Knowledge catalogue
arXiv:2512.14735v2 Announce Type: replace-cross Abstract: This paper proposes PyFi, a novel framework for pyramid-like financial image understanding that enables vision language models (VLMs) to reaso
Cursor cloud agents now run in isolated virtual machines where they can build, test, and verify their own code — then automatically attach artifacts such as videos, screenshots, and logs to the pul...
As AI agents demand real-time access to live, governed data, database lifecycle management has moved from a back-office task to a strategic imperative for enterprise infrastructure. The complexity of
Zencoder, a startup building an artificial intelligence orchestration layer for software development and business, today announced the launch of Zenflow Work, a major expansion of its platform that fo
Google Research introduced two AI agents to streamline academic workflows: **PaperVizAgent**, a visualizer agent for drawing academic figures, and **ScholarPeer**, a reviewer agent that automatica...
we recently trimmed the deepagents harness base prompt by 65% (including tool info) it shows — deepagents is cheap! We ran DeepSeek V4 Flash through 4 more agent harnesses (Hermes Agent, Pi Agent, Pri
this is a fundamental building block for `deepagents deploy` we're designing a memory layer built for multi-tenant systems, so memory can be scoped to a user, agent, or organization please dm me if th
arXiv:2610.21045v1 Announce Type: new Abstract: Tool-using language agents must revise prepared actions when evidence changes or authority is revoked. Selective withdrawal means suspending affected ac
arXiv:2610.20927v1 Announce Type: new Abstract: Long-horizon LLM agents rely on context compaction: when the interaction history outgrows the context window, a compressor replaces it with a natural-la
arXiv:2610.17827v1 Announce Type: new Abstract: Existing approaches to training and evaluating search agents focus heavily on final-answer quality, largely neglecting how generated answers map back to
arXiv:2610.19420v1 Announce Type: cross Abstract: Simulated environments enable scalable training data generation for embodied agents, but more data does not necessarily provide what a particular agen
arXiv:2610.17757v1 Announce Type: new Abstract: Large language model agents can follow complex human instructions to solve real-world tasks. In practice, however, initial instructions are often incomp
arXiv:2610.19642v1 Announce Type: cross Abstract: Reinforcement learning provides a direct mechanism for optimizing task objectives in large language model-driven agents, but task rewards are typicall
arXiv:2610.19810v1 Announce Type: cross Abstract: Large language models are increasingly competent at leveraging scientific knowledge and existing computational tools to execute complex workflows. At
arXiv:2608.01822v2 Announce Type: replace Abstract: Training LLM-based search agents requires high-quality search data: tasks that demand genuine multi-hop retrieval and trajectories that use search t
arXiv:2610.15055v1 Announce Type: new Abstract: Self-evolving agents are usually scored by endpoint Gain: held-out success after an update minus success before. That difference can credit a frozen res
AI coding ROI is earned in review. @Harvard / @_jellyfish_co : agents added 30% more code, but there was no significant gain in software output. PR review-to-merge time rose 49%. Most AI code review t
arXiv:2610.14977v1 Announce Type: new Abstract: Embodied agents built on foundation models rely on an execution harness to organize observations, guide actions, and incorporate execution feedback into
arXiv:2610.18684v1 Announce Type: cross Abstract: Personal-agent memory has largely focused on learning what users know, prefer, and want. However, knowing the user does not necessarily mean knowing w
At AI Engineer New York, Anthropic's @cjav_dev & @HarrisonStall from @ClaudeDevs drew on lessons from Unix and Linux to explain how agents can tackle bigger projects without overwhelming developers. h
Write-up: https://zhebrak.io/posts/brokenml/ Repo: https://github.com/zhebrak/brokenml I built a benchmark to determine the access level agents need to successfully fix broken ML workloads (PyTorch ov
arXiv:2610.06411v2 Announce Type: replace Abstract: Agentic systems increasingly coordinate molecular-design tools, but it is unclear which layer of the stack limits outcomes on real projects. We deve
arXiv:2610.09944v2 Announce Type: replace Abstract: An essential control of AI agents is their ability to manage runtime. This ability requires a sense of time-awareness, to predict and estimate wall-
arXiv:2610.11482v1 Announce Type: cross Abstract: Context: Large language model (LLM) agents are increasingly used as software and data-engineering assistants, yet evidence about locally deployable op
arXiv:2610.10778v1 Announce Type: cross Abstract: Long-term agents face growing storage demands as they accumulate experience. World models capture reusable regularities that can reduce the informatio
arXiv:2610.04838v2 Announce Type: replace Abstract: As coding agents take on long-horizon software evolution tasks spanning multiple files and stages, longer execution trajectories introduce two coupl
arXiv:2610.11732v1 Announce Type: new Abstract: Large language model (LLM) agents for portfolio management learn from experience: they credit each experience in their memory with the outcome of the de
arXiv:2610.04906v2 Announce Type: replace-cross Abstract: Work agents operate over digital artifacts to execute professional knowledge-intensive work, requiring training environments that support long
arXiv:2610.10635v1 Announce Type: new Abstract: Aerial vision-and-language navigation (VLN) agents are typically trained on detail-rich, trajectory-aligned commands, whereas users issue short, intent-
arXiv:2610.10629v1 Announce Type: new Abstract: Self-improving LLM agents can adapt a credit pipeline to a changed rule, but an agent that rewrites itself destroys the artefact a supervisor reviews: a
Amazon Bedrock AgentCore payments gives AI agents a managed way to pay for services on demand, with spending limits enforced by the infrastructure. See how Incarna's agents pay BlockRun for model infe
arXiv:2610.10513v1 Announce Type: cross Abstract: Language-model agents are increasingly asked to carry out open-ended scientific research, yet their results are usually graded against a known answer,
arXiv:2610.06910v1 Announce Type: new Abstract: Recent advances in Large Language Models (LLMs) have demonstrated remarkable capabilities in web front-end execution, with browser-based game generation
arXiv:2610.08691v1 Announce Type: new Abstract: Large language model agents are accelerating scientific automation, yet verified executions rarely become persistent program-level improvements, and exi
arXiv:2609.33678v2 Announce Type: replace Abstract: We introduce SWE-Game, a benchmark of 247 tasks grounded in 41 executable reference Godot games spanning 13 gameplay categories in 2D and 3D. Five t
arXiv:2610.07004v1 Announce Type: new Abstract: Task planning for LLM agents requires workflows that satisfy both user intent and complex sub-task dependencies. While existing planners work well for s
Dell Technologies Inc. today expanded the Dell AI Data Platform with a semantic layer and a knowledge graph intended to give artificial intelligence agents trusted context from a company’s own data. D
arXiv:2610.05732v1 Announce Type: new Abstract: LLM agents rely on long-term memory to retain and reuse information when performing tasks over long horizons. Existing methods provide limited support f
arXiv:2603.02348v2 Announce Type: replace Abstract: An agent meets a model as served: through an endpoint with a price card, a shared cache and other tenants, or on whatever hardware a self-hosted mod
arXiv:2610.02664v1 Announce Type: new Abstract: Long-horizon agents are now playing an increasingly significant role in assisting humans with complex problem-solving. However, it is exactly their exte
arXiv:2610.03153v1 Announce Type: cross Abstract: Workspace agents combine large language models with execution harnesses to perform stateful, multi-step tasks that access or modify external resources
arXiv:2610.02952v1 Announce Type: cross Abstract: Test-driven development gives AI coding agents executable requirements for implementing software. Because these agents can adapt their implementations
See how Arize uses Harbor and Phoenix to benchmark AI agents, MCP servers, skills, and CLIs in reproducible sandboxes, then inspect traces and annotations. The post How we benchmark AI agents and tool
arXiv:2610.02399v1 Announce Type: new Abstract: Multimodal agents are increasingly used for data visualization tasks but remain limited in autonomous review. Unlike humans, they may fail to recognize
arXiv:2609.33289v2 Announce Type: replace Abstract: Autonomous large language model (LLM) agents operating in multi-product markets must make sequential decisions under information asymmetry and resou
More agents don't mean higher performance. There is a coordination bottleneck to consider. Not to mention the unnecessary costs. So how many of a multi-agent team's actions actually help it finish the
arXiv:2609.39022v1 Announce Type: cross Abstract: Coding agents need to establish that a program satisfies a specification and that the specification captures the requested behavior. We study how expe
arXiv:2609.39547v1 Announce Type: new Abstract: GUI agents built on large language and vision-language models still struggle on unseen applications and complex multi-step tasks, as completing real GUI
arXiv:2609.39912v1 Announce Type: cross Abstract: Parallel search may generate a correct answer that final-answer voting fails to select. We formulate this consolidation stage as trajectory selection
arXiv:2609.38670v1 Announce Type: new Abstract: Final-answer accuracy does not reveal whether a scientific-search agent failed to encounter a target paper, attempt to inspect it, or return an accepted
arXiv:2609.37236v1 Announce Type: new Abstract: An agent that uses tools typically responds to what the user explicitly asks, yet completing the task may require information the user never requested.
arXiv:2609.35820v1 Announce Type: cross Abstract: English-only benchmarks expose only a narrow slice of voice-agent behavior. We introduce au-Multilingual, extending au-Voice to Spanish, Brazilian Por
arXiv:2609.36308v1 Announce Type: new Abstract: Reinforcement learning has helped AI agents solve increasingly difficult tasks, but high rewards do not always reflect the work users intended. In recen
arXiv:2609.36344v1 Announce Type: new Abstract: Deep-research agents conduct long-horizon investigations through iterative search, evidence evaluation, belief revision, and synthesis. However, they ma
arXiv:2502.04492v3 Announce Type: replace Abstract: The advancement of LLMs and their accessibility have triggered renewed interest in multi-agent reinforcement learning as robust and adaptive framewo
arXiv:2609.36679v1 Announce Type: new Abstract: Machine learning engineering (MLE) agents have made substantial progress, but learning through ML experimentation remains costly in time and computation
arXiv:2609.35900v1 Announce Type: cross Abstract: The integration of large language models (LLMs) into scientific workflows is accelerating, yet their ability to reconstruct the reasoning underlying p
WHAT THE F*CK. SpaceXAI is using Grok Bot to build Grok Bot. Its agents design, code, test, and ship the product. In this 45-minute session, Peng Zheng and Lauren Tanshowed their internal setup across
arXiv:2609.34262v1 Announce Type: cross Abstract: Agentic benchmarks guide model selection and training. Yet an agent can pass a task without demonstrating the intended capability. Such outcomes const
arXiv:2609.34177v1 Announce Type: cross Abstract: When an agent reuses logged experience, a changed decision may reflect the recorded score, the action's name, or the record's position in storage. Sta