Knowledge catalogue
arXiv:2609.03718v1 Announce Type: cross Abstract: Computer-aided engineering (CAE) simulation is among the largest and most demanding areas of engineering, where setting up a solver such as OpenFOAM,
Banger paper from BAAI. If you are building research agents, this one is worth your time. (bookmark it) They find that adding skills scores 134.3% higher on MLE-bench, 34.4% higher on PaperBench, 9.2%
arXiv:2609.00823v1 Announce Type: new Abstract: Long-horizon tool-use agents need not only to search and plan, but also to decide when to finalize. We study late-stage pressure states, in which an age
arXiv:2609.00546v1 Announce Type: cross Abstract: Agent systems are commonly described by the model and harness that currently produce their behavior. That boundary is useful for one execution but und
Brilliant paper on reducing reward hacking in agents. If you follow the recent OpenAI <> HuggingFace incident, you might want to check this paper out. (bookmark it) The usual response to reward hackin
arXiv:2608.30322v1 Announce Type: new Abstract: Professional agent tasks often depend on conventions that are absent from public corpora, yet benchmarks rarely control whether an agent has access to t
arXiv:2608.30165v1 Announce Type: cross Abstract: Scientific progress depends not only on finding solutions, but on learning the rules that explain why they work and using that understanding to design
arXiv:2608.30362v1 Announce Type: new Abstract: As LLM agents take real-world actions through tools, indirect prompt injection (IPI) has emerged as a serious threat. The standard metric, Attack Succes
arXiv:2608.26867v1 Announce Type: new Abstract: Large language model agents reason, call tools, and act autonomously over many steps, but their agentic skills-correctly sequencing tools, planning unde
arXiv:2608.26530v1 Announce Type: new Abstract: Long-horizon agent runs generate experience that can improve both the current run and future work. Most self-improvement methods process this experience
arXiv:2608.26221v1 Announce Type: cross Abstract: As generative AI gains traction, researchers are investigating its potential to serve as proxies for humans. From undergoing cognitive psychology expe
arXiv:2608.25570v1 Announce Type: new Abstract: Hardware kernel optimization requires repeated compilation, correctness testing, profiling, and revision. LLM agents can automate parts of this process,
arXiv:2608.26081v1 Announce Type: cross Abstract: Collective intelligence can emerge when individuals coordinate through a shared environment, allowing local actions to accumulate into durable social
IBM has released Granite 4.2, an open‑source agentic AI model that adds native reasoning, tool use, coding instruction following and speech capabilities to enterprise agents. The suite of pre‑built mo
arXiv:2608.18312v1 Announce Type: new Abstract: Autonomous scientific agents now increasingly propose ideas, write code, run experiments, analyze results, and even draft papers. Observe and audit thos
arXiv:2608.18508v1 Announce Type: cross Abstract: We are witnessing an explosion of agentic systems for computational chemistry simulations: from half a dozen in 2024 to a dozen in 2025, and the curre
arXiv:2608.17433v1 Announce Type: new Abstract: LLM agents have been widely adopted to operate mission-critical infrastructure (MCI). These agents normally rely on a harness that determines what infor
arXiv:2608.17499v1 Announce Type: new Abstract: User-facing tool agents must coordinate dialogue and tool use as user goals unfold over multiple turns. Yet interactive reinforcement learning typically
arXiv:2604.05485v2 Announce Type: replace Abstract: LLM agents call tools, query databases, delegate tasks, and trigger external side effects. Once an agent system can act in the world, the question i
If you write rules in an AGENTS.md, this one is worth your time. When a coding agent follows your rule, it may have been going to do that anyway. Harness-IF separates the two by scoring 256 rules one
arXiv:2608.06811v1 Announce Type: cross Abstract: Resolving a real software issue with a large language model (LLM) agent is a long repair episode, often tens to hundreds of steps spanning exploration
nOps rebuilt its Clara FinOps AI agent on Amazon Bedrock AgentCore, replacing a self-managed Amazon EKS stack running LangChain and LangGraph. The move cut time-to-production by 75% (from 10-12 months
arXiv:2608.02650v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly rely on external tools to complete complex real-world tasks. However, reliable tool-use planning remains
arXiv:2608.00339v1 Announce Type: cross Abstract: AI agents increasingly perform open-ended tasks in settings where their conclusions can guide consequential decisions. We provide evidence that AI age
arXiv:2608.02358v1 Announce Type: new Abstract: To operate robustly in open-world environments, autonomous agents should be able to infer the behavior of unfamiliar systems through interaction alone,
arXiv:2608.02499v1 Announce Type: cross Abstract: Real-world software development requires coding agents to operate in shared workspaces where users may inspect and modify code during an ongoing task,
arXiv:2607.28229v1 Announce Type: new Abstract: The web is increasingly accessed by AI agents rather than humans. Every agent needs knowledge, especially in the life-sciences, where agentic pipelines
arXiv:2606.13317v2 Announce Type: replace Abstract: Skill self-evolution methods for LLM agents aim to turn execution trajectories into reusable skill documents. However, current pipelines typically d
arXiv:2607.23588v1 Announce Type: new Abstract: Creative AI is moving from single-step asset generation toward long-horizon multimodal production. Although recent generative models can synthesize high
arXiv:2510.24411v3 Announce Type: replace Abstract: Computer-using agents powered by Vision-Language Models (VLMs) have demonstrated human-like capabilities in operating digital environments like mobi
arXiv:2510.24668v2 Announce Type: replace Abstract: Language agents have demonstrated remarkable potential in web search and information retrieval. However, many search-agent benchmarks assume that us
arXiv:2607.12397v1 Announce Type: new Abstract: LLM agents act in external environments where each action changes the state that later decisions condition on, and where a single wrong step can waste i
arXiv:2607.07548v1 Announce Type: new Abstract: Large language model based search agents increasingly adopt multi-agent architectures in which a main agent decomposes a complex question into sub-queri
arXiv:2606.24893v1 Announce Type: new Abstract: For agents to learn continuously from interaction with the world at test time, they must be able to explore effectively, acquire new world knowledge and
arXiv:2606.04903v1 Announce Type: cross Abstract: We introduce the LLM agent architecture Agentic Redux, intended for use with nontrivial problem domains that require linear auditability. Using the ty
Merge API Inc., a platform provider delivering connective infrastructure for artificial intelligence to business data and tools, launched Agent Handler for Employees, easing the strain on information
Robinhood Markets Inc. today opened its trading and banking platforms to artificial intelligence agents, launching a beta Agentic Trading product and a virtual Agentic Credit Card that can place stock
arXiv:2605.23263v1 Announce Type: cross Abstract: Embodied agents, which couple intelligent decision-making with physical actuation in the real world, impose far more stringent and heterogeneous commu
arXiv:2602.00979v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly deployed as educational agents for automatic short answer grading (ASAG) in real-world education
arXiv:2605.23146v1 Announce Type: cross Abstract: Classical reinforcement learning assumes the agent interacts with a fixed environment whose behavior does not depend on the agent's policy. This assum
Enterprises have figured out how to stand up AI agents, but agent management is another problem entirely. The agentic moment is forcing organizations to interrogate everything, including the operating
brain dump of how/why we use Evals to measure agents before & after shipping to prod 1. Good Evals simulate what our real users will do and encounter. They’re not really random benchmark tasks, they r
arXiv:2605.09018v1 Announce Type: cross Abstract: We introduce Evolutionary Ensemble (EvE), a decentralized framework that organizes existing, highly capable coding agents into a live, co-evolving sys
arXiv:2605.08580v1 Announce Type: cross Abstract: To cope with the large contexts that long-horizon LLM agents produce, modern frameworks increasingly rely on compaction -- invoking an LLM to rewrite
arXiv:2605.09104v1 Announce Type: new Abstract: As LLM agents evolve, tokens have emerged as the core economic primitives of Agentic AI. However, their exponential consumption introduces severe comput
arXiv:2605.06869v1 Announce Type: new Abstract: AI agent research spans a wide spectrum: from RL agents that learn from scratch to foundation model agents that leverage pre-trained knowledge, yet no u
arXiv:2510.25224v3 Announce Type: replace Abstract: While Large Language Models (LLMs) are increasingly used in agentic frameworks to assist individual users, there is a growing need for agents that c
this is the part of the deep agents production series i've been most excited to get to: sandboxes without an execution environment, a production agent is only as capable as its fixed toolset. give an
arXiv:2605.01986v1 Announce Type: new Abstract: What if the twelve jurors of Sidney Lumet's 12 Angry Men (1957) were not men, but large language models? Would the one juror who disagrees still be able
arXiv:2604.25847v1 Announce Type: cross Abstract: Optimization modeling underpins real-world decision-making in logistics, manufacturing, energy, and public services, but reliably solving such problem
arXiv:2604.19775v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed as autonomous agents capable of reasoning, planning, and acting within interactive environments.
When we launched Microsoft Agent Framework last October, we made a promise: building production-grade AI agents should feel as natural and structured as building any other software. Today, we’re deliv
arXiv:2511.11793v3 Announce Type: replace Abstract: We present MiroThinker v1.0, an open-source research agent designed to advance tool-augmented reasoning and information-seeking capabilities. Unlike
arXiv:2604.18860v1 Announce Type: cross Abstract: GUI agents that control desktop computers via screenshot-and-click loops introduce a new class of vulnerability: the observation-to-action gap (mean 6
arXiv:2604.18271v1 Announce Type: new Abstract: As the world of agentic artificial intelligence applied to robotics evolves, the need for agents capable of building and retrieving memories and observa
Zero-trust security startup Zero Networks Ltd. today announced the launch of AI Segmentation, a set of platform capabilities designed to give enterprises identity-based control over autonomous artific
Nice paper from Google. And a great application of AI agents. Wearables capture a staggering amount of physiological signals every day. CoDaS is an AI co-data-scientist that turns raw wearable sensor
This might be the most important score your website will ever get. Agents are about to become the #1 source of traffic on the internet. Sites that aren't ready will disappear. http://orank.ai spawns r
arXiv:2511.09149v4 Announce Type: replace Abstract: While natural language is the de facto communication medium for LLM-based agents, it presents a fundamental constraint. The process of downsampling
Certinia Inc. wants to transform the professional services industry with artificial intelligence — tasking teams of AI agents to work alongside employees. The company operates a Salesforce-native clou