Your daily dose of AI context engineering news and research
April 02, 2026 • Generated 20:13 UTC
"Context engineering is the delicate art and science of filling the context window with just the right information for the next step." — Andrej Karpathy. A frontier, first-principles handbook inspired by Karpathy and 3Blue1Brown for moving beyond prompt engineering to the wider discipline of context design, orchestration, and optimization.
arXiv:2604.00002v1 Announce Type: new Abstract: Here we introduce the Olfactory Perception (OP) benchmark, designed to assess the capability of large language models (LLMs) to reason about smell. The benchmark contains 1,010 questions across eight task categories spanning odor classification, odor ...
arXiv:2604.00006v1 Announce Type: new Abstract: AI-powered recruitment tools are increasingly adopted in personnel selection, yet they struggle to capture the requisition (req)-specific personal competencies (PCs) that distinguish successful candidates beyond job categories. We propose a large lang...
arXiv:2604.00085v1 Announce Type: new Abstract: Large language models applied to clinical prediction exhibit case-level heterogeneity: simple cases yield consistent outputs, while complex cases produce divergent predictions under minor prompt changes. Existing single-agent strategies sample from on...
arXiv:2604.00281v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly embedded in computer science education through AI-assisted programming tools, yet such workflows often exhibit objective drift, in which locally plausible outputs diverge from stated task specifications. E...
arXiv:2604.00072v1 Announce Type: new Abstract: Can classifier-based safety gates maintain reliable oversight as AI systems improve over hundreds of iterations? We provide comprehensive empirical evidence that they cannot. On a self-improving neural controller (d=240), eighteen classifier configura...
Official implementation for the paper: "Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering""
The ultimate all-in-one guide to mastering Claude Code. From setup, prompt engineering, commands, hooks, workflows, automation, and integrations, to MCP servers, tools, and the BMAD method—packed with step-by-step tutorials, real-world examples, and expert strategies to make this the global go-to repo for Claude mastery.
Optimizing inference proxy for LLMs
arXiv:2604.00003v1 Announce Type: new Abstract: This study evaluates the reliability of information extraction approaches from KRS documents using three strategies: LLM only, Hybrid Deterministic - LLM (regex + LLM), and a Camelot based pipeline with LLM fallback. Experiments were conducted on 140 ...
arXiv:2604.00008v1 Announce Type: new Abstract: As qualitative researchers show growing interest in using automated tools to support interpretive analysis, a large language model (LLM) is often introduced into an analytic workflow as is, without systematic evaluation of interpretive quality or comp...
arXiv:2604.00009v1 Announce Type: new Abstract: We present the design rationale, implementation attempt, and failure analysis of Eyla, a proposed identity-anchored LLM architecture that integrates biologically-inspired subsystems -- including HiPPO-initialized state-space models, zero-initialized a...
arXiv:2604.00010v1 Announce Type: new Abstract: Large language models cannot estimate how long their own tasks take. We investigate this limitation through four experiments across 68 tasks and four model families. Pre-task estimates overshoot actual duration by 4--7$\times$ ($p < 0.001$), with mode...
arXiv:2604.00012v1 Announce Type: new Abstract: Despite the impressive performance of general-purpose large language models (LLMs), they often require fine-tuning or post-training to excel at specific tasks. For instance, large reasoning models (LRMs), such as the DeepSeek-R1 series, demonstrate st...
arXiv:2604.00005v1 Announce Type: new Abstract: Emotion plays an important role in human cognition and performance. Motivated by this, we investigate whether analogous emotional signals can shape the behavior of large language models (LLMs) and agents. Existing emotion-aware studies mainly treat em...
arXiv:2604.00249v1 Announce Type: new Abstract: Single-agent large language model (LLM) systems struggle to simultaneously support diverse conversational functions and maintain safety in behavioral health communication. We propose a safety-aware, role-orchestrated multi-agent LLM framework designed...
arXiv:2604.00074v1 Announce Type: new Abstract: Accurate prediction of evacuation behavior is critical for disaster preparedness, yet models trained in one region often fail elsewhere. Using a multi-state hurricane evacuation survey, we show this failure goes beyond feature distribution shift: hous...
arXiv:2604.00362v1 Announce Type: new Abstract: No one has independently reproduced OpenAI's published scores for gpt-oss-20b with tools, because the original paper discloses neither the tools nor the agent harness. We reverse-engineered the model's in-distribution tools: when prompted without tool...
arXiv:2604.00050v1 Announce Type: new Abstract: Federated Learning (FL) has emerged as a promising technique for training language models on distributed and private datasets of diverse tasks. However, aggregating models trained on heterogeneous tasks often degrades the overall performance of indivi...
arXiv:2604.00069v1 Announce Type: new Abstract: Artificial intelligence is transforming molecular and materials science, but its growing computational and data demands raise critical sustainability challenges. In this Perspective, we examine resource considerations across the AI-driven discovery pi...
arXiv:2604.00066v1 Announce Type: new Abstract: Although Deep Reinforcement Learning has proven highly effective for complex decision-making problems, it demands significant computational resources and careful parameter adjustment in order to develop successful strategies. Evolution strategies offe...
arXiv:2604.00094v1 Announce Type: new Abstract: Machine learning is increasingly used to improve decisions within branch-and-bound algorithms for mixed-integer programming. Many existing approaches rely on deep learning, which often requires very large training datasets and substantial computationa...
arXiv:2604.00004v1 Announce Type: new Abstract: The extension of context windows in Large Language Models is typically facilitated by scaling positional encodings followed by lightweight Continual Pre-Training (CPT). While effective for processing long sequences, this paradigm often disrupts origin...
arXiv:2604.00284v1 Announce Type: new Abstract: We formally introduce a improvisational wordplay game called Connections to explore reasoning capabilities of AI agents. Playing Connections combines skills in knowledge retrieval, summarization and awareness of cognitive states of other agents. We sh...
arXiv:2604.00067v1 Announce Type: new Abstract: An agent that operates sequentially must incorporate new experience without forgetting old experience, under a fixed memory budget. We propose a framework in which memory is not a parameter vector but a stochastic process: a Bridge Diffusion on a repl...
OpenViking is an open-source context database designed specifically for AI Agents(such as openclaw). OpenViking unifies the management of context (memory, resources, and skills) that Agents need through a file system paradigm, enabling hierarchical context delivery and self-evolving.
arXiv:2604.00007v1 Announce Type: new Abstract: We present Dynin-Omni, the first masked-diffusion-based omnimodal foundation model that unifies text, image, and speech understanding and generation, together with video understanding, within a single architecture. Unlike autoregressive unified models...
arXiv:2604.00319v1 Announce Type: new Abstract: We develop algorithms for collaborative control of AI agents and critics in a multi-actor, multi-critic federated multi-agent system. Each AI agent and critic has access to classical machine learning or generative AI foundation models. The AI agents a...
[NeurIPS 2025] PyTorch implementation of [ThinkSound], a unified framework for generating audio from any modality, guided by Chain-of-Thought (CoT) reasoning.
A framework designed to manage context, dependencies, and tasks in large-scale Cline projects within VS Code
arXiv:2604.00013v1 Announce Type: new Abstract: Multimodal sentiment analysis aims to understand human emotions by integrating textual, auditory, and visual modalities. Although Multimodal Large Language Models (MLLMs) have achieved state-of-the-art performance via supervised fine-tuning (SFT), the...
📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
Cosmos-Reason1 models understand the physical common sense and generate appropriate embodied decisions in natural language through long chain-of-thought reasoning processes.
Open source platform for AI Engineering: OpenTelemetry-native LLM Observability, GPU Monitoring, Guardrails, Evaluations, Prompt Management, Vault, Playground. 🚀💻 Integrates with 50+ LLM Providers, VectorDBs, Agent Frameworks and GPUs.
arXiv:2604.00356v1 Announce Type: new Abstract: Agentic applications based on large language models increasingly rely on multi-step interaction loops involving planning, action execution, and environment feedback. While such systems are now deployed at scale, improving them post-deployment remains ...
Expose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth!
arXiv:2604.00137v1 Announce Type: new Abstract: Tool-integrated LLMs can retrieve, compute, and take real-world actions via external tools, but reliability remains a key bottleneck. We argue that failures stem from both tool-use accuracy (how well an agent invokes a tool) and intrinsic tool accurac...
arXiv:2604.00414v1 Announce Type: new Abstract: LLM systems must make control decisions in addition to generating outputs: whether to answer, clarify, retrieve, call tools, repair, or escalate. In many current architectures, these decisions remain implicit within generation, entangling assessment a...
The conversational control layer for customer-facing AI agents - Parlant is a context-engineering framework optimized for controlling customer interactions.
arXiv:2604.00001v1 Announce Type: new Abstract: Gradient-based data selection offers a principled framework for estimating sample utility in large language model (LLM) fine-tuning, but existing methods are mostly designed for offline settings. They are therefore less suited to online fine-tuning, w...
Build effective agents using Model Context Protocol and simple workflow patterns
KAG is a logical form-guided reasoning and retrieval framework based on OpenSPG engine and LLMs. It is used to build logical reasoning and factual Q&A solutions for professional domain knowledge bases. It can effectively overcome the shortcomings of the traditional RAG vector similarity calculation model.
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"
A modular graph-based Retrieval-Augmented Generation (RAG) system
Build, Evaluate, and Optimize AI Systems. Includes evals, RAG, agents, fine-tuning, synthetic data generation, dataset management, MCP, and more.
SoTA production-ready AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.
Open-source context retrieval layer for AI agents
arXiv:2604.00076v1 Announce Type: new Abstract: Reinforcement Learning (RL) agents often struggle with efficiency and performance in complex environments. We propose a novel framework that uses a Large Language Model (LLM) to dynamically generate a curriculum over available actions, enabling the ag...
arXiv:2604.00132v1 Announce Type: new Abstract: We develop a machine learning (ML) surrogate model to approximate solutions to Maxwell's equations in one dimension, focusing on scenarios involving a material interface that reflects and transmits electro-magnetic waves. Derived from high-fidelity Fi...