arXiv Machine Learning
Aug 10
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation
arXiv:2608. 06422v1 Announce Type: new Abstract: Giving an LLM judge more compute does not necessarily make it check more requirements.
Large language models
Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv AI
Aug 10
SkillProx: Self-Evolving Agent Skills via Proximal Textual Gradient Descent
arXiv:2608. 07449v1 Announce Type: new Abstract: LLM agents increasingly adapt to recurring tasks by accumulating procedural knowledge in skills.
arXiv AI
Aug 10
EntropyMoE: Entropy-Aware Sparse Expert Routing for Tokenizer-Free LLMs
arXiv:2608. 06398v1 Announce Type: new Abstract: Recent byte-level large language models (LLMs) have made tokenizer-free modeling increasingly competitive by grouping bytes into dynamically sized patches.
arXiv AI
Aug 10
Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin
arXiv:2608. 06411v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) achieve strong performance across diverse vision-language tasks, but their efficiency is limited by the cost of processing numerous visual tokens.
arXiv AI
Aug 10
WebGrader: Training LLMs for Web Development with Self-Evolving Programmatic Grader
arXiv:2608. 06474v1 Announce Type: new Abstract: Large language models increasingly generate complete websites from natural-language descriptions, and reinforcement learning has become a central approach to closing their remaining functional gap.
arXiv AI
Aug 10
Automated item evaluation: Predicting item acceptance and rejection using LLM-generated critiques
arXiv:2608. 06609v1 Announce Type: new Abstract: Automated item evaluation (AIE) refers to the use of computational methods to assess item quality without requiring manual expert review or field testing of the items under evaluation.
arXiv AI
Aug 10
Shape Your Feed: An LLM-based Agentic System for Conversational Recommendation
arXiv:2608. 06632v1 Announce Type: new Abstract: Industrial recommendation systems predominantly adopt a passive ranking paradigm that infers user preferences from implicit behavioral signals (e.
arXiv AI
Aug 10
AgentPatch: Coarse-to-Fine Weak-Task Repair for Merging Agentic Multimodal Large Language Models
arXiv:2608. 06699v1 Announce Type: new Abstract: Agentic multimodal large language models (MLLMs) extend multimodal perception and reasoning with planning, tool use, and interaction in dynamic environments.
arXiv AI
Aug 10
bioMoR: Biology-Guided Mixture-of-Recursions for Effective Genomic Learning
arXiv:2608. 06727v1 Announce Type: new Abstract: Transformer models for high-dimensional omics analysis process thousands of genes or pathways, although only a subset requires deep computation.
arXiv AI
Aug 10
IB-RL: Isolated Bilateral Reinforcement Learning for Strategic Dialogue Agents
arXiv:2608. 06735v1 Announce Type: new Abstract: Reinforcement learning (RL) has achieved strong results in improving large language models (LLMs) on tasks with stationary, verifiable rewards, such as mathematical reasoning and code execution.
arXiv AI
Aug 10
From Cheap Fakes to Pure Synthesis: Addressing the New Era of T2V Fake News Videos
arXiv:2608. 06732v1 Announce Type: new Abstract: Recent text-to-video (T2V) generation models enable fake news videos to be synthesized from scratch, shifting the threat beyond cheap fakes assembled from existing footage.
arXiv AI
Aug 10
CEDAR: Agent-Orchestrated Tree Search for Goal-Directed Optimization of Complex Systems
arXiv:2608. 06871v1 Announce Type: new Abstract: Complex systems, core objects of study in artificial life, model diverse phenomena through nonlinear, feedback-driven interactions that produce emergent behavior, with applications from population dynamics and biology to economic policy and strategic decision-making.
arXiv AI
Aug 10
Blind to the Pivotal Vote: Aggregate Independence Metrics Miss Where Verification Actually Helps
arXiv:2608. 06940v1 Announce Type: new Abstract: LLM judge panels are a standard evaluation tool, but prior work reports highly correlated panel errors: nine judges provide roughly the effective information of two independent ones, and aggregation closes only a small fraction of the gap.
arXiv AI
Aug 10
Science Edge Evaluation: SEE the Missing Step Toward Real Scientific Discovery
arXiv:2608. 06931v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly involved in scientific discovery, yet it remains unclear whether they can support complex real laboratory science.
arXiv AI
Aug 10
Does Splitting a Triage Decision Across Agents Hide Bias or Help Catch It? A Multi-Agent Simulation Study of LLM-Based Resource Allocation Under Audit Capacity Constraints
arXiv:2608. 06949v1 Announce Type: new Abstract: Prior benchmarking work has shown that a single large language model (LLM), forced to make life-or-death resource-allocation decisions, exhibits measurable demographic bias.
arXiv AI
Aug 10
ReQuant: Fixed-Grid Discrete Refinement for Post-Training Quantization
arXiv:2608. 07019v1 Announce Type: new Abstract: Post-training quantization (PTQ) is widely used to reduce the memory and computational cost of large language models.
arXiv AI
Aug 10
PTQ4SNN: Membrane-Aware Post-Training Quantization for Spiking Neural Networks
arXiv:2608. 07066v1 Announce Type: new Abstract: Spiking neural networks (SNNs) enable sparse and event-driven computation, but their low-bit deployment remains incomplete because recurrent membrane states are commonly retained in floating point even after weight quantization.
arXiv AI
Aug 10
Multi-Level Modeling of Large Language Model Inference Latency and Energy via Hybrid Analytical--Machine-Learning Predictors
arXiv:2608. 06723v1 Announce Type: cross Abstract: The rapid scaling of Large Language Models (LLMs) has significantly increased computational cost, energy consumption, and inference latency, making accurate estimation essential for sustainable artificial intelligence deployment and hardware-aware design.
arXiv AI
Aug 10
PHASE-Tree: Modeling Character-State Evolution in Long-Horizon Role-Playing Dialogue
arXiv:2608. 06975v1 Announce Type: cross Abstract: Long-horizon role-playing demands that characters remain recognizable as they evolve with the narrative.
arXiv AI
Aug 10
Diffusion LLMs as Targets and Adversaries: Mechanistic Safety Exploits
arXiv:2608. 07430v1 Announce Type: cross Abstract: Diffusion Large Language Models (DLLMs) replace autoregressive next-token prediction with iterative parallel denoising, yet their internal safety mechanisms remain poorly understood.