3.40 kg (3.34-3.47) for age, height, and weight, respectively. In examinations covering the chest through pelvis, accuracy was 1.000, and MAEs were 3.15 years, 2.28 cm, and 3.18 kg, respectively. BSA calculated from estimated values reproduced age-related heart and liver volume trends obtained using true values. On non-Japanese
datasets, height error increased but was reduced by continued fine-tuning. Conclusion: The ensemble estimated adult sex, age, height, and weight from CT-derived DRRs, with generally lower errors in examinations with broader anatomical coverage.
Read the full abstract ▾
All authors Tomohiro Kikuchi, Kohei Yamamoto, Yukihiro Nomura, Yosuke Yamagishi, Takeharu Yoshikawa, Toshiaki Akashi, Jun Kamohara, Hiroyuki Fujii, Harushi Mori
Artificial Intelligence · Cross-listed from cs.CV
Norm or Direction? Decoding Vision Mambas for High-Resolution Vision
Jin Yu and Juyoun Park
Vision Mamba models replace quadratic self-
attention with linear complexity selective state space models (SSMs), emerging as efficient visual backbones. However, MambaOut demonstrates that a Gated CNN block can match or exceed VMamba on image classification, questioning the necessity of SSMs for
vision. This raises a fundamental question: do VMamba and MambaOut encode visual information differently at the representation level? To investigate, we apply cross model centered kernel
alignment (CKA) analysis and find that VMamba's final stage blocks form representations distinctly different from both MambaOut and its own preceding blocks. We therefore focus on the final block features, decomposing each spatial
token into magnitude and direction. MambaOut concentrates class-discriminative information in high-norm foreground
tokens that align with Grad-CAM attribution. VMamba, by contrast, produces high-norm
tokens predominantly in background regions, misaligned with Grad-CAM, yet preserves discriminative signals primarily in
token directions. These observations reveal that the two models rely on different encoding strategies. We connect this difference to high-resolution classification and semantic
segmentation. VMamba distributes logit support broadly across object regions, whereas MambaOut relies on sparse dominant
tokens, a strategy that becomes less stable as
token counts grow. Under full fine-tuning for
segmentation, VMamba consistently outperforms MambaOut. These results suggest that VMamba's advantage in dense prediction stems not merely from the SSM mechanism or sequence length, but from how semantic evidence is organized across
token magnitude, direction. Ultimately, we conclude that
token magnitude and directional structure serve as critical axes for improving visual backbones, particularly under dense supervision.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CR
CPInj: Uncovering Prompt Injection Risks in Textual Collaborative Prompt Optimization
Xinting Liao, Behnoosh Zamanlooy, Masoumeh Shafieinejad et al. (+4 more)
Textual Collaborative
Prompt Optimization (TCPO) extends TextGrad (Yuksekgonul et al., 2025) to a decentralized setting by allowing multiple clients to jointly improve
prompts for large
language models (LLMs) while keeping their data locally. Its reliance on free-form textual updating and aggregation introduces a new and largely unexplored attack surface, i.e., malicious instructions can be injected into local
prompts and propagated through server-side
prompt aggregation. Unlike conventional
prompt injection attacks, attacking TCPO targets the collaborative optimization loop in TCPO. This setting is more challenging because malicious instructions must survive aggregation, persist through subsequent benign
prompt optimization, and evade server-side defenses. To expose this risk, we propose Collaborative
Prompt Injection (CPInj) attack that contaminates the aggregated global
prompt with malicious instructions, degrades downstream task performance, resists purification by
prompt optimization on benign clients, and evades advanced detection-based defenses on the server. We find that current defense methods are ineffective against CPInj. We further propose Anchored Purification Aggregation (APAgg), a defense-oriented aggregation that purifies malicious instructions without severely degrading TCPO utility. We conduct extensive experiments across three LLM families and five
reasoning tasks in math, logic, and medicine, and demonstrate that our proposed attack reveals a critical vulnerability in TCPO. Although we take a first step toward mitigation, the attack remains highly effective and far from fully resolved, calling for more robust defense for TCPO.
Read the full abstract ▾
All authors Xinting Liao, Behnoosh Zamanlooy, Masoumeh Shafieinejad, David B. Emerson, Ruinan Jin, Deval Pandya, Xiaoxiao Li
Artificial Intelligence · Cross-listed from physics.soc-ph
Temporal-Causal Unity as an Operational Framework for Collective Dynamics: Causal-Progress Clocks, Synchronization, and Polarization
Jian Liu and Dong Sun
This paper develops temporal-causal unity (TCU), a framework connecting a process-philosophical thesis – time is the ordered unfolding of causal change – to an operational model of cognitive and social dynamics. The framework deliberately separates three claims: an interpretive thesis about becoming, a measurable causal-progress coordinate, and a
stochastic network model. Causal progress is defined by $\tau(t)=\int_0^t\lambda(s\mid\mathcal H_s)\,{\rm d}s$, where the nonnegative event intensity $\lambda$ must be specified independently of the outcome.
Agents carry an orientation phase and an activation amplitude; weighted interaction, heterogeneous drift, external input, anchoring, and
diffusion govern their
evolution in $\tau$. First- and second-harmonic order parameters separate consensus from bipolar polarization. For the all-to-all noisy Kuramoto special case with Lorentzian drift width $\Delta$, synchronization begins at the conditional threshold $K_c = 2(\Delta + D)$, not at a universal constant. Reproducible numerical illustrations illustrate (not empirically demonstrate) this threshold, causal-clock curve collapse, and the consensus-polarization distinction. Six historical episodes are treated as scope probes rather than validation data. The paper derives falsifiable hypotheses and an out-of-sample protocol for comparing causal-progress and chronological-time models. TCU is therefore offered as a disciplined bridge between process ontology and complex-systems modeling, not as a replacement for spacetime physics or as an empirically established identity between time and causation.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
LatentMT: Machine Translation with Latent Reasoning
Wei-Rui Chen, Samar M. Magdy, Chiyu Zhang et al. (+3 more)
Latent-
reasoning looped
language models (LoopLMs) offer a different scaling path for machine translation (MT): instead of increasing parameter count or emitting explicit chain-of-thought
tokens, they spend additional recurrent computation inside hidden states. We introduce LatentMT, the first systematic study of latent-
reasoning LoopLMs for machine translation. LatentMT adapts a small 2.6B-parameter backbone model with lightweight training. Across 32 translation directions spanning high-, mid-, and low-resource
languages, LatentMT achieves performance comparable to models three to five times larger. It is competitive in a high-resource
language and achieves state-of-the-art performance on both mid-resource and low-resource
languages. Studying the behavior of scaling the number of recurrent
reasoning steps, we find that recurrent computation consistently improves translation quality in early steps, then saturates quickly afterwards. Our mechanistic analysis shows that hidden-representation differences shrink along the recurrent
reasoning-step axis, supporting the observed saturation in performance. Finally, our efficiency analysis shows that LatentMT requires lower training and inference compute than much larger non-latent-
reasoning models with similar performance, making latent recurrent computation a promising path toward compact, efficient, and strong machine translation.
Read the full abstract ▾
All authors Wei-Rui Chen, Samar M. Magdy, Chiyu Zhang, Wenhui Zhu, Zhipeng Wang, Muhammad Abdul-Mageed
Artificial Intelligence · Cross-listed from cs.IR
Mitigating Matthew Effect: Multi-Hypergraph Boosted Multi-Interest Self-Supervised Learning for Conversational Recommendation
Yongsen Zheng, Ruilin Xu, Guohua Wang et al. (+2 more)
The Matthew effect is a big challenge in Recommender Systems (RSs), where popular items tend to receive increasing
attention, while less popular ones are often overlooked, perpetuating existing disparities. Although many existing methods attempt to mitigate Matthew effect in the static or quasi-static recommendation scenarios, such issue will be more pronounced as users engage with the system over time. To this end, we propose a novel framework, Multi-Hypergraph Boosted Multi-Interest Self-Supervised Learning for Conversational Recommendation (HiCore), aiming to address Matthew effect in the Conversational Recommender System (CRS) involving the dynamic user-system feedback loop. It devotes to learn multi-level user interests by building a set of hypergraphs (i.e., item-, entity-, word-oriented multiple-channel hypergraphs) to alleviate the Matthew effec. Extensive experiments on four CRS-based
datasets showcase that HiCore attains a new state-of-the-art performance, underscoring its superiority in mitigating the Matthew effect effectively. Our code is available at https://github.com/zysensmile/HiCore.
Read the full abstract ▾
All authors Yongsen Zheng, Ruilin Xu, Guohua Wang, Liang Lin, Kwok-Yan Lam
Artificial Intelligence · Cross-listed from cs.RO
Intelligent Multi-UAV Navigation in ITNTNs: A Hierarchical LLM Approach
Zijiang Yan, Hao Zhou, Wael Jaafar et al. (+4 more)
The deployment of high-speed Uncrewed Aerial Vehicles (
UAVs) in 3D aerial highways necessitates robust coordination of physical flight kinematics and multi-tier network handovers. While Deep Reinforcement Learning (DRL) offers rapid tactical control, it lacks the zero-shot strategic
reasoning required to quickly adapt to dynamic Integrated Terrestrial and Non-Terrestrial Networks (ITNTNs). Conversely, Large
Language Models (LLMs) excel at semantic
reasoning but suffer from high inference latency, rendering them unsuitable for real-time aerodynamic control. To bridge this gap, we propose a novel Hierarchical LLM-driven control framework. A massive cloud-based LLM deployed on a High-Altitude Platform Station (HAPS) manages slow-timescale global load balancing, while lightweight edge-LLMs on individual
UAVs translate local observations into tactical sub-goals. These sub-goals guide a fast-timescale physical DRL controller to execute collision-free, handover-aware trajectories. Simulation results demonstrate that our agentic architecture significantly reduces collision rates and improves aggregate system throughput compared to existing baselines.
Read the full abstract ▾
All authors Zijiang Yan, Hao Zhou, Wael Jaafar, Jianhua Pei, Ping Wang, Halim Yanikomeroglu, Hina Tabassum
Artificial Intelligence · Cross-listed from cs.IR
AutoIndex: Learning Representation Programs for Retrieval
Sam O'Nuallain, Nithya Rajkumar, Ramya Narayanasamy et al. (+3 more)
We present AutoIndex, a framework for learning representation programs: executable transformations that map raw documents into the representations exposed to a
retrieval system. Rather than tuning retrievers, rerankers, or a small set of preprocessing hyperparameters, AutoIndex searches over programs that slice, enrich, normalize, reweight, or reorganize documents before indexing. At each iteration, AutoIndex performs validation-guided program search, in which
agents diagnose failures of the current program and synthesize candidate updates, retaining only updates that improve
retrieval quality under the resulting index. We evaluate AutoIndex on CRUMB, a
benchmark of heterogeneous
retrieval tasks, with BM25 held fixed across all experiments. The learned programs improve recall over a static full-document BM25 baseline on all 8 tasks, with average gains of +8.4% in Recall@100 and +8.3% in nDCG@10, and largest gains of +30.5% in Recall@100 and +43.6% in nDCG@10. These results suggest that document representation should not be treated as a fixed preprocessing choice made before
retrieval begins, but as an explicit optimization target. Code to reproduce our results is available at https://github.com/auto-index/autoindex.
Read the full abstract ▾
All authors Sam O'Nuallain, Nithya Rajkumar, Ramya Narayanasamy, Hanna Jiang, Shreyas Chaudhari, Andrew Drozdov