Knowledge catalogue
arXiv:2604.27045v1 Announce Type: cross Abstract: As Large Language Model (LLM) agents transition from single-session tools to persistent systems managing longitudinal healthcare journeys, their memor
arXiv:2604.27283v1 Announce Type: cross Abstract: Large language model (LLM)-based coding agents increasingly rely on external memory to reuse prior debugging experience, repair traces, and repository
Twitter said pick a side. The eval said the question was wrong. Six months ago, MCP (model context protocol) was the hot new thing: tool usage with a built-in discovery... The post MCP vs. CLI Skills
Harnesses If you've used Claude Code or Codex, you've used a harness. A harness is the infrastructure layer that wraps an AI coding agent and decides how it operates, what it can touch, and how you me
arXiv:2604.26106v1 Announce Type: new Abstract: Forecasting benchmarks produce accuracy leaderboards but little insight into why some forecasters are more accurate than others. We introduce Bench to t
arXiv:2511.02399v2 Announce Type: replace-cross Abstract: Recent advances in large language model agents offer the promise of automating end-to-end software development from natural language requireme
arXiv:2604.17612v2 Announce Type: replace-cross Abstract: Multi-agent systems built on large language models (LLMs) are difficult to reason about. Coordination errors such as deadlocks or type-mismatc
arXiv:2508.01875v4 Announce Type: replace Abstract: Real-time streaming video understanding in domains such as autonomous driving and intelligent surveillance poses challenges beyond conventional offl
Information technology management software provider Auvik Networks Inc. today announced the launch of Auvik Aurora: artificial intelligence-powered IT agents that are designed to help IT professionals
Databricks and Stripe have collaborated on infrastructure projects designed to support AI agents, likely focusing on data processing and payment integration capabilities. The initiative demonstrates h
arXiv:2604.25067v1 Announce Type: cross Abstract: Forecasting when AI systems will become capable of meaningfully accelerating AI research is a central challenge for AI safety. Existing benchmarks mea
arXiv:2603.26041v3 Announce Type: replace Abstract: In recent years, GUI visual agents built upon Multimodal Large Language Models (MLLMs) have demonstrated strong potential in navigation tasks. Howev
DeepSeek-V4 is an advanced language model featuring a million-token context window that enables practical agentic applications beyond simple retrieval. The model demonstrates improved efficiency and u
Artificial intelligence and data security company Cyera Ltd. announced today that it has acquired Ryft Data Inc., an Israeli startup with an automated data lake platform designed for enterprises deplo
Meta employees' activity at work is now being used to train the company's AI agents. As reported by Reuters, Meta is installing a tool it calls Model Capability Initiative (MCI) on US-based employees'
Artificial intelligence and machine learning have been a central focus for Boomi LP over much of its 26 years as a data activation company. The organization began storing anonymized metadata from cust
Let's talk parsing charts 📊📈. Last week we released ParseBench, the first document OCR benchmark for AI agents. New in ParseBench: ChartDataPointMatch. Most document look at a chart and OCR the captio
arXiv:2604.15715v1 Announce Type: cross Abstract: The development of general-purpose agents requires a shift from executing simple instructions to completing complex, real-world productivity workflows
arXiv:2604.15671v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have demonstrated significant potential for embodied decision-making; however, their application in complex chemical
arXiv:2604.15505v1 Announce Type: cross Abstract: LLM agents operating under organizational policies must comply with authorization constraints typically specified in natural language. In practice, su
We recently shipped quality-of-life improvements to the Cursor CLI to make working with agents in the terminal more delightful. Use /debug to find root causes and fix tricky bugs that are hard to repr
arXiv:2604.14267v1 Announce Type: new Abstract: Search agents extend Large Language Models (LLMs) beyond static parametric knowledge by enabling access to up-to-date and long-tail information unavaila
LLM agents loop, drift, and get stuck on hard reasoning tasks up to 30% of the time. Current fixes are either too blunt (hard step limits) or too expensive (LLM-as-judge adding 10-15% overhead per ste
Anna Tong / Forbes: AI labs are buying Slack, Jira, and email archives from defunct startups to build “reinforcement learning gyms” and train AI agents in simulated workplaces — Defunct startups are b
arXiv:2604.13072v1 Announce Type: new Abstract: LLM-based agents are increasingly expected to handle real-world assistant tasks, yet existing benchmarks typically evaluate them under isolated sources
`deepagents deploy` now supports user scoped memory! add a user/ directory in your project so each user gets their own writable AGENTS.md, seeded on first deploy and persisted across conversations. yo
arXiv:2604.12948v1 Announce Type: new Abstract: LLM agents with persistent memory store information as flat factual records, providing little context for temporal reasoning, change tracking, or cross-
arXiv:2604.12290v1 Announce Type: new Abstract: Current LLM agent benchmarks, which predominantly focus on binary pass/fail tasks such as code generation or search-based question answering, often negl
arXiv:2604.12177v1 Announce Type: new Abstract: LLM-based agents can execute actions that are syntactically valid, user-sanctioned, and semantically appropriate, yet still violate organizational polic
John Collison / Cheeky Pint: Q&A with ElevenLabs co-founder Mati Staniszewski on how audio models work, the company's business model, the conversational Turing Test, voice agents, and more — Mati Stan
Aaron Holmes / The Information: Microsoft says it is “exploring the potential of technologies like OpenClaw in an enterprise context”, including a team of always-on agents within Microsoft 365 — As Mi
arXiv:2604.08988v1 Announce Type: new Abstract: Current LLM-based agents demonstrate strong performance in episodic task execution but remain constrained by static toolsets and episodic amnesia, faili
arXiv:2604.07831v1 Announce Type: cross Abstract: Existing red-teaming studies on GUI agents have important limitations. Adversarial perturbations typically require white-box access, which is unavaila
we are doing this podcast specifically to highlight the innermost details of building agents in production may be a little niche, but its a niche i like 🤷♂️ @hwchase17 Great content, really appreciat
what he said 🗣️ the very best agents today obsessively tailor the harness layer around the model I’m looking at you “5 things I learned from the Claude code leak” bros 👀 orchestration patterns, tool d
Artificial intelligence is proving to be a big bet for many companies across the enterprise landscape, and the gamblers are getting nervous. A survey of 2,400 global employees and C-suite leaders rele
1Password says 90 finance staff built 21 agents in an internal hackathon and reports 5–10 hours saved per person weekly; method is not supplied.
arXiv:2610.21270v1 Announce Type: new Abstract: Trustworthy biomedical AI requires reliable action selection when evidence is missing, stale, conflicting, or late, not only accurate answers on static
arXiv:2610.21496v1 Announce Type: new Abstract: Reliable repository-level coding requires agents not only to generate correct code but also to preserve constraints and respond to tool feedback across
arXiv:2606.17029v2 Announce Type: replace Abstract: Deep research agents synthesize long-form reports by searching and reasoning over retrieved evidence. Reinforcement learning with rubric-based rewar
arXiv:2610.19822v1 Announce Type: cross Abstract: LLM agents are evolving from a single model calling tools to planners that orchestrate multiple expert models whose capabilities live in distinct weig
arXiv:2610.19712v1 Announce Type: new Abstract: Multi-session agents can switch between LLMs to balance performance and inference cost. Such switches require transferring a history for continuity, yet
.@NVIDIA Nemotron 3.5 Super VL is now live on Together AI. An open-weight multimodal model built for visual reasoning and always-on agents that see, reason, and act across documents, screens, and vide
NVIDIA’s open‑source Nemotron 3.5 Super VL is a 120 B parameter mixture‑of‑experts multimodal model that activates only 12 B parameters per token, enabling combined reasoning, instruction following, t
arXiv:2610.16778v1 Announce Type: cross Abstract: Cloud graphical user interface (GUI) agents send instructions and screenshots to remote planners, exposing personally identifiable information (PII).
arXiv:2610.20390v1 Announce Type: new Abstract: With the rapid development of vision-language models (VLMs), Web-GUI agents have achieved promising performance in interacting with real-world interface
arXiv:2610.18548v1 Announce Type: new Abstract: Language and vision language models can support autonomous systems, but changing operating conditions may compromise the reliability of their semantic o
arXiv:2610.18082v1 Announce Type: new Abstract: Long-horizon agents often struggle to recover from failures whose causes lie several steps earlier, beyond what local reflection or backtracking can res
arXiv:2610.17685v1 Announce Type: cross Abstract: Enterprise agents face safety risks that cannot be determined from individual actions alone. Existing safety benchmarks largely evaluate action-local
arXiv:2610.17444v1 Announce Type: new Abstract: Language model (LM) agents can fail for different reasons, requiring different explanations and interventions. We study how state beliefs, action values
arXiv:2610.12828v1 Announce Type: new Abstract: Outcome-supervised group-relative policy optimization (GRPO) assigns the same advantage to every token in an LLM agent trajectory, leaving useful and un
arXiv:2610.11007v1 Announce Type: new Abstract: At the start of every session, LLM agents load a fixed context file, such as exttt{AGENTS.md}. Each loaded token in the file is charged again in every l
arXiv:2609.34565v2 Announce Type: replace Abstract: Long-horizon tasks require LLM agents to continually draw on information from earlier interactions. However, retaining the full history increases co
arXiv:2610.12274v1 Announce Type: new Abstract: Text-to-SQL models are commonly trained to map questions directly to static queries, whereas real-world database agents operate through stateful, multi-
arXiv:2610.11030v1 Announce Type: cross Abstract: Tool-using LLM agents violate the policies they are deployed to enforce, often silently. Prior defenses hand-write rules, query an LLM verifier per ac
arXiv:2610.12403v1 Announce Type: cross Abstract: Skill-augmented agents improve sample efficiency by distilling successful trajectories into reusable strategies. Yet most existing approaches remain t
arXiv:2610.10285v1 Announce Type: cross Abstract: In the wake of the increasingly public discussion about AI alignment, recent work has tried to propose specific AI architectures that behave safely. H
arXiv:2610.08862v1 Announce Type: cross Abstract: Household robots must accommodate new user instructions while executing ongoing tasks. Existing agents often regenerate or extensively revise the rema
arXiv:2610.10332v1 Announce Type: new Abstract: Learning from large-model demonstrations offers a way to train small agents that can complete recurring tasks without calling a large model at every ste
arXiv:2610.07614v1 Announce Type: new Abstract: We evaluate whether AI agents can match the reported findings of published biomedical studies using public data. Existing evaluations do not consistentl