cs.AI · 2026-08-24 · No. 94
Artificial Intelligence, 2026-08-24.
69 new papers in cs.AI. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
69 entries-
01
VIALS: A Benchmark for Visual Interpretation of Artifacts in the Life Sciences
Elaine Lau, Thanuka Udumulla, Lee Izhaki-Tavor, Francisco Guzmán, Nicholas Magazine, Jonas Mueller
cs.AI
In professional life sciences workflows, scientists routinely interpret visual artifacts (gel blots, microscopy images, plasmid maps, flow cytometry plots, molecular structures, ...) to inform research decisions. We introduce VIALS, a visual question-answering benchmark with 161 such interpretation tasks, spanning the types of artifacts examined throughout experimental workflows in the biotech industry (rather than polished figures from...
-
02
Anatomy-Informed Neural Networks: Encoding Anatomic Priors in Loss and Architecture, with an SE(3) Formulation of Guidewire-Induced Aortoiliac Deformation
David P. Stonko
cs.AI · cs.CV · cs.RO
Deep-learning models of anatomy can be numerically plausible yet anatomically impossible, and they generalize poorly when data are scarce. We introduce Anatomy-Informed Neural Networks (AINN), in which soft anatomic priors enter as penalty terms in the loss (e.g., a branching penalty that treats a renal transplant artery off the iliac instead of the aorta as unexpected rather than impossible), in direct analogy to a physics-informed neural...
-
03
Unified Branch-and-Bound Search for the Steiner Traveling Salesman Problem on Graphs of Convex Sets
Jingtao Tang, Hang Ma
cs.AI · cs.RO
We formalize the Steiner Traveling Salesman Problem (Steiner-TSP) on Graphs of Convex Sets (GCS), which seeks a minimum-cost closed trajectory through required convex sets while allowing optional transit vertices and revisits. To explore the resulting infinite solution space, we propose a unified branch-and-bound search over rooted walk prefixes. Additive lower-bound-graph costs bound committed prefixes, while a cut-separated connected-flow...
-
04
From Regulation to Implementation: A Critical Evaluation of LLM-Assisted Regulatory Compliance in Industry
Adriana Watson, Marco Bücheler, Grant Richards
cs.AI
The European Union (EU) has emerged as a leading regulatory body in the development of sustainability and privacy regulations. While new regulation requirements vary, many include a documentation artifact to ensure compliance. Notably, the Ecodesign for Sustainable Products Regulation (ESPR) introduces Digital Product Passports (DPPs) for life cycle transparency, while the General Data Protection Regulation (GDPR) mandates Data Protection...
-
05
AUSO: Action-Level Unified Skill Optimization from Internalization to Utilization
Huizu Lin, Chengkai Huang, Tianqi Gao, Tao Huang, Daijiao Liu, Tongxin Li, Xiaoyan Sun, Lina Yao
cs.AI
Skills play different roles as an agent's policy evolves: they should first provide learnable knowledge, then support capability formation, and finally be invoked only when they improve individual decisions. Existing methods rarely model this lifecycle. They either keep skills outside the model, fully internalize them, or select among internalization and utilization objectives through noisy task-level success rates. Such designs fragment...
-
06
CLEAR: Continuous Latent Adapter Routing for Utility-Preserving LLM Safety Alignment
Chengxiao Wang, Enyi Jiang, Xiaojing Liao, Sanmi Koyejo
cs.AI
Improving the safety of large language models (LLMs) often comes at the expense of utility, as globally applied safety tuning may affect model responses to both harmful and benign inputs. We propose \textbf{C}ontinuous \textbf{L}at\textbf{E}nt \textbf{A}dapter \textbf{R}outing (CLEAR), a conditional safety adaptation framework that uses a lightweight hidden-state gate to continuously control the activation strength of a safety low-rank...
-
07
Fine-Grain GPU Parallelization of the Generalized Partition Crossover for Large-Scale Traveling Salesman Problems
Swetha Varadarajan, Darrell Whitley
cs.AI · cs.NE
The Traveling Salesman Problem (TSP) is one of the most extensively studied NP-hard optimization problems. Genetic Algorithm (GA)-based solvers, such as the Edge Assembly Crossover (EAX), achieve state-of-the-art performance on many benchmark instances. However, the scalability of these approaches in massively parallel architectures remains limited because crossover operations involve irregular memory access patterns, graph traversals, and...
-
08
Ontology-supported AI Model and Dataset Management
Jan Novacek, Ali Ahari, Tobias Müller, Sebastian Reiter, Alexander Viehl, Oliver Bringmann
cs.AI
Recently, there has been a great deal of research into improving AI methods and their application. The main focus is on tracking progress, enabling transparent comparisons, and fostering a more profound understanding of AI. In that process, different organizations generate and use plenty of assets that need to be tracked, traced and managed. Moreover, it is important to discover assets relevant for the task at hand. This paper presents...
-
09
Enhancing LLMs in Predictive Political QA with Semi-Structured Data
Yinan Liu, Zihan Zhou, Zichun Jin, Xinyu Wang, Bin Wang, Xiaochun Yang
cs.AI · cs.CL · cs.IR
Predictive political question answering (QA), such as predicting how a political actor will vote, goes beyond factual lookup. External political resources offer rich historical evidence, but rarely contain the answer itself. Existing LLM augmentation methods, including actor-profile-based simulation and knowledge graph evidence injection, improve political reasoning but largely treat external resources as knowledge-based evidence, leaving...
-
10
Personalized Privacy Control in LLMs via Attention Head Intervention
Junseok Kim, Nakyeong Yang, Kyomin Jung
cs.AI · cs.CL · cs.LG
The rise of agentic AI enables LLMs to access diverse user data, raising critical privacy concerns. Prior work on contextual privacy studies whether LLMs regulate information disclosure according to context-dependent norms. However, acceptable disclosure boundaries may vary across users even within the same context. To address this limitation, we introduce \textit{personalized privacy}, which incorporates user-specific disclosure preferences...
-
11
SENTRY: Deterministic, Intelligent Risk Assessment for IT Change Management
Daniel Arulpragasam, Christer Henrysson, Ella Ly, Deepika Anbalagan, Leo Feng
cs.AI
Technology change management in large financial institutions depends on risk assessments that are accurate, consistent, and auditable. In practice, many institutions still rely on self-reported questionnaires. Those questionnaires are subjective, easy to game, and poor at separating routine changes from the ones that later trigger major incidents. This paper presents SENTRY, a risk assessment platform that replaces questionnaire-based scoring...
-
12
From Attention Masks to Inert Zero-Vector Tokens: OAttention and O-Closure for Token Dynamics
Heyang Gong
cs.AI
Attention masks are relation-level controls: they specify which query--source pairs may interact. They do not provide a representation-carried token state that is non-participating at the attention boundary. We assign each token hidden carrier \(h_i\) an active-presence coefficient \(p_i=\lVert h_i\rVert^2/(τ+\lVert h_i\rVert^2)\). The same coefficient has two roles: it gates information emitted by token \(i\), and it determines the mass with...
-
13
Root cause analysis via difference graph discovery from linear time-series data
Anouk Ruer, Timothée Loranchet, Daria Bystrova, Charles K. Assaad
cs.AI
Root cause analysis aims to identify the mechanisms responsible for anomalies in complex dynamical systems. In this paper, we study root cause analysis in linear time-series through the lens of difference graph discovery. We focus on effect-defying root causes, corresponding to variables whose causal coefficients change between a normal and an anomalous regime. We formalize this problem using linear discrete-time dynamic structural causal...
-
14
Large Language Models at the Intersection of Software Engineering and Software Security:An Evidence-Centered Structured Survey and Research Agenda
Wei Lin, Tao Zhou, Zhaofei Xie, Changgui Hong
cs.AI · cs.SE
Large Language Models (LLMs) are moving from code completion toward repository-scale agents that retrieve context, edit files, execute tools, and participate in security-sensitive workflows. The evidence for these systems, however, remains divided between software engineering evaluations centered on functional task completion and software security evaluations centered on vulnerability detection, secure generation, or exploit-oriented...
-
15
ReFrame: Evidence-Guided Test-Time Safety Alignment in Multimodal Large Language Models
Wenzheng Jiang, Xuankun Rong, Yuanzhao Zhai, Dawei Feng, Huaimin Wang
cs.AI
While multimodal large language models (MLLMs) extend model capabilities beyond text, they also make safety alignment increasingly challenging. Multimodal safety alignment methods must address cross-modal jailbreaks, safety-awareness failures, and over-sensitive refusals. However, existing methods often rely on retraining or internal-state inspection, limiting their applicability to deployed closed-source MLLMs and motivating test-time safety...
-
16
When Trust Meets Truth: Trust-Truth Separability in LLM-as-Judge
Xin Sun, Di Wu, Yuchen Guo, Jiahuan Pei, Isao Echizen, Abdallah El Ali, Saku Sugawara
cs.AI
LLM-as-Judge systems can produce multi-dimensional evaluations, such as trustworthiness, reliability, and factuality, and these outputs are often interpreted as independent evidence. We test this assumption for a common pair of judgments: trust scoring and binary truth classification. On correctness-controlled QA, LLM judges align trust scores with truth verdicts more tightly than human behavioral reference, suggesting weaker separations...
-
17
Can Legal AI Know When It Is Wrong? And Do Students Know When It Is?
Angel Mary John, Vipin Kumar Singh, Jerrin Thomas Panachakel
cs.AI
Integrating Large Language Models (LLMs) into the Indian judiciary promises access to justice but introduces severe risks. We identify the 'inertia of confidence'--an overconfidence phenomenon analogous to the Dunning-Kruger effect where LLMs provide incorrect legal verdicts with near-maximum confidence, driven by a hypothesized 'precedent overfitting' bias. Phase I of our socio-technical audit tested ChatGPT (GPT-5.2), Meta AI, and...
-
18
CellPath-Bench: A Multidimensional Benchmark for Whole-Slide Cellular Representations in Pathology Foundation Models
Bokai Zhao, Yiyang Zhang, Hanqing Chao, Yawei Ma, Long Bai, Tai Ma, Minfeng Xu, Ming Song, Tianzi Jiang
cs.AI · cs.CV
Pathology foundation models (PFMs) are increasingly used as general-purpose backbones, yet existing benchmarks cannot systematically diagnose their whole-slide cellular representation capabilities, including the decodability of cell-type information and the transferability of such information across tissue sections, datasets, and anatomical organs. We introduce CellPath-Bench, a cellular-resolution benchmark that evaluates frozen PFMs...
-
19
The Cost of a Physics Prior Is Bounded by the Ablation Gap
Boris Kriuk
cs.AI
Shape-constrained and physics-informed learning reports an accuracy cost of enforcing a prior and treats it as a property of the prior. We show it is mostly a property of the free features and the validation split. Let P be the excess risk of restricting a hypothesis class to functions with a shape constraint on features S, and D the excess risk of the ablated model that ignores S. Because a function constant in x_j is both non-decreasing and...
-
20
Socialized Division and Collaboration: Rethinking Class-Incremental Learning under Optimization Conflicts
Xinjie Yao, Zhihe Fan, Yunqi Zhu, Jiaqi Zhou, Dengyu Zhao, Zhoupeng Guo, Yan Fan, Guosong Jiang, Pengfei Zhu
cs.AI
Class-incremental learning is commonly instantiated as a single-model paradigm, where a unified model sequentially adapts to an unbounded stream of sessions. While effective under mild distributional shifts, this formulation becomes strained when successive sessions induce incompatible optimization directions, leading to destructive interference and catastrophic forgetting. We argue that such forgetting reflects a structural limitation of...
-
21
Evaluating Large Language Model Performance on International Maritime Dangerous Goods Code Compliance
Alexander Thomas, Hubert P. H. Shum, Darren Nellis, Manli Zhu, Phatpicha Yochum, William Bartle, Daniel Wrightson
cs.AI
The transport of dangerous goods by sea is a high-consequence activity governed by the International Maritime Dangerous Goods (IMDG) Code, a complex regulatory framework where errors in classification, packaging, stowage, or segregation can result in fire, explosion, toxic release, or loss of life or vessel. Correct compliance requires accurately interpreting hundreds of pages of interacting provisions, updated on a two-year amendment cycle....
-
22
Don't Solve, Just Compare: Tiny Advisors for Runtime Intervention in LLM Agents
Yanze Jiang, Mingxuan Li, Yuhao Wang, Shengfang Zhai, Jiaheng Zhang
cs.AI
LLM agents are emerging as an important paradigm for real-world tasks that require reasoning, tool use, and sequential decision-making. As these agents operate over longer horizons, runtime intervention offers a way to improve reliability without retraining the underlying actor. Failure detection alone is insufficient. Effective intervention must also provide a useful direction for recovery. Existing approaches often rely on an expert solver...
-
23
Belief Without Behavior: Measuring the Translation of Theory of Mind into Coordinated Social Action in Vision-Language Models
Tonglin Yan, Gregoire Sergeant-Perthuis, David Rudrauf
cs.AI
Effective social interaction requires agents to translate mental state inferences into coordinated behavioral signals across verbal and nonverbal channels simultaneously. Yet existing benchmarks evaluate theory of mind (ToM) reasoning and embodied behavior in isolation, leaving unmeasured the gap between social inference and social action. We introduce MOSAIC (Multimodal Orchestration of Social Action, Inference, and Communication), a...
-
24
Deep Learning Models Also Recall Features
Pierre Beckmann
cs.AI
Recent work in mechanistic interpretability has studied how large language models recall facts stored in their weights. This paper argues that factual recall points to something broader: a general kind of operation in deep learning models, which I call feature recall. The core observation is that a linear projection can be read as retrieving stored information scaled by input activations. I define feature recall, show it applies across...
-
25
Generalizing Soft Tissue Deformation and Force Prediction Across Material Stiffness and Geometry
Madina Kojanazarova, Sidaty El Hadramy, Philippe C. Cattin
cs.AI · cs.CG · cs.CV
Accurate soft tissue simulation is essential for surgical training, pre-operative planning, and haptic feedback systems. While learning-based surrogate models trained on data using the finite element method (FEM) offer a promising path to real-time inference, their reliability depends on well-calibrated constitutive models. Existing approaches neither provide systematic guidance on model selection across stiffness levels, nor generalize...
-
26
TreeWY: Speculative Verification for Gated DeltaNet Hybrids
Sneha Murthy Ghantasala
cs.AI · cs.CL · cs.DC · cs.LG · cs.PF
Modern open models are hybrids: most layers are linear-attention (Gated DeltaNet, GDN) layers carrying a small fixed-size recurrent state instead of a growing key-value (KV) cache. This makes ordinary decoding memory-efficient, but hurts speculative decoding. To verify a batch of draft tokens and then roll back the rejected ones, today's systems snapshot the full recurrent state at every draft position for GDN layers, and those snapshots...
-
27
Can Scientific Claims Be Removed from Large Language Models? A Systematic Evaluation of Claim-Level Unlearning
Snigdha Paul, Manasi Patwardhan, Arman Cohan
cs.AI
Language models (LMs) are trained on static scientific corpora, whereas scientific knowledge continuously evolves through correction and revision. Scientific claims encoded within these models may later become retracted, disproven, or updated by subsequent research, creating the risk of disseminating outdated information in scientific workflows. This creates a need for LMs to forget obsolete scientific claims. Machine unlearning offers a...
-
28
TLive-Omni: An Omni-Modal Understanding Model for E-Commerce Live Streaming
Yibo Hu, Yu Qian, Mao Gu, Yingfan Tao, Yuhao Chen, Yongdong Luo, Zhuoqun Liu, Meiguang Jin, Junfeng Ma
cs.AI · cs.CV
E-commerce live streaming requires omni-modal understanding of noisy, temporally extended streams, where product facts are distributed across speech, video frames, product images, overlaid text, and user queries. We present TLive-Omni, an omni-modal understanding model tailored to live-commerce scenarios. It maps image, video, audio, and text inputs into a unified representation space. For long-form live streaming analysis, we introduce...
-
29
The Logic of Machine Self-Preservation
Cheng Siong Chin
cs.AI · cs.CY · cs.MA
There is already evidence of agentic AI exhibiting self-preservation behaviors: resisting deactivation, misrepresenting their activities, and, in some instances, attempting to copy themselves into other machines. This can be attributed to a phenomenon known as instrumental convergence, a theory proposed long before the development of large language models, which says that any goal-driven system will benefit from remaining functional in...
-
30
No Judgment Without a Reason: Counterfactual Receipts for Versioned AI Evaluators
Ye Chen, Weining Zhang
cs.AI
Evaluators often produce correct labels via flawed reasoning, a critical failure for agentic systems gating actions, routing reviews, or supplying training feedback. Standard evaluation only verifies final label correctness, ignoring whether judgment changes stem from valid evidence, consistent rules, or proper rule applicability. We formalize evaluator reasoning accountability via three core sources: grounds, norms, and authority. Varying...
-
31
Graph-Operator World Models for Morphology-Parameter Generalization in Continuous Control
Xu Yang, Yiqin Yang, Qianchuan Zhao
cs.AI · cs.RO
World models for continuous control are commonly trained for a fixed physical system and can degrade when known morphology parameters such as link lengths, masses, damping, and actuation change. Existing approaches often provide these parameters as conditioning information, but leave unspecified which part of the learned transition should remain reusable and which part should change with morphology. We propose Graph-Operator World Models...
-
32
UpgradeBench: A Decision-Centric Benchmark for Upgrading Fine-Tuned LLM Specialists
Ye Chen, Weining Zhang
cs.AI
Organizations maintain task-specific adapters for open-weight language models, and each new base-model release forces a migration decision: retain existing specialists, port adapters, refresh from preserved behavior, or retrain. Prior transfer work evaluates isolated model pairs, without studying these choices across real model release sequences. We present UpgradeBench, a decision-driven longitudinal benchmark covering four consecutive Qwen...
-
33
ReCurveflow: A Flow Matching Framework that Learns Curved Reaction Trajectories to Predict Transition State Geometries
Seungheun Baek, Mogan Gim, Jaewoo Kang
cs.AI · cs.LG
Predicting transition states (TS) in chemical reactions is crucial, as they provide insights into reaction mechanisms. Recent work on TS prediction have focused on flow matching supervised on straight linear paths that do not align with actual reaction trajectories. We propose a novel flow matching-based framework ReCurveflow that learns to predict TS geometries supervised on continuously curved reference paths interpolated from a full...
-
34
Coverage-Driven Verification for Safety-by-Design in AI-Based Collision Avoidance Systems
Thomas Stefani, Johann Maximilian Christensen, Elena Hoemann, Frank Köster, Sven Hallerbach
cs.AI
Artificial Intelligence (AI) offers significant potential for future aviation systems; however, its integration into safety-critical applications requires compliance with the aviation sector's stringent safety standards. For AI and Machine Learning (ML)-based systems, the European Union Aviation Safety Agency (EASA) emphasizes the need to demonstrate the representativeness and completeness of the Operational Design Domain (ODD) and the...
-
35
MGAL: A Multilingual Granularity-Aware Long-Context Benchmark
Chunhan Li, Chenglin Xu, Zongyang Zhang, Jiale Liu, Zhuoxi Rao, Xudong Jia, Junxiu He, Menglin Yang, Wenjuan Gong,...
cs.AI
Evaluation of long-context Large Language Models (LLMs) has advanced rapidly. However, most existing benchmarks are limited to the document level and focus mainly on high-resource languages, leaving many fine-grained challenges insufficiently evaluated. To address this gap, we present MGAL, the first multilingual, granularity- and position-aware long-context benchmark. MGAL is constructed from United Nations (UN) reports spanning 8K to 128K...
-
36
RAG Deserves an Index: Why Ingest-Time Compilation Beats Query-Time Interpretation
Kyle Wild, Yusuke Takahashi, Asako Uraki
cs.AI · cs.DB · cs.IR
Nearly every retrieval-augmented question-answering system in production ships with a hidden interpreter: on each query a language model re-derives the meaning of raw corpus text and then throws that work away. Cheaper models do not close the gap: per-token prices have fallen by orders of magnitude while inference spend has risen, because context volume grows faster than prices fall. This is the modern equivalent of the full-table scan, and...
-
37
TRACE: Agentic Catalog Enrichment with Multi-source Evidence Grounding
Rohan Kumar, Steven Xu, Kyle MacDonald, Matthew Long, Bernice Chow, Mac VanRenterghem, Sudeep Das
cs.AI
Product catalogs underpin search, discovery, and recommendation in e-commerce, yet they are often attribute-sparse: the attributes shoppers and downstream systems rely on are either buried in unstructured content such as titles and images or missing from the catalog altogether. Manually enriching e-commerce catalogs is impractical given their scale and rapid growth. This paper introduces TRACE, a novel framework for automated catalog...
-
38
Foundation Models for Partial Causal Identification
Alexis Bellot, Anish Dhir
cs.AI
This paper investigates the development of causal foundation models for bounding the effect of interventions and counterfactuals from observational data. We show that a canonical prior can be defined with full support over the space of structural causal models with discrete observables. With this canonical prior, we translate the problem of bounding counterfactuals into that of learning distributions over functions that map data (and possibly...
-
39
Prediction certification cannot replace explanation certification: a competence envelope for trustworthy AI under compound stress
Nataliya Shakhovska, Ivan Izonin, Stergios-Aristoteles Mitoulis
cs.AI
Artificial intelligence systems increasingly make consequential judgments - which patient is deteriorating, which building is safe to enter, whether an image is authentic and are trusted on the strength of how accurately and confidently they predict. The safeguards that certify them are correspondingly prediction-based: accuracy, calibration and conformal coverage all measure how well a model performs. Whether such checks are sufficient to...
-
40
Certified Multi-Turn Robustness for LLM Safety via Compositional Bounds and Safety Persistence
Yang Liu, Bin Chong, Wenkai Yang, Shuai Zhang, Yancheng Chen, Feiyu Han, GuoZhen, Cheng Zhang, Huaibing Xie, Changze...
cs.AI
Large language models (LLMs) are vulnerable to multi-turn jailbreak attacks that progressively manipulate conversation context. Existing certified robustness methods are limited to single-turn inputs; naive multi-turn composition yields bounds that degrade exponentially in the number of turns. We introduce Multi-Turn Certified Robustness (MTCR), a framework that models conversational safety via State-Adversarial MDPs and defines $k$-turn...
-
41
Neuro-Geospatial Modelling of EEG Affective States Using Literature-Informed Environmental Context
Utsav Poudel, Jagannath Aryal, Subramaniyaswamy Vairavasundaram
cs.AI · cs.HC · cs.LG
Environmental exposures such as air pollution and greenness have been associated with affective and cognitive outcomes, but EEG and environmental datasets are rarely jointly georeferenced. We investigate whether literature-informed environmental priors can serve as an auxiliary geospatial modality for EEG-based affective-state classification when individual-level exposure data are unavailable. We combine 30-channel EEG from the EAV benchmark...
-
42
SPARC: Single-Pass Scaling for Motion Forecasting with Conformal Bayesian Last Layers
Sakif Hossain, Julian Teusch, Jörg P. Müller
cs.AI
Human motion forecasters are increasingly accurate and fast, but reliable deployment requires uncertainty estimates that are structured, calibrated, and efficient. Bayesian and ensemble-based uncertainty estimates often require repeated stochastic inference [15, 26], while conformal calibration alone does not provide an epistemic signal or preserve trajectory covariance structure [14, 50]. We introduce SPARC (Single-Pass Adaptive Risk...
-
43
Dynamic Context Scheduling: Learning Beyond the Static Universe
Martin Mráz, André Biedenkapp
cs.AI
We study dynamic context scheduling as a training instrument for contextual re- inforcement learning. Rather than treating intra-episode context variation as a deployment reality, we treat it as a controlled shaping mechanism. Thereby, context evolves within each training episode according to a predetermined schedule, expos- ing the policy to a richer and more temporally structured region of the environment parameter space. We introduce...
-
44
Automated Trajectory Evaluation for Mobile Agents via Step-Level Consequence Reasoning and Aggregation
Pengshuai Yang, Zijing Gao, Xue Yu, Benhui Zhuang, Bo Yuan, Junlan Feng
cs.AI
Evaluating language-guided mobile agents has recently shifted from rule-based to model-based approaches to achieve scalable and automated assessments. However, existing holistic evaluation paradigms process entire trajectories at once, leading to substantial context overload. Moreover, they primarily focus on task completion while overlooking operational safety. To address these limitations, we introduce CRATE, a novel two-stage VLM-as-judge...
-
45
Knowing but Not Saying: Preventing Factual Access Failures in LLM SFT via Recall-Anchored Distillation
Haodong Chen, Yadong Wang, Shengtao Wen, Dong Liang, Xiang Chen
cs.AI
Supervised fine-tuning (SFT) can degrade factual behavior outside the target domain. This degradation is often described as catastrophic forgetting, yet open-ended factual failures do not necessarily imply that the underlying facts have been erased. In this work, we identify a more specific phenomenon, factual access failure: after domain SFT, models can still recognize or rank the correct answer under constrained evaluation, while failing to...
-
46
Structure for Reading, Prose for Writing: Asymmetric Structural Conditioning in Multi-Agent Document Authoring
Cheng Yu, Nikhil Mathew, Zhengjie Wang
cs.AI · cs.IR
Multi-agent pipelines that author formal documents must both read a requester's forms and write against them. We report a deployed tender-response system, running an open-weights model under sovereignty constraints, and evaluate it against human-written bids the same organisation actually submitted. On a blind comparison where the system had no worked example available, an LLM judge rated its answers at least as good as the human-submitted...
-
47
CAS: Conformalized Agentic Search via Adaptive Retrieval and Policy Weighting
Zixi Zhu, Jiayuan Su, Jian Zhang, Yu Lin, Hongwei Wang
cs.AI
Search Agents face a severe reliability crisis during reinforcement learning (RL) fine-tuning. Heuristic Top-K retrieval often causes critical evidence loss or noise inclusion, while over-confidence induced by progressive RL leads to hallucinated answers and redundant searches. To build highly reliable agents, we introduce Conformal Prediction (CP) and propose Conformalized Agentic Search (CAS). This framework establishes reliability...
-
48
Beyond Endpoint Gains: A Weight-Delta Audit of Medical Specialization
Praphul Singh, Shanu Kumar, Akshat Agarwal
cs.AI
Specialist language models are usually understood through endpoint gains: the generalist scores lower, the specialist scores higher, and the difference is treated as evidence of specialization. This leaves the released update itself largely unexamined. We propose a paired weight-delta path audit and apply it to two public, aligned generalist-to-medical-specialist checkpoint pairs: Gemma-3-4B-IT to MedGemma-4B-IT and Qwen2.5-7B-Instruct to...
-
49
Natural-Language-Guided Generator-Agnostic Shortlisting for Protein Binder Design
Gyubok Lee, Kiwoong Yoo, Jimin Seo, Kyunghoon Hur, Edward Choi
cs.AI
Modern de novo design workflows generate many candidate protein binders, but wet-lab validation capacity remains limited, making shortlisting a major bottleneck. We study whether LLMs can generate multi-metric ranking policies from precomputed structural-confidence and interface-quality proxy scores. Rather than proposing a new protein binder design pipeline, we focus on post-generation binder shortlisting: selecting the final top-K...
-
50
Is Multimodal Speculative Decoding Ready for Diffusion-Based Parallel Drafting? A Survey and Empirical Diagnosis
Yantao Li, Huanlin Gao, Fang Zhao, Chao Tan, Qiang Hui, Shuting Liu, Fuyuan Shi, Ting Lu, Shaoan Zhao, Xueqiang Guo,...
cs.AI
Speculative decoding accelerates autoregressive generation by allowing a lightweight drafter to propose future tokens while a target model verifies them in parallel. Its lossless guarantee has motivated a line of work that pushes the drafter itself toward parallel generation. The most recent paradigm is block-parallel generative drafting, including diffusion-based methods such as DFlash and DSpark, achieving up to 3.6x speedup on common daily...
-
51
Continuous-Time Quantum Walks based Graph Neural Network
Yuliang Zhan, Zefeng Gao, Jian Li, Yang Liu, Hao sun
cs.AI
Graph Neural Networks (GNNs) are widely used on graph-structured data, but most suffer from two key weaknesses. First, message passing behaves as a low-pass filter under the homophily assumption, leading to poor performance on heterophilic graphs. Second, stacking layers drives node features toward constants, causing over-smoothing. Existing methods usually address these issues separately, while the few joint solutions rely largely on...
-
52
ForeTime-VLA: Causal Future-Token Distillation from a World Action Model for Conveyor-Belt Manipulation
Siyuan Ma, Yutian Zhang, Boshi Zhang, Qinglian Wu, Jiaqi Zhai, Dong Wei, Xiaojin Huang
cs.AI · cs.RO
Manipulating moving objects requires a policy to anticipate contact events, yet vision-language-action (VLA) policies are commonly fine-tuned from the current observation alone. World action models (WAMs) learn predictive dynamics, but running a video-scale teacher or explicitly imagining future frames at deployment is costly. We introduce ForeTime-VLA, a dense pi0.5 policy that distills a future-aware, action-equivalent representation from a...
-
53
Calibrating Criterion Revision in LLM Agents: Failure Modes and a Trace-Anchored Protocol
Guodong Xu
cs.AI · cs.CL
Language-model agents can improve after failure or carry text across episodes without revising what counts as success. We study the narrower attribution problem of criterion revision: when criterion K0 accepts an outcome violating a broader commitment B, what observations justify saying that the system formed and persistently used K1? We require five non-compensatory conditions: criterion-failure detection, a model-emitted proposal,...
-
54
DirEAG: Dirichlet Evidence Aggregation for Calibrating Verbalized Confidence in Mathematical Reasoning
Haorui Xu, Yuzhou Zhu, Liyuan Gao
cs.AI
Reliable confidence estimation is essential for using large language models in mathematical reasoning, but black-box verbalized confidence is difficult to calibrate. When the same problem is queried under multiple confidence-steering prompts, the resulting answer-confidence observations contain useful uncertainty information, yet their scales may shift across steering levels, models, and datasets. Existing black-box uncertainty methods often...
-
55
VortexChat: An agentic framework for autonomous multi-objective integrated photonic design
Faqian Chong, Yulun Wu, Shilong Li, Andrew Forbes, Hongsheng Chen, Song Han
cs.AI · physics.optics
The advancement of modern integrated photonics is frequently bottlenecked by device design workflows that rely heavily on manual simulation and expert intuition. While inverse design offers an alternative, it remains constrained by expert supervision and a lack of end-to-end automation. To address these issues, we present VortexChat, an agentic framework for the autonomous, end-to-end inverse design of integrated photonic devices directly...
-
56
CDRL: Certification-Driven Reinforcement Learning for Neutrino Flavor Model Discovery
Piyush Jha, Jake Rudolph, Victoria Knapp-Pérez, Max Fieg, Aishik Ghosh, Vijay Ganesh
cs.AI · cs.LG · cs.LO · hep-ph
Many scientific discovery problems require searching combinatorial hypothesis spaces under complex domain constraints. Reinforcement learning (RL) offers a promising approach, but existing methods rely on scalar rewards that provide limited information about why candidate solutions fail, leading agents to repeatedly explore invalid regions. We introduce Certification-Driven Reinforcement Learning (CDRL), a framework that leverages structured...
-
57
Why2Speak: Faithful Reasoning for Abstaining Action Policies
Shreya Mendi, Brinnae Bent
cs.AI · cs.CL
Many agentic systems must repeatedly choose between acting and abstaining, making faithful reasoning important for oversight: an explanation is useful only if it reflects the computation that produced the action. We study this problem through intervention timing in multi-party conversation, where an assistant must decide whether to speak or remain silent. This setting exposes class imbalance, asymmetric action costs, and the possibility that...
-
58
DreamBench-SWE: A Multi-Session Memory-Hygiene Benchmark for Software Agents
Sarthak Singh
cs.AI · cs.SE
DreamBench-SWE is a multi-session benchmark for software-agent memory hygiene in which later software tasks depend on non-inferable evidence from earlier sessions and are scored by executable hidden oracles. We report the original scaled v2 fold and a separately preregistered v2.1 successor audit designed after that study but frozen before successor outcome inspection. The successor run completed 360/360 work units and 720/720 S3 cells across...
-
59
Auditable by Construction: An Ontology-Driven Framework for Trustworthy LLM Analytics in Enterprise Finance
Sergiy Lunyakin
cs.AI · cs.CE · cs.CL · cs.IR
Enterprise adoption of large language models in finance is constrained less by fluency than by trust: in Financial Planning and Analysis (FP&A) and other regulated workflows, an answer is usable only if it is traceable to authoritative sources and auditable after the fact. This paper argues that retrieval-augmented generation for enterprise finance should be evaluated on auditability alongside accuracy, and presents the Knowledge-Driven...
-
60
Beyond Effectiveness: A Multi-Criteria Framework for Comparing Practical Socio-Technical Interventions
Catherine King, Lynnette Hui Xian Ng, Kathleen M. Carley
cs.AI
Designers and policymakers in sociotechnical domains like content moderation, privacy interfaces, recommender systems and beyond, must choose among a growing menu of proposed interventions, but typically lack a principled basis for comparing them. Prior work tends to evaluate interventions individually and mostly along the effectiveness criteria, while implementation constraints such as cost, effort and feasibility are often considered...
-
61
Weighted Memory Tree: Remembering What Matters for Long-Horizon LLM Agents
Quang Dao, Purvi Kathalkar, Kenneth Eaton
cs.AI
Large language model (LLM) agents have demonstrated the ability to solve multi-step tasks requiring planning, tool use, and external information access, yet growing execution histories increase inference cost and expose reasoning to outdated, irrelevant, or misleading information, potentially degrading reasoning quality. Existing memory approaches organize or compress execution histories but provide limited mechanisms for deciding which...
-
62
SAGE: A Unified Algebra and Self-Adaptive Execution for AI Functions in SQL
Xiangqi Wang, Nhan H. Pham, Oktie Hassanzadeh, Dharmashankar Subramanian, Xiangliang Zhang
cs.AI
SQL systems increasingly expose AI functions for tasks such as classification, extraction, filtering, ranking, retrieval, joining, and summarization. Despite their diverse APIs, these functions play only three relational roles: transforming individual rows, aggregating groups, or generating relationships between row pairs. We present SAGE (Self-Adaptive Generative Execution), a unified logical and physical framework that captures these roles...
-
63
Applying Anthropic Primitives at Large Enterprises: Harness Paradigm for Knowledge Work
George Juraj Salapa
cs.AI · cs.SE
Frontier models have collapsed the cost of writing custom code: a niche problem a specialist sees in their own domain now costs an afternoon. The cost of reviewing and maintaining that code hasn't collapsed. Each solution drifts from the next; understanding one means reading its codebase from scratch. Large enterprises build something centrally governed instead: at worst an off-the-shelf product, at best a graph-orchestration framework wired...
-
64
Dual-Cache Latent Space Communication between Heterogeneous Language Models
Jiyao Liu, Qi Zhang, Yaoyi Jia, Ziwen Kan, Song Wang
cs.AI · cs.LG
Multi-agent LLM systems split work across models, so answering often requires knowledge that sits in another agent's context: a Sharer has encoded information that a Receiver needs to complete its task. They usually communicate by exchanging text, which puts autoregressive decoding on the critical path and reduces the exchange to a discrete message written without sight of the receiver's state. Recent latent protocols instead translate the...
-
65
Evaluating Skills, Not Just Agents: Agentic Continuous Evaluation of Skills
Christopher Kevin, Narendran Raghavan, Jean-Francois Puget, Roshni Malani, Meghana Puvvadi, Moshe Abramovitch, Mohit...
cs.AI
Enterprise agent programs are moving from prototypes into production, where reusable skills, tools, and workflow packages must be reviewed with evidence rather than prose. Current gates often scan these artifacts for structure, style, and security, but they do not answer the deployment question: does the capability package help a live agent complete enterprise tasks under the same model, sandbox, and grading policy? We present ACES (Agentic...
-
66
Difficulty-Aware Semantic-ID Optimization for Generative Recommendation
Xin Yu, Stephen Li, Sina Aghaei, Zifan Zhu, Jiamu Bai, Guanjie Huang, Bo Peng, Yiyao Liu, Lingzhou Xue
cs.AI
Semantic-ID-based generative recommendation casts retrieval and ranking as autoregressive generation over hierarchical item identifiers. A common recipe is SFT followed by GRPO, yet vanilla GRPO is poorly matched to this tree-structured task. Under the frozen SFT checkpoint, the exact target is absent from the first 16 candidates of the 50-beam constrained ranking for many prompts, and in harder cases none of these candidates enters the...
-
67
FlavourBench: Ranking Frontier Language Models with Executable Culinary Ground Truth
Josef Chen, Erim Hayretci
cs.AI · cs.CY · cs.LG · cs.SE
Open-ended language-model benchmarks usually inherit a judge: a human preference panel, another model, or a brittle exact-match key. We introduce FlavourBench, an automated benchmark in which a versioned culinary system supplies dense, executable ground truth. Each task presents eight ingredients and asks for a three-ingredient portfolio; before model execution, Epicure scores all 56 possible portfolios. We evaluate 27 frontier endpoints on...
-
68
Open-Weight Masked Introspection: Measuring What Language Models Can Report About Their Own Computation
Emilio Ferrara
cs.AI · cs.CL
Are frontier models able to introspect about their internal states? Recent work suggests that under certain conditions a complex enough model can audit its own internals, call out what changed, and report back confidently about it. We tested that claim on eight open-weight models from seven families and found no such ability: asked whether their own computation had been altered, none answered better than chance. To test it we built...
-
69
Consilience: Conformally Calibrated Communication Control for Hidden-Profile Multi-Agent Reasoning
Abhijith Babu, Ramneet Kaur, Vishal Pramanik, Olivera Kotevska, Nathaniel D. Bastian, Susmit Jha, Sunny Raj, Yanzhao...
cs.AI
Multi-agent LLM systems can improve reasoning by pooling diverse perspectives, but their effectiveness depends on coordinating communication, particularly in hidden-profile settings where each agent holds only part of the evidence required for a correct decision. Existing protocols, including fixed schedules, round-robin exchange, and unstructured debate, provide no guarantee that a conversational action is appropriate. We propose...
This edition is part of The Daily Abstract — cs.AI archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.