Examining Human-Like Behaviors in LLMs: A Multi-Dimensional Analysis of Model Behaviors, User Factors, and System Prompts
Large language models (LLMs) exhibit a wide range of human-like behaviors, from expressing thoughts and emotions, to engaging in relationship-building with users, to refusing requests and maintaining boundaries. Despite their prevalence, researchers and practitioners lack methods and empirical insig...
Tiny robots powered by light can hunt down and collect bacteria
Researchers have built microscopic, light-driven robots that can rapidly navigate through liquid, collect bacteria, and deposit them in chosen locations. These tiny “cleaners” could open new possibilities for manipulating cells and microbes with remarkable precision.
When to Communicate: Belief Distributions and KL Divergence for Principled Gating in Multi-Agent RL
arXiv:2608.14559v1 Announce Type: new
Abstract: Effective communication in multi-agent reinforcement learning requires agents to decide not only \textit{what} to communicate, but when? Existing approaches either communicate at every timestep or learn a binary gate through REINFORCE policy gradients...
The Unwritten Benchmark: A New Challenge for Multimodal Machine Learning in Abstract Perceptual Reasoning
arXiv:2608.14558v1 Announce Type: new
Abstract: Current multimodal models have demonstrated remarkable proficiency in recognizing static visual and auditory content. However, their capacity for abstract perceptual reasoning, inferring unseen information from dynamic, generative processes, remains a...
Large Language Models Show Metacognitive Sensitivity in Medical Reasoning
arXiv:2608.14552v1 Announce Type: new
Abstract: Large language models (LLMs) are increasingly evaluated and used in medicine, but clinical usefulness depends on answer accuracy and whether confidence tracks evidence quality and uncertainty. We developed a controlled, psychophysics-inspired clinical...
DumpsterCluster: From Dumpster Diving to Serving LLaMA-70B on $60 GPUs
arXiv:2608.14614v1 Announce Type: new
Abstract: As AI datacenters retire functional GPUs, vast quantities of still capable accelerators enter secondary markets. This paper investigates whether these retired GPUs can find a productive afterlife to form a DumpsterCluster that can serve modern LLM inf...
Coarse-to-Fine Multi-Resolution Diffusion Models for Trajectory Generation in Urban Systems
arXiv:2608.14570v1 Announce Type: new
Abstract: Understanding human mobility is critical for a wide range of urban applications, including traffic management, epidemic control, and urban planning. However, due to privacy concerns, the availability of large-scale public trajectory data remains limit...
arXiv:2608.14563v1 Announce Type: new
Abstract: Forward-Pass-Only MLP training (FPO) adapts large language models without a backward pass through the model body, achieving 2.7--3.2x the throughput of standard fine-tuning at ~40% less peak training memory, while leaving off-domain benchmarks within ...
Learning Discrete Riemannian Metrics for Physical Fields with Cochain-Frame Equivarianc
arXiv:2608.14556v1 Announce Type: new
Abstract: Physical fields on meshes require a separation between topology and geometry: conservation laws are topological and should be exact, while geometry, material response, and anisotropic coupling must be learned from data. Existing neural surrogates ofte...
Agentao: A Governed Local-First Runtime for Tool-Using LLM Agents
arXiv:2608.13574v1 Announce Type: new
Abstract: LLM agents increasingly operate as execution systems that invoke tools, modify local state, use persistent memory, and interact with external protocols. These capabilities make agents useful, but they also introduce risks related to over-privileged ac...
A Year in LLM Serving: Workload Evolution, Caching and Load-Balancing
arXiv:2608.13573v1 Announce Type: new
Abstract: Large Language Model (LLM) serving has become a critical cloud workload, and realistic traces are essential for motivating and benchmarking serving systems. However, existing LLM serving workload studies remain limited in scale and scope. They often o...
Modular Cognitive Architecture Emerges in Large Language Models
arXiv:2608.13567v1 Announce Type: new
Abstract: The human brain exhibits a striking degree of functional specialization, with distinct networks supporting language, formal reasoning, reasoning about other minds, and reasoning about the physical world. Is this modular organization a fundamental prin...
Depth-Aware Sensitivity Analysis of Mixture-of-Experts Models via Magnitude-Based Expert Masking
arXiv:2608.13565v1 Announce Type: new
Abstract: Mixture-of-Experts (MoE) architectures scale large language models (LLMs) while preserving computational efficiency through sparse activation. Despite their widespread adoption, the relative importance of individual MoE layers remains insufficiently c...
Inducing Reward-Free Judging Rubrics that Reduce Over-Crediting in Agent Evaluation
arXiv:2608.13564v1 Announce Type: new
Abstract: Evaluating language-model agents at scale increasingly relies on a second language model as an automatic judge, because the gold signal, an executable environment reward, is expensive, slow, or unavailable at deployment time. Such a judge is a reward-...
Hard Cases, Bad Labels: Testing Error Exposure and Error Location in Uncertainty Sampling Under Bounded Label Noise
arXiv:2608.13601v1 Announce Type: new
Abstract: Active learning can reduce labeling cost by selecting informative examples, but the most uncertain examples may also be the hardest to label correctly. This study tests whether uncertainty sampling fails because it acquires more corrupted labels or be...
Don't Claim Benchmark-Oriented Optimization Improves General Coding Capability -- Diverse Evaluation Is Required
arXiv:2608.13566v1 Announce Type: new
Abstract: Post-training papers, model cards, and blog posts often treat scores on a small set of coding benchmarks (e.g., SWE-bench and LiveCodeBench) as evidence of broad coding capability, both for research artifacts and user-facing systems. We argue that opt...
L-FNO: Lorentzian Fourier Neural Operator for Stochastic Event Dynamics
arXiv:2608.13562v1 Announce Type: new
Abstract: Modern operational systems face uncertainty even in routine conditions, where rare, bursty, and self-exciting events emerge from both exogenous covariates and endogenous event dynamics. Standard neural operators are typically trained as regression-sty...
Multi-Agent Scheduling with LLM-Assisted Contract Net Negotiation for Stream Processing in Mobile Edge Computing
arXiv:2608.12371v1 Announce Type: new
Abstract: Stream-processing systems increasingly operate across heterogeneous mobile edge--cloud infrastructures, where workload volatility, resource contention, and stringent quality-of-service (QoS) requirements complicate decentralized scheduling. This paper...
Agreement Is Not Alignment: Divergent Moral Grounds in Human and LLM Ethical Judgments
arXiv:2608.12368v1 Announce Type: new
Abstract: Agreement with human judgments is a common proxy for evaluating the alignment of large language models (LLMs). Yet agreement in final labels does not show that human annotators and models rely on the same moral grounds. Two agents may reach the same j...
Position: The Alignment Community is Unintentionally Building a Censor's Toolkit
arXiv:2608.12346v1 Announce Type: new
Abstract: This position paper argues that modern AI alignment methods - originally designed to prevent harmful output - are dual-use technologies that may easily be misused by malicious actors for censorship and manipulation. By mapping current alignment techni...
Diagnostic Foundation for Evaluating LLMs' Research Integrity as Co-Scientists
arXiv:2608.12345v1 Announce Type: new
Abstract: Language models are increasingly deployed as co-scientists, yet their ability to uphold research integrity under institutional pressure remains unmeasured. We introduce IntegrityBench, a benchmark evaluating misconduct classification, ethical action r...
Position: Reasoning is a Learnable Rule-Based Process
arXiv:2608.12325v1 Announce Type: new
Abstract: Autonomous reasoning is among the most scientifically and economically motivating topics in AI today. Historically the purview of symbolic AI, recent advances have mainly emerged from deep probabilistic generative models. Despite immense interest and ...
World’s first superconducting quantum heat engine could help unlock massive quantum computers
A tiny superconducting engine has successfully converted heat near absolute zero into useful work, demonstrating the first cyclic quantum heat engine of its kind. Future versions could operate autonomously inside quantum computers, potentially eliminating huge numbers of costly, noise-producing micr...
arXiv:2608.12438v1 Announce Type: new
Abstract: We formulate generative modeling as a path integral in which flow-based, diffusion-based, variational, and adversarial models arise as different evaluation principles for a single master action. Its Martin-Siggia-Rose-Janssen-de~Dominicis (MSRJD) form...