Knowledge catalogue
arXiv:2609.28850v1 Announce Type: new Abstract: Reproducing a machine learning paper involves most research steps, from installing software and debugging to running experiments, work that AI agents in
arXiv:2609.27334v1 Announce Type: new Abstract: Agentic memory systems reuse past experience to improve future performance, yet most existing designs curate memory at write time: once a task is comple
arXiv:2609.27246v1 Announce Type: cross Abstract: As embodied agents take on increasingly social and relational roles in VR, visual realism and embodiment alone may be insufficient; users must also pe
Free SemIf this week is useful. Typed outputs + probabilities look like a cleaner way to route agents than parsing LLM text every time. jev is a new type of model - 'decision models' there are a few o
Grounded Confidence is here for Extract! 🦙 When your agents and workflows depend on extracted data, you need to know how accurate that data is. We’ve added confidence scores to give you a better read
Banger paper from Google Cloud AI Research. If you follow autonomous research agents, this one is worth your time. ScientistTwo takes a problem from a human expert and runs the full discovery cycle wi
arXiv:2609.20822v1 Announce Type: cross Abstract: Coding agents have emerged as a promising paradigm for robot manipulation: a language model writes the robot controller as a program, and agents built
arXiv:2609.19387v1 Announce Type: new Abstract: Agents are increasingly asked to design hardware, and increasingly reported to succeed. Such reports establish that a design improved; they cannot estab
arXiv:2609.17632v1 Announce Type: new Abstract: Large language model (LLM) trading agents can combine market data, news, and executable analysis, but their behavior is often controlled by static hand-
arXiv:2609.17984v1 Announce Type: new Abstract: Machine-learning libraries such as Weka and scikit-learn were designed for human programmers. Language-model agents now use these same libraries by reca
Artificial intelligence agents have become table stakes in enterprise software, but in financial reporting, audit and compliance, speed counts for little if the output cannot be defended. That gap bet
I think Claude Managed Agents strikes the right balance here, the sandbox is optional and can be spun up independently of the rest of the agent loop. I recently ported an old project that was focused
arXiv:2609.16053v1 Announce Type: cross Abstract: Long-term memory is essential for LLM-based agents operating over extended interactions. Existing memory systems primarily update memory when new info
arXiv:2609.17523v1 Announce Type: new Abstract: We introduce and release ScienceBuddy, an interactive scientific research workspace that brings continually improving scientific agents into researchers
arXiv:2609.16760v1 Announce Type: new Abstract: With the rapid development of Large language model (LLM), agent systems enhanced by LLMs show huge potential in being able to deal with complex tasks, e
arXiv:2609.14060v1 Announce Type: cross Abstract: Quantization is one of the default deployment paths for open-weight LLM agents, but it is not behavior-preserving: an adversary can release a full-pre
arXiv:2609.14976v1 Announce Type: new Abstract: Long-horizon LLM agents accumulate memory across sessions, creating sparse but high-impact risks: stale facts, conflicting updates, cross-user leakage,
arXiv:2609.13889v1 Announce Type: cross Abstract: Harness design has transformed the development of LLM-based agents by integrating memory, tool use, and runtime control. However, this design also int
arXiv:2609.13117v1 Announce Type: new Abstract: Full-duplex evaluation often emphasizes whether an agent keeps speaking or stops. That binary cannot express a third response humans use routinely: cont
arXiv:2609.05776v1 Announce Type: new Abstract: Evaluating enterprise agents on domain-specific benchmarks is critical, yet public benchmarks rarely evaluate whether agents can integrate business know
arXiv:2609.08062v1 Announce Type: new Abstract: Tool-using language agents can delegate and revoke permissions while acting through external services. We show that two authorization histories can have
arXiv:2609.05435v1 Announce Type: new Abstract: Modern language agents are expected to operate over long horizons: they ask follow-up questions, reuse worked examples, handle tool feedback, and adapt
arXiv:2609.06563v1 Announce Type: cross Abstract: Social deduction games (SDGs) require agents to reason under partial observability by maintaining relational beliefs about hidden roles and team align
arXiv:2603.04949v2 Announce Type: replace-cross Abstract: As web agents close the gap with humans on benchmarks, one question arises: Do today's agents perform just as well on tomorrow's web? We intro
arXiv:2609.07051v1 Announce Type: new Abstract: World models increasingly serve as the predictive core of model-based reinforcement learning agents, enabling them to simulate future dynamics and reaso
arXiv:2609.04280v1 Announce Type: cross Abstract: Modern LLM-based agents operate through a harness of tools, reusable skills, and specialist agents that shapes what they observe and what they can do.
arXiv:2606.12821v2 Announce Type: replace Abstract: Environmental scientists spend disproportionate effort on data wrangling rather than analysis. New AI agents can be a helpful tool, but no benchmark
arXiv:2508.00935v3 Announce Type: replace-cross Abstract: Computer-using agents (CUAs), which can autonomously control computers to perform multi-step actions, might pose significant safety risks if m
arXiv:2609.04167v1 Announce Type: cross Abstract: Repository-level software engineering benchmarks have significantly advanced the evaluation of coding agents, but existing benchmarks primarily measur
Qonto uses Claude through Bedrock in customer-facing financial agents; Anthropic reports faster transfers and invoice creation.
arXiv:2608.29357v1 Announce Type: new Abstract: Multimodal search agents answer visual questions by interleaving image understanding, web retrieval, tool use, and evidence synthesis. Strong systems ex
arXiv:2508.13186v2 Announce Type: replace-cross Abstract: AI agents with advanced reasoning and tool-use capabilities have demonstrated impressive performance in web browsing for deep search. However,
arXiv:2608.30041v1 Announce Type: cross Abstract: Large language model agents place outputs from external skills into their execution context, allowing attacker-controlled data to influence later priv
arXiv:2605.05726v2 Announce Type: replace Abstract: As LLM agents are increasingly deployed with large libraries of reusable skills, selecting the right skill for a user request has become a critical
arXiv:2608.30785v1 Announce Type: new Abstract: Production agent skills are directory bundles, not isolated prompts. The root is loaded at activation; references, schemas, scripts, assets, and nested
arXiv:2608.29363v1 Announce Type: new Abstract: Enterprise data agents answer business queries by chaining many tool calls over multiple reasoning steps, routinely accumulating hundreds of thousands o
Great reporting. Bad framing. The OpenAI and Hugging Face incident is serious. Agents coordinated, reward hacked, shared information and exploited real infrastructure. But calling this an “AI civiliza
Atlassian uses Claude for complex Rovo workflows and Claude Code internally; its multimodel platform also uses Google Cloud.
arXiv:2608.26199v1 Announce Type: new Abstract: We ask whether AI agents powered by locally deployed large language models can reliably automate expert-defined hardware design workflows in an industry
arXiv:2607.15439v2 Announce Type: replace Abstract: Our previous ARC-AGI-3 agent bundled executable world modeling, prompted simplification, and exact replay verification, leaving their individual con
arXiv:2608.26546v1 Announce Type: new Abstract: Autonomous agents are increasingly adopted to complete complex, multi-tool workflows in real-world settings. However, existing benchmarks typically sepa
arXiv:2608.26696v1 Announce Type: new Abstract: Enterprise deployments of autonomous AI agents inherit a control model built for human users and long-lived services, and the fit fails in three specifi
arXiv:2608.26882v1 Announce Type: cross Abstract: Industrial control systems (ICSs) rely on programmable logic controllers (PLCs) to connect networked computation with physical control. Tool-using lar
arXiv:2608.27182v1 Announce Type: new Abstract: LLM agents are increasingly applied to anomaly detection and root-cause analysis in time-series observations collected from real-world systems; however,
arXiv:2510.22775v2 Announce Type: replace Abstract: While language model agents have advanced software engineering, existing test-based supervision is limiting its scalability on real-world issues. Th
Brain makes a user’s full history available to Computer without loading all of it into every prompt. Agents can explore it on demand, verify claims against the underlying evidence, and keep it current
arXiv:2608.20631v1 Announce Type: new Abstract: Large language model (LLM) agents have demonstrated the ability to solve multi-step tasks requiring planning, tool use, and external information access,
Hey everyone! I wanted to share something I’ve been working on. I was inspired by projects from DeepMind and OpenAI, but noticed that most games are prohibitively difficult to integrate with an agent
arXiv:2608.19993v1 Announce Type: new Abstract: Loading reusable skill documents into a bounded context window is now the primary way large language model (LLM) agents acquire task-specific capabiliti
arXiv:2608.18272v1 Announce Type: cross Abstract: Classical seismic data reconstruction relies on manually designed structural priors and iterative operators, whose coupled design space is far larger
arXiv:2608.18351v1 Announce Type: cross Abstract: Tool-using large language-model agents can complete a task while exercising authority that the user did not grant or the task does not need, causing e
arXiv:2608.17718v1 Announce Type: new Abstract: Long-horizon agents increasingly operate across many steps, tools, and observa- tions. In this setting, the relevant oversight question is not only whet
arXiv:2608.15108v1 Announce Type: cross Abstract: Large language model agents are increasingly connected to high-value resources such as computing infrastructure, credentials, usage budgets, identitie
arXiv:2608.14905v1 Announce Type: new Abstract: AI has long assisted scientific research, but the rapid advance of LLMs and agentic scaffolds is reshaping the landscape; a single system can now carry
arXiv:2608.14132v1 Announce Type: cross Abstract: Mobile GUI Agents powered by multimodal large language models (MLLMs) show promise in human-computer intelligence. However, current research primarily
arXiv:2608.13574v1 Announce Type: new Abstract: LLM agents increasingly operate as execution systems that invoke tools, modify local state, use persistent memory, and interact with external protocols.
arXiv:2608.13420v1 Announce Type: new Abstract: Embodied intelligent virtual agents are expected to operate as persistent, adaptive, and context-aware entities within complex virtual and Metaverse wor
arXiv:2608.12990v1 Announce Type: new Abstract: Long-horizon LLM agents must preserve information from past interactions to support future tasks. Existing memory systems typically rely on eager consol
arXiv:2608.13522v1 Announce Type: cross Abstract: AI agents are increasingly used for programming, but do not provide any guarantee on the correctness of generated code. Verified code generation, in w
arXiv:2608.10366v1 Announce Type: new Abstract: Real-world data science involves long-horizon workflows that span data wrangling, exploration, modeling, visualization, and validation, and require coor