Knowledge catalogue
Microsoft has developed Project Solara, a platform for devices that run AI agents instead of apps, based on Android instead of Windows. The platform is Microsoft's bet that AI will open up entirely ne
arXiv:2606.01552v1 Announce Type: new Abstract: Role-playing agents(RPAs) are widely used to steer large language models(LLMs) toward role-consistent behavior, yet existing benchmarks mainly evaluate
arXiv:2606.01311v1 Announce Type: cross Abstract: Large language model (LLM) agents increasingly rely on reusable external skills to solve long-horizon interactive tasks. Existing training-free skill
Verification is the hidden bottleneck for knowledge work agents, especially in legal AI — complex, long-horizon work is graded by rubrics with dozens of strict criteria. In new research with @LangChai
arXiv:2605.30838v1 Announce Type: new Abstract: LLM-powered search agents enable multi-step reasoning and tool use. However, these capabilities introduce retrieval-induced safety degradation, as harmf
arXiv:2605.30690v1 Announce Type: new Abstract: Long-term memory is essential for LLM agents to reason coherently across extended interactions, personalize responses, and reuse past experience. Howeve
arXiv:2603.18382v2 Announce Type: replace Abstract: Anonymization is often assumed to protect privacy once explicit identifiers are removed, because re-identification has historically required special
just a small zoom out on the vibe shift: in Feb 2025 @soumithchintala was talking about his dream of personal, local, private agents, most people didn't believe him. it's June 2026 and @pewdiepie has
arXiv:2603.22744v2 Announce Type: replace Abstract: Large language models excel on objectively verifiable tasks such as math and programming, where evaluation reduces to unit tests or a single correct
Personal agents are exploding in popularity, with open source projects like OpenClaw and Hermes seeing rapid adoption by AI developer communities on GitHub. Built to adapt to individual preferences an
arXiv:2605.30723v1 Announce Type: new Abstract: LLM agents increasingly retrieve externally curated skills-procedural instructions retrieved at decision time-to improve performance on long-horizon int
// The Efficiency Frontier // Cool paper on context management. As agents reuse the same documents and histories across many turns, the cheapest context strategy is not fixed. This work describes a pr
arXiv:2605.29910v1 Announce Type: cross Abstract: Consensus protocols form the backbone of distributed systems and blockchains, where implementation bugs can cause data corruption and financial losses
Cursor has introduced an auto-review mode feature that enables AI agents to execute tool calls with reduced approval requirements while maintaining safer execution practices. This feature streamlines
arXiv:2605.30152v1 Announce Type: cross Abstract: Proactive agents read user activity as text and call an LLM on every event to decide whether to act. But user activity is not natively text: it is a s
arXiv:2605.29256v1 Announce Type: cross Abstract: Role-playing with large language models is fundamentally a session-level task, requiring agents to sustain character identity and interaction quality
arXiv:2605.28965v1 Announce Type: new Abstract: Linking free-text phenotype descriptions to ontology terms, typically referred to as phenotype annotation, is essential for the cross-study integration
Having Grok Build sub-agents to iterate several ideas for me on data loading, batching, inference, and writing results to files for dense datasets before I went to sleep. It gave me a nice summary of
arXiv:2605.30159v1 Announce Type: new Abstract: Memory-augmented LLM agents tackle complex long-horizon tasks by recursively summarizing interaction trajectories into compact memory. However, existing
arXiv:2605.29119v1 Announce Type: new Abstract: Computer use agents (CUAs) have shown strong potential for automating complex digital workflows, yet their training remains constrained by costly live e
arXiv:2605.28850v1 Announce Type: new Abstract: We study behavioral alignment and representation dynamics of large language model (LLM) agents in financial decision environments. Using TradeArena, an
arXiv:2605.29794v1 Announce Type: new Abstract: LLM agents now draw on growing skill libraries to handle complex tasks. However, injecting more skills does not always improve task completion and can e
arXiv:2605.27761v1 Announce Type: new Abstract: The rapid development of GUI foundation models and mobile GUI agents has spurred numerous evaluation benchmarks, yet most rely on simulated environments
Banger paper from Harvard. AutoScientists drops the central planner entirely. Agents interpret shared experimental data, self-organize around promising directions, evaluate proposals before resource a
arXiv:2605.27935v1 Announce Type: new Abstract: Recent mechanistic studies suggest that large language models (LLMs) may utilize their depth inefficiently in standard single-turn tasks. Whether this s
arXiv:2605.27904v1 Announce Type: new Abstract: Time series forecasting in real-world settings often depends not only on historical observations, but also on external context that must be actively dis
arXiv:2605.27566v1 Announce Type: new Abstract: Progress in neural combinatorial optimization for Dynamic Flexible Job Shop Scheduling Problem (DFJSP) is currently hindered by a methodological tension
Jeremy Kahn / Fortune: London-based Geordie AI, which builds a security and governance platform for AI agents, raised a 30M Series A led by Balderton at an estimated 180M valuation — Geordie AI, a Lon
arXiv:2605.28646v1 Announce Type: cross Abstract: GUI agents rely on screenshots to infer intent and operate across applications, but these screenshots often contain private messages, medical records,
🚨 This is EXACTLY WHY ICE agents are FORCED to wear masks ICE Newark rioter: “I HAVE YOUR FACE, MOTHERF***ER” “Your WHOLE F***ING FAMILY is DEAD!” “Your KIDS. Your WIFE. ALL DEAD!” This is the type of
arXiv:2605.26785v1 Announce Type: cross Abstract: Post-trained LLMs are often optimized to align responses with human preferences, making them safe, polite, and conversationally appropriate. In advers
Boston Tech Week featured a session hosted by Mason Dry and Sydney Runkle with the Blitzy AI team focused on building deep agents. The event was promoted via Luma Events and appears to be an education
This article discusses implementing role-based access control (RBAC) systems that work for both human users and AI agents, likely addressing how to manage permissions and authentication in environment
arXiv:2601.05899v2 Announce Type: replace Abstract: Recent breakthroughs in Large Language Models (LLMs) have positioned them as a promising paradigm for agents, with long-term planning and decision-m
Gary Marcus shares a video clip discussing the intersection of AI agents and questions of responsibility, featuring contributors Thierry Souttiaux and Silicon Valley commentators. The post highlights
arXiv:2605.23939v1 Announce Type: new Abstract: Web agents require both high-level reasoning (for task decomposition) and low-level interactions (for page elements manipulation) to conduct different t
arXiv:2605.24517v1 Announce Type: cross Abstract: CLI agents are the closest thing language models have to an embodied setting: the model emits commands, the terminal executes them, and the returned s
arXiv:2605.24941v1 Announce Type: cross Abstract: Modern LLM agents combine long-term memory for personalization with tool-calling interfaces for taking actions in the world -- a combination underpinn
arXiv:2605.25869v1 Announce Type: new Abstract: Long-term memory is essential for persistent LLM agents, yet prevailing architectures store historical interactions as unstructured, flat text. This unc
An OpenAI insider (@thsottiaux) raises concerns about the risks of over-relying on AI agents to handle cognitive tasks, warning against wholesale delegation of thinking to autonomous systems. The warn
arXiv:2605.26081v1 Announce Type: new Abstract: Deep research agents face vast, interdependent, and pervasively uncertain information. Existing systems explore what evolving intermediate representatio
arXiv:2605.25981v1 Announce Type: new Abstract: We document an empirical phenomenon in chain-of-thought and ReAct agents driven by ten large language models from seven architecture families: meaning-b
arXiv:2605.23551v1 Announce Type: cross Abstract: A goal-conditioned reinforcement learning agent exploring an environment will see a wealth of information throughout a trajectory, most of which is di
arXiv:2605.23754v1 Announce Type: new Abstract: Developing constitutive models that capture how materials deform under load traditionally requires years of specialized expertise in continuum mechanics
arXiv:2605.23067v1 Announce Type: new Abstract: Reinforcement learning (RL) has emerged as a viable recipe for training LLM agents to reason over external memory banks in multi-session dialogue. Exist
arXiv:2605.23220v1 Announce Type: new Abstract: Despite the growing use of world models as decision-making agents, their adversarial robustness remains underexplored due to the lack of dedicated autom
arXiv:2605.21965v1 Announce Type: new Abstract: Large language models increasingly use external tools such as web search and document retrieval to solve information-intensive tasks. However, multi-hop
Google just revealed Omni, personalized cross-device intelligence, and Spark agents at I/O 2025. I sat down with CEO Sundar Pichai to figure out what comes next: 1:46 Omni: 'Nano Banana for video' 4:5
arXiv:2408.08812v2 Announce Type: replace Abstract: Deployed reinforcement learning agents often face safety requirements that are specified only after training, such as new hazard maps, revised risk
Google I/O 2026 featured several new AI model releases including Gemini 3.5 Flash, an Omni model codenamed NanoBanana for video processing, Spark for background agent tasks, and Antigravity 2.0. These
arXiv:2605.19604v1 Announce Type: new Abstract: Large Language Model (LLM) agents increasingly act inside real workspaces, where tools and skills determine whether model reasoning becomes reliable act
LLM agents & memory systems operate in continuously updated environments (Git repos, evolving docs). They must process long contexts, recover earlier information, and reason over many updates that cre
arXiv:2605.19769v1 Announce Type: new Abstract: We present OpenComputer, a verifier-grounded framework for constructing verifiable software worlds for computer-use agents. OpenComputer integrates four
arXiv:2605.20061v1 Announce Type: new Abstract: Reinforcement learning from verifiable rewards (RLVR) is a promising paradigm for improving large language model (LLM) agents on long-horizon interactiv
arXiv:2602.11767v3 Announce Type: replace Abstract: Advances in large language models (LLMs) are driving a shift toward using reinforcement learning (RL) to train agents from iterative, multi-turn int
arXiv:2605.16309v1 Announce Type: new Abstract: LLM-based agents can recover from individual execution errors, yet they repeatedly fail on the same fault when the underlying process knowledge--operato
This article presents benchmarking results for AI coding agents evaluated at scale, likely comparing performance metrics such as code generation accuracy, execution success rates, and inference effici
arXiv:2605.16728v1 Announce Type: new Abstract: This paper proposes a minimal architecture for body-grounded perspective formation in artificial agents. Extending prior work, the model introduces an i
This article likely discusses the feasibility and methods of contacting AI agents or customer service representatives by phone, exploring whether voice communication is available as an interaction opt
arXiv:2605.17281v1 Announce Type: cross Abstract: Tool-augmented LLM agents call APIs whose intermediate outputs, such as presigned URLs, session tokens, and OAuth state parameters, are observation co