cs.AI · 2026-09-10 · No. 111

Artificial Intelligence, 2026-09-10.

40 new papers in cs.AI. Titles, authors, abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →

01 — The papers

40 entries

01

JarvisGUI: Towards Cross-Device GUI Agents with Dynamic Task Composition

Zixiang Chen, Yuheng Lu, Zihao Cheng, Zeming Liu, Jizeng Bai, Ziye Huang, Zhiyin Lin, Zihan Li, Yuhang Guo, Yunhong...

cs.AI

Real-world GUI usage frequently involves workflows that span multiple devices and platforms, requiring the transfer of intermediate results, maintenance of shared state, and coordination across heterogeneous environments. However, existing GUI benchmarks overwhelmingly evaluate agents on single-device, statically defined tasks, thus leaving such cross-device capabilities largely unexamined, resulting in an overly optimistic assessment of...

arxiv.org/abs/2609.10451 · PDF
02

ConvMem: Convolutional Memory for Long-Context Reasoning

Hongming Zhang, Zhaozhen Gu, Fengshuo Bai, Ming Hao, Qingyang Zhang, Yuanyuan Wang, Shiyang Tang, Yanna Wang, Bo Xu

cs.AI · cs.CL

While Large Language Models (LLMs) have demonstrated impressive capabilities, they often struggle with extremely long contexts due to fixed context limits. To address this, sequential approaches like MemAgent extend the effective context by reading text in segments and iteratively updating a fixed-size memory. However, this sequential paradigm suffers from high latency and requires costly reinforcement learning (RL) training, which can lead...

arxiv.org/abs/2609.10441 · PDF
03

Fortunate Recall: Ontology-Driven Memory Lifecycle Management for Persistent Coherence in LLMs

Ansuman Mullick, Eray Tüzün

cs.AI

Current LLM memory systems treat all personal facts identically, so stores grow without bound while retrieval precision degrades. The core challenge is lifecycle management: which memories should persist, which should be replaced, and at what rate, conditioned on the behavioral type of each fact. Fortunate Recall (FR) is a composable policy layer that classifies personal facts into a 10+1 behavioral ontology and applies category-specific...

arxiv.org/abs/2609.10413 · PDF
04

Cyber-Financial Contagion: Modeling the Propagation of an AI Vendor Compromise Through the Banking System

Alex Leytes

cs.AI · cs.CY · cs.LG

The banking system now depends on a small set of shared artificial intelligence vendors for fraud screening, credit decisioning, anti-money-laundering triage, customer analytics, and internal decision support. This paper studies how a compromise inside one of those vendors can propagate along a chain of operational, informational, and financial linkages until it triggers losses that look, from the outside, like a classical banking crisis. We...

arxiv.org/abs/2609.10350 · PDF
05

From Symbolic Perception to Logical Deduction: A Framework for Guiding Language Models in Geometric Reasoning

Weichen Dai, Rafael Medeiros Cabral, Ziyi Shou, Yan Cao, Xin Shen, Dongcai Lu, Yi Zhou

cs.AI · cs.CL

Plane geometry remains a significant challenge in AI, requiring the integration of visual perception and mathematical reasoning. While Large Multimodal Models (LMMs) naturally handle visuo-linguistic inputs, they are often computationally intensive and opaque. We demonstrate that a pure Large Language Model (LLM), when equipped with specialized modules, can rival state-of-the-art LMMs on complex geometry problems. Our framework integrates a...

arxiv.org/abs/2609.10335 · PDF
06

TRACE: Training Reasoning Agents for Causal Exploration with Synthesized Rewards

Rui Sun, Zhan Shi, Bing He

cs.AI · cs.LG

Reinforcement learning with verifiable rewards (RLVR) has advanced language-model reasoning in domains such as mathematics and code, where objective answers are inexpensive to check. Diagnostic reasoning over complex data lacks this advantage: establishing the true cause of an anomaly often requires costly expert investigation and may remain ambiguous after the fact. We ask whether this asymmetry of verification can instead be engineered. We...

arxiv.org/abs/2609.10315 · PDF
07

What Should an Agent Forget? Separating What Is Stored from What Is Used

Yuhang Li, Yuchen Li

cs.AI

Persistent language agents need stored experience to remain available across time, while each answer requires evidence suited to a particular question. A superseded fact can mislead a current-state answer and still be essential for a historical query. We present RD-Forget, a training-free framework that separates what an agent stores from what it uses. A retained source archive preserves observations, and a query-conditioned memory view...

arxiv.org/abs/2609.10263 · PDF
08

Why Sample What You Can Enumerate? Exact Policy Optimization for Genomic Tool Selection

Haoyue Liu, Xiaoyu Ma, Ye Chen, Zhichao Wang, Xiaoying Tang

cs.AI

Reinforcement learning over a frozen reasoner has become a common recipe for teaching a policy which external tools to invoke. We show that this recipe becomes structurally mismatched in specialist scientific settings where the complete tool-subset space is enumerable. There, a small set of recurring computational capabilities covers the domain, so the space of tool subsets is combinatorial yet small enough to enumerate, and GRPO still...

arxiv.org/abs/2609.10221 · PDF
09

Beyond Surface Imitation: Contrastive Modeling for Reasoning Path Alignment in Multimodal In-Context Learning

Mingbo Yang, Wenqiang Wang, Zhaolu Kang, Peng Chen, Yannan Chen, Sunshang Wang, Yan Xiao

cs.AI

In-context learning (ICL) is widely used in multimodal large language models (MLLMs) and achieves strong performance across a wide range of multimodal tasks. However, existing multimodal ICL methods often rely on surface level imitation of in-context demonstrations, making it difficult for MLLMs to align their responses with the reasoning path required by the given multimodal input. This limitation becomes more pronounced in complex...

arxiv.org/abs/2609.10177 · PDF
10

Kernel-Managed Shared Memory for System-Wide Personalization

Ryan Lum, Yongfeng Zhang

cs.AI · cs.LG

AI systems become more useful when they can adapt to the people using them, but in multi-agent systems, useful context learned by one agent often remains unavailable to others. We present kernel-managed shared memory, a system-level abstraction in which specialized agents write structured, tagged memories while the agent-system kernel, not individual agents, governs retrieval, privacy enforcement, and prompt injection. We implement and...

arxiv.org/abs/2609.10144 · PDF
11

Agent-Based ML-LLM Fusion with Self-Optimizing Prompts for Plateau Weather Alerts

Shuai Yan, Yang Xu, Shan He

cs.AI · cs.LG

To address insufficient contextualization, weak generalization, and poor scenario adaptation in tourism meteorological services, we propose SmartWeatherAgent--a unified three-stage architecture integrating intent recognition, hazard prediction, and reasoning-enhanced generation. The system fuses rule-based methods with large language models to parse queries at multiple granularities and employs a LightGBM model enriched with highland-specific...

arxiv.org/abs/2609.10135 · PDF
12

RAP: Research Attention Prediction Reveals Target-Conditioned Evidence Acquisition Biases

Yingqian Wu, Jingcong Liang, Siyuan Wang, Zhenfei Yin, Philip Torr, Junchi Yu, Zhongyu Wei

cs.AI · cs.CL

Large language models (LLMs) increasingly act as research agents, yet their ability to track shifts in research attention is difficult to evaluate because reviews and research ideas lack uniquely verifiable outcomes. We introduce Research Attention Prediction (RAP), a rolling benchmark covering 278 AI/ML fields and 1,390 episodes. At each cut-off, an LLM agent searches a temporally restricted arXiv corpus and predicts the next six months'...

arxiv.org/abs/2609.10092 · PDF
13

Reference-Based Bias Detection in LLMs via Relative Representations of Hidden States

Marek Jeliński, Jan Dubiński, Maciej Chrabaszcz, Sebastian Cygert

cs.AI

Existing bias auditing methods typically rely on model outputs, requiring costly benchmarks or judge models and potentially missing internal shifts that never appear in generated text. We propose a reference-based method that audits bias in hidden-state representations across related model variants, for example before and after fine-tuning. Because fine-tuning reshapes representation geometry, absolute hidden states are not directly...

arxiv.org/abs/2609.10060 · PDF
14

OntologyAligner: Ontology-Aligned Retrieval and Hierarchy-Guided Large Language Model Reranking for Biomedical Ontology Normalization

Jie Song, Zhichuan Xu, Ziyu Lu, Meng Xiao, Cheng Bi, Yuxin Zhang, Xin Zheng, Xiaoran Li, Qiongfang Cao, Hao Yang,...

cs.AI · cs.CL

Biomedical ontology normalization maps free-text expressions to standardized concepts, enabling consistent integration and analysis of biomedical data. This task remains challenging because lexical variation and subtle distinctions among hierarchically related concepts can obscure concept boundaries. We present OntologyAligner, a three-stage framework that combines ontology-aligned retrieval, large language model candidate reranking, and...

arxiv.org/abs/2609.10055 · PDF
15

Belief-State Engine: Augmenting LLMs for Principled Planning Under Partial Observability

Arnab Chattopadhayay, Debdipta Halder

cs.AI · cs.LG · cs.RO

Large language model agents produce fluent action sequences across a wide range of tasks, yet they fail in characteristic ways once the environment becomes partially observable. Ambiguous feedback pushes them into premature commitments. A single informative observation can collapse their uncertainty onto the wrong hypothesis. Policies drift as the history grows. We trace these symptoms to a common structural cause. An LLM agent, as commonly...

arxiv.org/abs/2609.10036 · PDF
16

Structural Process Supervision for Latent Chain-of-Thought Reasoning

Yiqi Li, Xu Chen, Chen Ju, Jiangchao Yao, Zhaoyang Li, Jinsong Lan, Xiaoyong Zhu, Bo Zheng, Yu Wang

cs.AI

Latent reasoning approaches enhance token-level efficiency and robustness by replacing verbose, explicit chain-of-thought (CoT) tokens with compact continuous-space embeddings. However, existing methods lack direct process supervision over these latent embeddings, which often leads to representation collapse and uneven information distribution. To address this, we propose Prototype-Mediated Process Supervision (PMPS), which introduces...

arxiv.org/abs/2609.09928 · PDF
17

Time-Frequency Geometric Cross-Attention for Chunked Vision-Language-Action Models

Shengye Dong, Haochen Niu, Hao Liu, Peiwen Lin, Chuang Wang, Shanmin Pang

cs.AI · cs.RO

Modern vision-language-action (VLA) policies predict a whole chunk of actions: one to two seconds of coordinated motion emitted in a single forward pass. Yet an action chunk is essentially a short multivariate trajectory, but inside these models it is a sequence of generic per-timestep hidden tokens decoded by a linear head. This under-serves two motion structures. First, frequency: a chunk superimposes a smooth global trend and fine...

arxiv.org/abs/2609.09925 · PDF
18

Grounded Evaluation and Repair for NL-to-PDDL Problem Generation

Joana Rosa, Pedro Santos, Valdemar Oliveira, Romão Silva, L. Miguel Silveira, Bruno Martins

cs.AI

Large Language Models (LLMs) have shown promise for translating Natural Language (NL) planning descriptions into PDDL problem instances. However, standard evaluation criteria such as syntactic validity or planner success can substantially overestimate faithfulness to the described task: a generated problem may be parseable and solvable while misrepresenting the intended initial state, goal, object structure, or optimization target. This paper...

arxiv.org/abs/2609.09898 · PDF
19

Decision Transformer for UAV-Mounted RIS-Assisted Dynamic D2D Communications

Yaxuan Liu

cs.AI · cs.RO

This paper studies unmanned aerial vehicle (UAV)-mouted reconfigurable intelligent surface (RIS)-assisted device-to-device (D2D) communication with stochastic link activation. It models UAV motion and attitude, time-varying Rician angles, and angle-dependent RIS reflection. A joint optimization of UAV trajectory, attitude, and RIS phases is formulated to maximize average sum rate under mobility, energy, and hardware constraints. The problem...

arxiv.org/abs/2609.09885 · PDF
20

Scored vs. Generated Readouts in Behavioral Language Models: An Empirical Study of Elicitation Format

Touchapon Kraisingkorn, Krittin Pachtrachai, Wachiravit Modecrua

cs.AI

Language models fine-tuned on customer behavior can predict outcomes and generate explanations, but these readouts are often treated as interchangeable. Holding model checkpoint and prompt content fixed, we compare probabilities obtained by scoring answer tokens with predictions generated after a written rationale. Across 13 model-domain cells covering four retail tasks in three markets, including two using fully public data and checkpoints,...

arxiv.org/abs/2609.09882 · PDF
21

AgentAudit: An Open, Extensible Framework for Full-Lifecycle Trust Evaluation of AI Agents

Shrey Nag, Sachita, Abhishek Kumar Singh, Lipi Goel, Rajeshwar Singh Janwar

cs.AI

Existing evaluation frameworks mostly assess only one part of AI agents, such as task completion (AgentBench) or security robustness (AgentDojo, ASB), rather than the complete pipeline of planning, tool selection, tool execution, memory and reasoning. Failures can occur at any stage, yet existing benchmarks rarely identify their precise source. AgentAudit evaluates the entire execution trace across ten capability, grounding, security and...

arxiv.org/abs/2609.09875 · PDF
22

Shifting Relational Paradigms for Affective Computing: Affective Resonance, Vitality Affects, and Vocal Interaction Fields

Cy Gorman, Yihang Yao

cs.AI

Affective computing has largely followed an individual-state paradigm, extracting discrete emotion labels or arousal/valence from isolated speakers. We argue this framing is incomplete for interaction. Drawing on affective resonance and vitality-contour accounts, we propose a relational framework in which the primary unit of affective analysis is the interactional field constituted within vocal dynamics. As a proof of concept, we present a...

arxiv.org/abs/2609.09864 · PDF
23

The Era by Eon Benchmark: A Generated Enterprise Estate with Exact Ground Truth for Benchmarking LLM Agents

Benjamin Gruenbaum, Doron Porat, Assaf Natanzon, Roy Zavida, Chen Dinachi, Or Itzahary

cs.AI

LLM agents for enterprise systems of record cannot be evaluated on customer production data, and no existing substitute provides ground truth. We present the Era by Eon Benchmark for evaluating LLM agents that use enterprise tools. The benchmark is built around a complete fictional company. It includes product simulators, company-specific internal databases, benchmark questions, and computed answer keys. Industry, company size, business...

arxiv.org/abs/2609.09853 · PDF
24

UnitBoost: Managing Compound LLM Systems with a Merge Operator, Not a Model

Xing Zhang, Guanghui Wang, Yanwei Cui, Mengdie Flora Wang, Peiyang He

cs.AI · cs.CL · cs.MA

Compound LLM systems often solve a coordination problem by adding a higher-level LLM. The resulting meta-agent reads workers' outputs, writes the final answer, allocates later calls, and decides when to stop. It is expressive, but it also concentrates three control decisions in an opaque, order-sensitive model call. We ask whether the manager needs to be generative at all. UnitBoost replaces that model with a defined meta-level operator: a...

arxiv.org/abs/2609.09815 · PDF
25

Proof-Carrying Cognition: Closing the Verification Gap with Reality-Settled Reward

Eshwar Reddy M, Sourav Karmakar

cs.AI · cs.LG

Frontier gains in language-model reasoning come from reinforcement learning on reasoning traces and are concentrated in domains with a cheap, sound verifier. We argue the field's binding constraint is the verification gap: no scalable, incorruptible reward for reasoning outside formal domains. We make four contributions. (1) Theory: in a joint-Gaussian model of best-of-N selection, verifier-gold correlation rho is the exact exchange rate...

arxiv.org/abs/2609.09776 · PDF
26

Procedural Memory Under Change: Reuse and Interference in Controlled Web Tasks

Yanze Cao

cs.AI

Procedural memory lets language agents reuse successful routines, but reuse presumes that a stored routine remains applicable. We study what happens when that presumption is deliberately violated. The study combines a retrospective, human-assisted interface-adaptation case from BrowserGym TimeWarp with controlled frozen-memory comparisons on synthetic shopping decisions. During the documented WebShop V1-V6 development path, interface-specific...

arxiv.org/abs/2609.09774 · PDF
27

LexAgentHallu: A Hierarchical Benchmark for Profiling Hallucinations in Legal Agents

Yujin Zhou, Mingxuan Zheng, Chuxue Cao, Huang Yidan, Jiale Chen, Yike Guo, Sirui Han

cs.AI

As large language models are increasingly deployed as tool-augmented legal agents, they introduce agentic hallucinations where tool-call and reasoning errors cascade into fabricated holdings and miscited authority. However, existing legal benchmarks evaluate only single-turn QA with outcome-level metrics, while agentic hallucination benchmarks lack legal-specific diagnostic capability. Neither answers to what extent and how a legal agent...

arxiv.org/abs/2609.09754 · PDF
28

Can Artificial Intelligence Support Healthcare and Mental Health Through Early Cyberbullying Detection ? The Impact of Emotion-Aware AI on Proactive Online Safety

Hamed Jelodar, Amir Firouzi, Yen-Wu Lo, Maryam Tanha, Sajjad Dadkhah

cs.AI · cs.CL

Healthcare systems, mental health, and public well-being are increasingly affected by cyberbullying and harmful online interactions. This paper presents CareGuard, an early-warning framework designed to support healthcare-driven mental health protection and proactive online safety through the detection of cyberbullying-related content using advanced natural language processing techniques. CareGuard integrates zero-shot semantic labeling with...

arxiv.org/abs/2609.09735 · PDF
29

Which Tokens Should SFT Actually Learn? A Token-Trimming Perspective on Mathematical Reasoning

Yaning Jia, Chunhui Zhang, Wenxuan Xu, Xingjian Diao, Xiaoyuan Wang, Soroush Vosoughi

cs.AI

Supervised fine-tuning (SFT) applies a uniform cross-entropy loss to all target tokens, even though different tokens provide unequal learning signals for mathematical reasoning. This uniform treatment can over-sharpen already mastered tokens while amplifying learning pressure on uncertain, low-confidence tokens, leading to suboptimal training dynamics. We propose Trimmed Logit-Gap SFT (TrimSFT), a simple token-level reweighting method that...

arxiv.org/abs/2609.09707 · PDF
30

Decision Shifts, Lost Label Functionality, and an Inconclusive Grounding Audit in Correctness-Gated Multi-Teacher Distillation

Xiaofei Feng

cs.AI

Candidate decision correctness and rationale grounding are different objectives. We examine correctness-gated multi-teacher distillation in a fixed experiment. Eight arms share 4,330 sources, a 63.9M-parameter student, 12,990 optimization rows, 406 updates, evidence inputs, and a decoder; seven teacher-based arms use one fixed three-response pool. Three seeds are evaluated on 267 held-out examples. Relative to unfiltered distillation, the...

arxiv.org/abs/2609.09702 · PDF
31

Safe to Stop? Risk-Constrained Stopping for Sequential Clinical Diagnosis Agents

Yuexin Wu, Vasile Rus

cs.AI

Clinical diagnosis agents must decide not only what test to request next, but also when to diagnose or defer. Existing agent benchmarks largely evaluate accuracy after fixed or unconstrained interaction, leaving autonomous stopping reliability implicit. We present Cros, a risk-constrained stopping layer combining state-wise error ranking, policy design on disjoint development splits, and LTT-style exact tests of selective diagnostic error and...

arxiv.org/abs/2609.09678 · PDF
32

PRAGMA: Evaluating Personalized Guidance with Memory Alignment in Lifelong Conversations

Hyojeong Yu, Hyukhun Koh, Minsung Kim, Yunah Jang, Kyomin Jung

cs.AI

Large language models (LLMs) are increasingly deployed as personalized assistants that interact with users over extended periods of time. As conversations grow longer, relying on full interaction histories becomes increasingly inefficient and unreliable: long contexts introduce substantial computational overhead, making it difficult for models to consistently identify and utilize the most relevant information for the current request. These...

arxiv.org/abs/2609.09664 · PDF
33

RESCUE-BENCH: Towards Relation-Aware Multi-Party Emotional Support Conversation Systems

Haichuan Hu, Yang Xiao, Mingni Tang, Jiawen Duan, Quanjun Zhang, Congqing He, Hao Zhang, Jiashuo Wang, Johan F....

cs.AI

Existing emotional support conversation systems mainly focus on one-on-one seeker-supporter interactions and individual emotional states, leaving interpersonal relations in multi-party scenarios underexplored. In this work, we introduce relation-aware emotional support conversation, a new task that evaluates whether LLMs can capture and utilize the evolving dynamics of relationships to offer more effective emotional support. We construct...

arxiv.org/abs/2609.09657 · PDF
34

Black-Box Red Teaming of Agentic AI: A Taxonomy-Driven Framework for Automated Risk Discovery

Divyanshu Kumar, Nitin Aravind Birur, Tanay Baswa, Sahil Agarwal, Prashanth Harshangi

cs.AI

Agentic systems are rapidly moving to production, where they read untrusted inputs, call tools with real permissions, and act autonomously, expanding the security surface beyond chat-only models. Yet standard evaluations remain single-turn and fail to capture multi-step agent vulnerabilities. We present a systematic black-box framework for risk-aware agent evaluation requiring only basic system descriptions. Our approach introduces: (1) a...

arxiv.org/abs/2609.09647 · PDF
35

RobustSGPO: Search-Space Control for Agent Harness Evolution

Zibo Zhao, Jijun Shi, Mo Zhou, Zhongyuan Wang, Shifu Bie, Yunfei Zhang, Xuanting Zhou, Xiangyu Wu, Bin Liu, Ruiming...

cs.AI

Semantic-gradient-based prompt optimization (SGPO) improves agent harnesses using execution feedback, but its local update rule leaves the choice of edit scope and operation unresolved. We introduce RobustSGPO, which specifies the requested edit, constructs and checks the patch, and continues search from either the incumbent or retained snapshots. We evaluate permission scheduling, cumulative controls, and task-family transfer in the AgentX...

arxiv.org/abs/2609.09646 · PDF
36

Seven Sources of Physical AI Capability Formation

Gang Chen

cs.AI

Capabilities relevant to Physical AI can arise from materially different formation histories, yet existing taxonomies organized by morphology, architecture, learning algorithm, task, or domain do not directly answer what gives rise to a capability. We define a capability-formation source as a factor materially contributing to capability formation, distinct from components or construction steps. We identify seven non-exclusive sources:...

arxiv.org/abs/2609.09627 · PDF
37

From State Synchronization to Cognitive Self-Evolution: An Operational Architecture for Cognitive Digital Twins

Haoran Gao, An Li, Zhen Li, Jun Cai

cs.AI

As Digital Twin (DT) systems evolve beyond state synchronization toward task-oriented and knowledge-driven operation, Cognitive Digital Twins (CDTs) have emerged as an extension that incorporates cognitive capabilities into twin operation. Existing CDT studies often focus on specific enabling techniques, such as learning modules, knowledge graphs, and large language models, while providing limited insight into how cognition can be...

arxiv.org/abs/2609.09625 · PDF
38

A Function-Space Approach to the Statistical Mechanics of Learning Dynamics

Yizhou Zhang, Weichen Wu, Lun Du, Zhengjie Miao

cs.AI

Deep neural networks exhibit regular macroscopic behavior despite highly nonlinear dynamics in vast parameter spaces. We develop a statistical-mechanical description of learning directly in function space, treating parameter configurations as microscopic realizations and functions with their dynamical operators as macroscopic variables. For mean-squared loss, the exact error dynamics are governed by the learning operator \(M=JJ^\ast\)....

arxiv.org/abs/2609.09589 · PDF
39

CityPlanner: A Sandbox Agent for Executable Urban Planning

Wentao Zhang, Jingyuan Wang, Zetong Zhou, Yifan Yang, Wenrui Wang

cs.AI · cs.CL

Urban planning is a real-world spatial optimization problem that requires selecting feasible actions from large candidate spaces under practical objectives such as cost and service quality. Existing optimization and reinforcement learning methods are effective for fixed formulations, but often depend on task-specific representations and constraint handling. We propose \emph{CityPlanner}, a sandbox-agent framework for executable urban...

arxiv.org/abs/2609.09578 · PDF
40

Multi-Agent Agentic Graph Learning via Structural Signatures

Liang Qu, Jianxin Li, Hua Wang

cs.AI

Agentic graph learning (AGL) has recently achieved promising results on graph reasoning tasks, where an agent powered by a large language model (LLM) sequentially samples the graph as evidence to support its final prediction. Existing methods either employ a single agent or orchestrate multiple role-based agents to reason and learn over the entire graph, but both essentially rely on a shared reasoning policy across different graph regions,...

arxiv.org/abs/2609.09565 · PDF

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.

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.