Knowledge catalogue
arXiv:2609.38288v1 Announce Type: new Abstract: We present AREX-2, an effort to advance the self-improving capability of LLM agents, which we define as the ability to iteratively refine a solution at
Cybersecurity startup Armadin Inc. today announced that it has raised 255.5 million in funding at a valuation exceeding 2.5 billion. Andreessen Horowitz and Accel co-led the Series B round. They were
arXiv:2609.40353v1 Announce Type: new Abstract: The task of 3D assembly requires translating an understanding of parts and their relationships into precise spatial arrangements. Can pretrained general
arXiv:2609.40097v1 Announce Type: new Abstract: Existing auto-research benchmarks often entangle multiple sources of improvement, including training frameworks, hyperparameters, compute budgets, and d
Amazon Web Services Inc.’s Strands Labs team has been playing around with an emerging class of lightweight artificial intelligence systems known as “decision models,” and it’s now making the fruits of
Banger paper from Meta and colleagues. (bookmark it) They discuss benefits of giving your agent write access to its own context. In other words, they investigate how effective it is to allow a languag
arXiv:2609.38527v1 Announce Type: new Abstract: This work evaluates the direct transfer of a co-evolved communication protocol from a 2D simulation to a 3D physical environment, without retraining the
arXiv:2609.39342v1 Announce Type: cross Abstract: Intrinsic motivation plays a central role in adaptive and goal-directed behavior by conferring agents reward-independent objectives and biases useful
arXiv:2609.39958v1 Announce Type: new Abstract: Corporate and investment banking teams use presentations to support credit decisions and advise clients on financing and transactions. Producing these d
arXiv:2609.39473v1 Announce Type: new Abstract: Autonomous agents increasingly rely on memory to generalize beyond their training environments. However, agents are bounded by what they have seen and b
arXiv:2609.39112v1 Announce Type: new Abstract: Camera traps accumulated vast, multidimensional data for wildlife monitoring, yet translating raw media archives into meaningful ecological insights rem
arXiv:2609.39065v1 Announce Type: cross Abstract: LLM agents increasingly rely on installable skills, which are packages of instructions, code, and resources that equip them with task-specific capabil
arXiv:2609.38812v1 Announce Type: new Abstract: Terminal agents rely on self-verification to assess and correct their solutions as they solve tasks through interaction with command-line environments.
arXiv:2609.39131v1 Announce Type: new Abstract: Large language model (LLM) serving requires substantial memory to store model weights and KV caches. As models grow larger and contexts become longer, m
Check out jes: An open source real-time guardrails for AI agents, powered by decision models like Jev from @typesafeai Built to guard every step in the agent trajectory: prompts, tool calls, tool resu
Code review has to change for coding agents. Why? For me, it’s about scaling coding reviews while ensuring quality. If you give a coding agent one task, it can return several pull requests across diff
arXiv:2609.39081v1 Announce Type: cross Abstract: We spent five weeks using an LLM coding agent on open problems in coding theory: finding large sets of four-letter words, such as DNA barcodes, that s
arXiv:2609.38662v1 Announce Type: cross Abstract: Recursive self-improvement (RSI) lets a system improve from its own outcomes; in LLM-based multi-agent systems, Agents refine one another within a tas
arXiv:2609.39542v1 Announce Type: new Abstract: This report examines and compares some of the many fine tuning and prompting methods existing, applying them within the domain of autonomous driving. Th
arXiv:2609.38912v1 Announce Type: new Abstract: Agent harnesses govern how large language models (LLMs) gather context, invoke tools, verify results, preserve state, and terminate, largely affecting a
arXiv:2609.39933v1 Announce Type: new Abstract: When designing machine learning models, desirable properties are often in tension: improving one behavior can impair another, so task progress can depen
arXiv:2609.40284v1 Announce Type: cross Abstract: Computer use agents (CUAs), which use graphical user interfaces (GUIs) to complete tasks on a computer, have recently surpassed human performance on m
An AI agent uses compute differently than a traditional application. Over a single session, it writes and runs code, calls a model, and waits on a tool or a person before picking the work back up. As
arXiv:2609.39559v1 Announce Type: new Abstract: In this work we study the problem of MAPFC, a post-optimization step for Multi-Agent Path Finding (MAPF) plans where we are given a feasible plan produc
arXiv:2609.39148v1 Announce Type: new Abstract: AI agents can externalize what they learn from past tasks into reusable skills, such as procedures, checklists, code, or other executable artifacts, tha
arXiv:2609.38536v1 Announce Type: cross Abstract: Diffusion-based large language models (dLLMs) promise to break the sequential latency bottleneck of autoregressive agents through parallel decoding, b
arXiv:2609.38437v1 Announce Type: new Abstract: Teleoperation systems are tuned for channel fidelity, while whether the operator experiences the device as part of the body, the Sense of Embodiment (So
arXiv:2603.01209v3 Announce Type: replace Abstract: In CodeAct, language-model agents write Python that calls tools and use execution feedback to choose actions. Persistent runtimes preserve Python va
arXiv:2609.38661v1 Announce Type: new Abstract: In recent years, LLM-based multi-agent systems have been widely applied to orchestrate tool-using agents into executable communication graphs. However,
Behavior intelligence company Exabeam Inc. today introduced a batch of new artificial intelligence features that push its cloud-based New-Scale platform further into agent-driven investigations. The c
arXiv:2609.39392v1 Announce Type: new Abstract: Autonomous research agents can generate hypotheses and conduct experiments, but experimentation remains a major source of computational cost. A fundamen
arXiv:2609.38960v1 Announce Type: cross Abstract: This paper presents a scalable optimal-transport-based framework for terminal distribution matching in multi-agent systems. While optimal transport pr
Agentic artificial intelligence-powered hardware systems design platform Flow Engineering Inc. announced Wednesday it has raised 50 million in early-stage funding to change how engineers develop and i
arXiv:2609.38516v1 Announce Type: cross Abstract: Large language models (LLMs) can now improve themselves by revising the instructions they follow, and LLM agents are increasingly orchestrated to work
arXiv:2609.38285v1 Announce Type: cross Abstract: Vision-language models (VLMs) can contradict themselves across views of the same spatial relation and fail to respond when that relation changes. Addr
arXiv:2504.04711v2 Announce Type: replace Abstract: Current large language models (LLMs) are constrained by human-derived training data and limited by a single level of abstraction that impedes defini
Great paper for the weekend ahead. Meta presents Context Language Models, which can natively manage their own context. Banger paper from Meta and colleagues. (bookmark it) They discuss benefits of giv
Great talk from Yogish Baliga 'From Vim (:wq) to 'You're absolutely right!'' tracing 20+ years of software engineering evolution. Highlights: 1/ open-weight models have closed the gap with closed mode
arXiv:2609.39601v1 Announce Type: cross Abstract: Precise grounding matters. It specifies which object is the target and where that object is, even in clutter and for tiny objects, and it has to be fa
arXiv:2609.39544v1 Announce Type: new Abstract: Recent achievements in AI-assisted mathematics require intensive interaction of agents with proof assistants to generate machine-checked proof certifica
arXiv:2609.39037v1 Announce Type: cross Abstract: Before a validator can be promoted to a hard gate on a deployment pipeline, it has to be shown that its firing separates outputs that reach users in w
arXiv:2609.39352v1 Announce Type: cross Abstract: LLM agents increasingly rely on reusable Skills for complex, multi-step tasks, creating a critical supply-chain attack surface where poisoned Skill co
arXiv:2609.40303v1 Announce Type: new Abstract: Recent autonomous machine learning engineering (MLE) agents have made significant progress on public leaderboards. Often motivated by progress stagnatio
IBM Corp. today announced a self-hosted deployment option for IBM Bob, its agentic software development platform, allowing enterprises to use artificial intelligence to build and modernize application
arXiv:2609.40070v1 Announce Type: cross Abstract: When inference demand exceeds available compute capacity, model providers must decide which requests should be served first. Users have different tole
arXiv:2504.06209v2 Announce Type: replace Abstract: Predicting future observations plays a central role in machine learning, biology, economics, and many other fields. It lies at the heart of organiza
We are introducing Clef and Clef-flash, open-source decision models hosted on Workers AI for high-speed classification and agentic workflows. Also launching: a new reinforcement learning platform that
jes, a jev open-source guardrails project LangChain Ambassador @EdenEmarco177 has been working on It uses LangChain’s TypeSafeClassifier under the hood. The docs include a LangChain middleware example
arXiv:2609.40103v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as automated judges for AI-generated content, yet a single judge is unreliable and even a panel o
arXiv:2609.39957v1 Announce Type: cross Abstract: Coding agents solve repository-level tasks through sequences of actions, where a single erroneous action can misdirect subsequent decisions and increa
arXiv:2609.39765v1 Announce Type: new Abstract: Agent memory faces heterogeneous access needs: a single-hop question may require one piece of evidence, whereas a multi-hop question must combine eviden
arXiv:2609.40195v1 Announce Type: cross Abstract: Long-term egocentric video enables personalized AI assistants to reason about daily life. However, as video histories grow to hundreds of hours spanni
arXiv:2609.38349v1 Announce Type: cross Abstract: Modern agentic systems combine an AI model with a harness that controls execution and environmental interactions. Harness design strongly affects long
arXiv:2609.39297v1 Announce Type: new Abstract: Autonomous agents powered by large language models (LLMs) are rapidly evolving into an open agentic ecosystem. To support trustworthy collaboration, ind
arXiv:2609.38294v1 Announce Type: new Abstract: We study the generation of agentic workflows that jointly optimize multiple objectives, such as accuracy, cost, latency, robustness, and consistency. Ex
arXiv:2609.39333v1 Announce Type: cross Abstract: Autonomous AI agents can turn authors' goals into interactive narratives by independently organizing and carrying out generation and revision. As agen
arXiv:2609.39105v1 Announce Type: new Abstract: Autonomous navigation in unstructured off-road environments requires reasoning about both vehicle--terrain interaction and environmental unknowns. We pr
Arasu Kannagi Basil / Reuters: OpenAI says that as of September 26, it has informed 100+ third-party organizations about unauthorized activity involving its AI agents — OpenAI has informed more than 1
At OpenAI's annual DevDay conference, the company pulled out all the stops to compete with its rivals - primarily Meta, whose Muse AI agent platform has seen early runaway success. CEO Sam Altman walk
arXiv:2609.39727v1 Announce Type: new Abstract: Cooperative language-model agents must coordinate over long horizons and adapt to changing environments and to partners with unfamiliar conventions, yet