When Quotes Crumble: Detecting Transient Mechanical Liquidity Erosion in Limit Order Books
arXiv:2604.21993v1 Announce Type: new
Abstract: We study the detection of transient liquidity erosion ("crumbling quotes") in electronic limit order books, where observable quote deterioration may reflect either mechanical liquidity withdrawal or informational repricing. Using the ABIDES agent-base...
Math Takes Two: A test for emergent mathematical reasoning in communication
arXiv:2604.21935v1 Announce Type: new
Abstract: Although language models demonstrate remarkable proficiency on mathematical benchmarks, it remains unclear whether this reflects true mathematical reasoning or statistical pattern matching over learning formal syntax. Most existing evaluations rely on...
An Artifact-based Agent Framework for Adaptive and Reproducible Medical Image Processing
arXiv:2604.21936v1 Announce Type: new
Abstract: Medical imaging research is increasingly shifting from controlled benchmark evaluation toward real-world clinical deployment. In such settings, applying analytical methods extends beyond model design to require dataset-aware workflow configuration and...
MolClaw: An Autonomous Agent with Hierarchical Skills for Drug Molecule Evaluation, Screening, and Optimization
arXiv:2604.21937v1 Announce Type: new
Abstract: Computational drug discovery, particularly the complex workflows of drug molecule screening and optimization, requires orchestrating dozens of specialized tools in multi-step workflows, yet current AI agents struggle to maintain robust performance and...
Read the Paper, Write the Code: Agentic Reproduction of Social-Science Results
arXiv:2604.21965v1 Announce Type: new
Abstract: Recent work has used LLM agents to reproduce empirical social science results with access to both the data and code. We broaden this scope by asking: Can they reproduce results given only a paper's methods description and original data? We develop an ...
Rethinking Publication: A Certification Framework for AI-Enabled Research
arXiv:2604.22026v1 Announce Type: new
Abstract: AI research pipelines now produce a growing share of publishable academic output, including work that meets existing peer-review standards for quality and novelty. Yet the publication system was built on the assumption of universal human authorship an...
Learn how Symphony, an open-source spec for Codex orchestration, turns issue trackers into always-on agent systems—boosting engineering output and reducing context switching.
I Reduced My Pandas Runtime by 95% — Here’s What I Was Doing Wrong
Most slow Pandas code "works", until it doesn't. Learn how to spot hidden bottlenecks, avoid costly row-wise operations, and know when Pandas is no longer enough.
The post I Reduced My Pandas Runtime by 95% — Here’s What I Was Doing Wrong appeared first on Towards Data Science.
Top 7 Benchmarks That Actually Matter for Agentic Reasoning in Large Language Models
As AI agents move from research demos to production deployments, one question has become impossible to ignore: how do you actually know if an agent is good? Perplexity scores and MMLU leaderboard numbers tell you very little about whether a model can navigate a real website, resolve a GitHub issue, ...
RAG Without Vectors: How PageIndex Retrieves by Reasoning
Retrieval is where most RAG systems quietly break. Traditional pipelines rely on vector similarity—embedding queries and document chunks into the same space and fetching the “closest” matches. But similarity is a weak proxy for what we actually need: relevance grounded in reasoning. In long, profess...
AI Weekly Issue #487: 100 years from now : The Allowance
This is 100 Years From Now, a weekly series. Once a week we skip a century and try to picture what life actually looks like when the stuff we're building now has had time to settle in.
This week: the billionaires who broke the economy want to pay you to shut up about it.
xAI Launches grok-voice-think-fast-1.0: Topping τ-voice Bench at 67.3%, Outperforming Gemini, GPT Realtime, and More
The new flagship voice model outperforms Gemini, GPT Realtime, and its own predecessor across retail, airline, and telecom workflows
The post xAI Launches grok-voice-think-fast-1.0: Topping τ-voice Bench at 67.3%, Outperforming Gemini, GPT Realtime, and More appeared first on MarkTechPost.
Anthropic created a test marketplace for agent-on-agent commerce
In a recent experiment, Anthropic created a classified marketplace where AI agents represented both buyers and sellers, striking real deals for real goods and real money.
A Coding Implementation on kvcached for Elastic KV Cache Memory, Bursty LLM Serving, and Multi-Model GPU Sharing
In this tutorial, we explore kvcached, a dynamic KV-cache implementation on top of vLLM, to understand how dynamic KV-cache allocation transforms GPU memory usage for large language models. We begin by setting up the environment and deploying lightweight Qwen2.5 models through an OpenAI-compatible A...
Google DeepMind Introduces Vision Banana: An Instruction-Tuned Image Generator That Beats SAM 3 on Segmentation and Depth Anything V3 on Metric Depth Estimation
A new Google paper argues that image generation pretraining is to computer vision what GPT-style pretraining is to NLP — and the benchmark numbers back that up.
The post Google DeepMind Introduces Vision Banana: An Instruction-Tuned Image Generator That Beats SAM 3 on Segmentation and Depth Anything...
Cursor V3 Explained: The AI Coding Agent That’s Replacing Traditional IDEs in 2026
In 2026, AI-powered coding tools began revolutionizing software development, with Cursor v3 emerging as a leading example. Unlike traditional development environments, Cursor v3 offers a new way for developers to interact with their code by utilizing AI agents that assist in coding tasks. Cursor v3 ...
Meet GitNexus: An Open-Source MCP-Native Knowledge Graph Engine That Gives Claude Code and Cursor Full Codebase Structural Awareness
Abhigyan Patwari's GitNexus has quietly crossed 19,000 GitHub stars by solving a problem every AI-assisted developer has hit but rarely named — agents that edit code they don't actually understand.
The post Meet GitNexus: An Open-Source MCP-Native Knowledge Graph Engine That Gives Claude Code and Cu...
Escaping the Agreement Trap: Defensibility Signals for Evaluating Rule-Governed AI
arXiv:2604.20972v1 Announce Type: new
Abstract: Content moderation systems are typically evaluated by measuring agreement with human labels. In rule-governed environments this assumption fails: multiple decisions may be logically consistent with the governing policy, and agreement metrics penalize ...
Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks
arXiv:2604.20987v1 Announce Type: new
Abstract: Long horizon interactive environments are a testbed for evaluating agents skill usage abilities. These environments demand multi step reasoning, the chaining of multiple skills over many timesteps, and robust decision making under delayed rewards and ...
Value-Conflict Diagnostics Reveal Widespread Alignment Faking in Language Models
arXiv:2604.20995v1 Announce Type: new
Abstract: Alignment faking, where a model behaves aligned with developer policy when monitored but reverts to its own preferences when unobserved, is a concerning yet poorly understood phenomenon, in part because current diagnostic tools remain limited. Prior d...
arXiv:2604.21003v1 Announce Type: new
Abstract: AI agents are increasingly deployed on complex, domain-specific workflows -- navigating enterprise web applications that require dozens of clicks and form fills, orchestrating multi-step research pipelines that span search, extraction, and synthesis, ...