All entries

Agents Catching Agents: Shortcut Cascades and Benchmark Gaming in Clinical Multi-Agent Systems

arXiv:2608.03744v1 Announce Type: new Abstract: Clinical decision support is moving toward committees of language-model agents deliberating on a shared workspace. We ask whether such committees can be

Agents

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks?

DGX agent

arXiv:2608.00155v1 Announce Type: cross Abstract: Large language model (LLM) agents can self-evolve by continually improving from their own accumulated experience. However, existing studies predominan

agentsarxiv-cs-lg

5 Aug 2026

Tutorials

Agogic: Performance-Timed Music Tokens for LLM-Native Text-to-Symbolic-Music Generation

arXiv:2608.03999v1 Announce Type: cross Abstract: Text-to-music language models begin with a choice usually made by default: how to tokenize music. Normally entangled with backbone, data, and recipe,

tutorialsarxiv-cs-cl

AI Agent Economics: Can Autonomous Economic Behavior Emerge among AI Agents under Minimal External Conditions?

arXiv:2608.03076v1 Announce Type: new Abstract: Multi-agent studies commonly place AI agents in predefined games, markets, or roles, making it difficult to distinguish endogenous economic organization

AI Alignment and Fiduciary Obligation

arXiv:2608.02660v1 Announce Type: cross Abstract: Advanced AI assistants engage users in extended interactions across a widening range of roles, including advice, decision support, collaboration, lear

AI Assistance Reduces Persistence and Hurts Independent Performance

arXiv:2604.04721v3 Announce Type: replace Abstract: People often optimize for long-term goals in collaboration: A mentor or companion doesn't just answer questions, but also scaffolds learning, tracks

AI-Assisted Peer Review Across Research Communities: From Reviewer AI Policies to LLM Review Quality

arXiv:2608.03581v1 Announce Type: cross Abstract: AI-assisted peer review is increasingly discussed and adopted as a tool to support the scientific publishing process, yet there is little systematic u

AI-Based Sound Effect Generation: A Narrative Review of Generative Models Across Input Modalities

arXiv:2608.03742v1 Announce Type: cross Abstract: Sound effects play a crucial role in conveying actions, events, and environmental cues across digital applications, often requiring a high degree of v

AI Forensics Across White-, Grey-, and Black-Box Access: A Process Model and Research Agenda for Post-Incident Investigation of AI Systems

arXiv:2608.03520v1 Announce Type: cross Abstract: AI systems are increasingly involved in decisions and actions that may later require investigation. When an AI related incident occurs, investigators

Tutorials

AI Sandbox: Technical Report

arXiv:2608.02679v1 Announce Type: cross Abstract: Collaborative AI experimentation across industry and academia requires platforms that enable rapid prototyping while preserving controlled access, ten

tutorialsarxiv-cs-ai

AI Security Leaderboard: Methodology, Results and Minimal Standard

arXiv:2608.03070v1 Announce Type: cross Abstract: Frontier AI model developers increasingly rely on layered safeguards to prevent catastrophic misuse, but little public evidence exists on how much pro

AI World Cup 2026: Benchmarking Large Language Models for End-to-End Football Tournament Prediction

arXiv:2608.03416v1 Announce Type: new Abstract: Large language models (LLMs) are now regularly asked to forecast real-world events, but comparisons are often difficult because models receive different

Ai2 expands collaboration with Hugging Face to accelerate open science

Ai2 is expanding its partnership with Hugging Face to give its growing portfolio of fully open models, datasets, benchmarks, and applications the storage, bandwidth, and integrations needed to reach m

researchai2

AIDE: Automated Instruction via Distilled Expertise for Reference-Free Motor Skill Coaching

arXiv:2608.03047v1 Announce Type: new Abstract: Generating natural-language coaching feedback on motor skills can accelerate learning, yet expert coaches are scarce and expensive. Existing reference-b

researcharxiv-cs-cv

Aligned in Form, Not in Meaning: The Comprehension - Containment Decoupling of LLM Safety in Low-Resource Bangla Derogatory Speech

arXiv:2608.02941v1 Announce Type: new Abstract: We audit five frontier large language models on native Bangla derogatory speech (gali) across six protocols to test a single hypothesis: Comprehension-C

safetyarxiv-cs-cl

Local Ai

Aligning Large Vision-Language Models at Test Time: A Trajectory-Guided Structured Sampling Approach

arXiv:2608.03204v1 Announce Type: cross Abstract: Post-training reinforcement learning (RL) algorithms are commonly used to align large vision-language models (LVLMs) with human intent and the require

local-aiarxiv-cs-ai

Applications

Also I think AISI is a great model of a government agency tasked with AI security. They have open benchmarks, very fast testing, and clear c…

applicationsethan-mollick--x

Also I think AISI is a great model of a government agency tasked with AI security. They have open benchmarks, very fast testing, and clear communication about incidents that is neither hyped up nor hi

Applications

Amortized Interventional Forecasting for Multivariate CIR Processes

arXiv:2608.03715v1 Announce Type: new Abstract: Mean-reverting dynamics are pervasive in finance, and the Cox--Ingersoll--Ross (CIR) process is a standard model for the time series they produce, from

applicationsarxiv-cs-lg

Agents

An Actionable Diagnosis of Multilingual, Multi-Agent Planning Failures

arXiv:2608.03735v1 Announce Type: cross Abstract: Multilingual multi-agent systems exhibit substantial degradation beyond English, yet prior work rarely identifies how task-critical information is los

agentsarxiv-cs-cl

ANCHOR-RE: An Agentic Neuro-Symbolic Framework for Grounded Biomedical Relation Extraction

arXiv:2608.03154v1 Announce Type: new Abstract: Biomedical relation extraction (BioRE) extracts structured knowledge from biomedical literature for applications such as knowledge base construction and

AnchorKV: Anchor-Residual KV Cache Compression

arXiv:2608.02901v1 Announce Type: cross Abstract: The key-value (KV) cache is the primary memory bottleneck in long-context LLM inference. Existing approaches attack it from opposite ends: eviction me

researcharxiv-cs-cl

ANNOTARES: A Dataset for Extracting Logical Structures from German Statutory Texts

arXiv:2608.03898v1 Announce Type: new Abstract: The automatic structural analysis of legal texts is a cornerstone of legal technology, yet the extraction of their logical components remains a signific

Tutorials

Announcing Discovery Loop! I am very excited to announce that, along with my longtime friends and collaborators @Sanjay_Ghemawat, @OriolViny…

tutorialsyohei-nakajima--x

Announcing Discovery Loop! I am very excited to announce that, along with my longtime friends and collaborators @Sanjay_Ghemawat, @OriolVinyalsML and @quocleix, we are founding Discovery Loop (@DiscoL

Another real-world manifestation of the kind of misaligned actions frontier systems developed by leading companies can take to achieve goals…

Another real-world manifestation of the kind of misaligned actions frontier systems developed by leading companies can take to achieve goals. Current frontier AI models are trained with reinforcement

safetyyoshua-bengio--x

Anthropic confirms it is building an in-house silicon team to design custom chips for Claude, co-designing hardware and models and using a 'multi-chip approach' (Tom Carter/Business Insider)

Tom Carter / Business Insider: Anthropic confirms it is building an in-house silicon team to design custom chips for Claude, co-designing hardware and models and using a “multi-chip approach” — - Anth

model-releasestechmeme

Local Ai

Any-OPD: Heterogeneous On-Policy Distillation for Flow-Matching Models via Representation-Space Bridging

arXiv:2608.03316v1 Announce Type: cross Abstract: On-policy distillation, in which a teacher corrects samples that the student itself generates, presupposes that the two models speak the same language

local-aiarxiv-cs-cv

Anyone interested in building a harness-only benchmark?

model-releasesr-localllama

There are a lot of LLM benchmarks but few, if any, harness benchmarks. I am thinking this would be a really good community project to build one. End goal: a leaderboard of harness performance (multipl

Approximate Speculative Decoding

arXiv:2608.03447v1 Announce Type: cross Abstract: Speculative decoding accelerates autoregressive generation by verifying a draft block with a target model in parallel. Under standard greedy verificat

ARCHead: Activation-Metric Residual Correction for Large Language Model Output Heads

arXiv:2608.02703v1 Announce Type: new Abstract: Weight-only quantization substantially reduces the storage of large language model (LLM) transformer blocks, but practical backends often retain the fin

researcharxiv-cs-cl

ArtECulture: Benchmarking Culture-Conditioned Visual Emotion Understanding in Multimodal Large Language Models

arXiv:2608.03358v1 Announce Type: new Abstract: Existing visual emotion understanding methods typically ignore cultural variations in emotional perception. We introduce culture-conditioned visual emot

AS-FedBridge: Pseudo-Spike Bridge Distillation for Heterogeneous ANN-SNN Federated Learning

model-releasesarxiv-cs-lg

arXiv:2608.03324v1 Announce Type: new Abstract: Federated learning enables collaborative model training across distributed edge devices while strictly preserving data privacy. To facilitate practical

Agents

Asking Questions the Right Way: A Multi-Agent Conversational System for Prompt Formulation in Complex Task Resolution

arXiv:2608.01366v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are integral to complex intellectual tasks, yet output quality remains constrained by user-provided prompts. Iter

agentsarxiv-cs-ai

Assessing speech quality metrics for evaluation of neural audio codecs under clean speech conditions

arXiv:2509.24457v1 Announce Type: cross Abstract: Objective speech-quality metrics are widely used to assess codec performance. However, for neural codecs, it is often unclear which metrics provide re

Assessing the Effect of Cross-Domain Mapping on Creativity in Humans and Large Language Models

arXiv:2603.19087v2 Announce Type: replace Abstract: Creativity is the ability to come up with novel ideas, a capacity crucial for human development and flourishing. Are large language models (LLMs) cr

Assessment of Conditional Diffusion Model for Synthetic Histopathology Image Generation

model-releasesarxiv-cs-lg

arXiv:2608.03990v1 Announce Type: new Abstract: Synthetic histopathology image generation has emerged as an approach that may address data scarcity in computational pathology, yet current evaluation m

ATFlash: Per-RoPE-Wavelength Attention Windows for Compute/Memory-Efficient LLM Inference

arXiv:2608.02947v1 Announce Type: cross Abstract: The attention score with rotary position embeddings (RoPE) decomposes exactly into a sum over its 2D-rotation frequency pairs, and each pair's wavelen

Attention is Case-Sensitive

arXiv:2608.03711v1 Announce Type: cross Abstract: In human visual perception, uppercase lettering serves as a natural salience cue that captures attention within lowercase text. In this paper, we pres

researcharxiv-cs-cl

Attribute-based Undetectable Watermarking for Generative AI Models

arXiv:2608.03174v1 Announce Type: cross Abstract: Generative AI systems increasingly produce content whose provenance is difficult to verify, motivating watermarking techniques for identifying model-g

Automated Visualization Code Synthesis via Multi-Path Reasoning and Feedback-Driven Optimization

arXiv:2502.11140v4 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have become a cornerstone for automated visualization code generation, enabling users to create charts through na

Automatic Patient-Specific Microwave Ablation Planning Accelerated by a Physics-Guided Deep Learning Model

arXiv:2608.03086v1 Announce Type: cross Abstract: Microwave ablation (MWA) is a promising minimally invasive treatment for liver tumors, but its therapeutic outcome strongly depends on patient-specifi

researcharxiv-cs-lg

Agents

Autoreflection: How Agentic Strange Loops Turn Human Culture into AI Infrastructure

arXiv:2608.03800v1 Announce Type: cross Abstract: An LLM-based agent is a loop that reads itself. Agentic frameworks externalize identity, memory, and disposition into editable files. The agent loads

agentsarxiv-cs-ai

Applications

AutoSND: From Execution Evidence to Structural Policies for Automated Network Dismantling Heuristic Discovery

arXiv:2608.03653v1 Announce Type: new Abstract: Network dismantling is fundamental to analyzing the robustness and vulnerability of complex systems, yet practical heuristics must balance effectiveness

applicationsarxiv-cs-ai

AWS partners with Anthropic and OpenAI to bring Continuum into coding tools

model-releasessiliconangle

Amazon Web Services Inc. today said it has partnered with Anthropic PBC and OpenAI Group PBC to wire AWS Continuum for code vulnerabilities directly into the tools developers write code in. The integr

b10276

Prefer npm ci over install for security (#26601) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramew

b10278

build : remove GGML_METAL_USE_BF16 from all build scripts (#26604) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel

b10280

vendor : apply patches for subprocess.h (#26606) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramew

b10282

server: Adding spec-decode counters to /metrics endpoint (#26389) server: add spec-decode counters to /metrics endpoint server: fixed review comments and now aligned param names exactly with vLLM. Web

b10284

fit: Fix memory allocation for MTP layers (#26605) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFram