Knowledge catalogue
Meir Orbach / CTech: Cisco agrees to acquire Astrix Security, which helps companies monitor and control the permissions granted to AI agents, a source says for approximately $400M — The Israeli startu
arXiv:2605.00370v1 Announce Type: new Abstract: Centralized multimodal learning commonly compresses language, acoustic, and visual signals into a single fused representation for prediction. While effe
Jerry Liu predicts that genuinely useful long-running AI agents will become a reality by 2026, viewing this development as simultaneously inevitable and remarkable. The post reflects on how advances i
Digital security company DigiCert Inc. today introduced a new AI Trust framework to help organizations secure AI systems and their outputs, along with new capabilities to help secure autonomous agents
Google Cloud is assembling an ambitious agentic enterprise stack it believes will close the gap between AI ambition and real business outcomes. But the transition from traditional, linear workflows to
arXiv:2604.26020v1 Announce Type: cross Abstract: Usability testing with experts and potential users can assess the effectiveness, efficiency, and user satisfaction of graphical user interfaces (GUIs)
arXiv:2604.23990v1 Announce Type: new Abstract: This paper presents PSA-Eval, a failure-centered runtime evaluation framework for deployed trilingual public-space agents. The central claim is that, wh
arXiv:2604.23194v1 Announce Type: new Abstract: Large language model-based agents have recently emerged as powerful approaches for solving dynamic and multi-step tasks. Most existing agents employ pla
arXiv:2604.24348v1 Announce Type: new Abstract: The evolution of Multimodal Large Language Models (MLLMs) has shifted the focus from text generation to active behavioral execution, particularly via OS
arXiv:2603.18563v2 Announce Type: replace Abstract: As autonomous AI agents increasingly mediate online platform markets, a fundamental question emerges: do these markets generate stable strategic out
arXiv:2604.21896v1 Announce Type: new Abstract: This paper introduces a new paradigm for AI game programming, leveraging large language models (LLMs) to extend and operationalize Claude Shannon's taxo
arXiv:2604.19789v1 Announce Type: new Abstract: We present an autonomous large language model (LLM) agent for end-to-end, data-driven materials theory development. The model can choose an equation for
benchmarking agents by their ability to play video games 🎮 We are excited to launch VideoGameBench on Antim Labs, created by @a1zhang, Thomas L. Griffiths (@cocosci_lab), @karthik_r_n, and @OfirPress
arXiv:2602.18571v2 Announce Type: replace-cross Abstract: While significant progress has been made in automating various aspects of software development through coding agents, there is still significa
arXiv:2604.19457v1 Announce Type: new Abstract: Long-horizon enterprise agents make high-stakes decisions (loan underwriting, claims adjudication, clinical review, prior authorization) under lossy mem
arXiv:2604.18847v1 Announce Type: new Abstract: As LM agents gain the ability to execute actions on real computer systems, we need ways to not only prevent harmful actions at scale but also effectivel
LiteParse: our open-source, layout-aware PDF parser for AI agents. The secret? Grid projection. Instead of heavy ML layout models or flat text extraction, it projects text onto a monospace grid so ali
arXiv:2504.15304v2 Announce Type: replace Abstract: Can AI agents deal with hard choices -- cases where options are incommensurable because multiple objectives are pursued simultaneously? Adopting a t
arXiv:2510.07043v2 Announce Type: replace Abstract: Human decision-making often involves constrained optimization. As LLM agents are deployed to assist with real-world tasks like travel planning, shop
arXiv:2504.13541v5 Announce Type: replace-cross Abstract: Training resource-constrained autonomous agents on multiple tasks simultaneously is crucial for adapting to diverse real-world environments. R
arXiv:2604.15075v1 Announce Type: cross Abstract: Open-weight Small Language Models(SLMs) can provide faster local inference at lower financial cost, but may not achieve the same performance level as
arXiv:2604.13151v1 Announce Type: new Abstract: Language Model (LM) agents are increasingly used in complex open-ended decision-making tasks, from AI coding to physical AI. A core requirement in these
Simon Willison discusses the perception that LLMs and coding agents are primarily useful for greenfield development (starting new projects from scratch) rather than for maintaining and modifying large
arXiv:2509.21823v2 Announce Type: replace Abstract: Reward is critical to the evaluation and training of large language models (LLMs). However, existing rule-based or model-based reward methods strugg
AI Search is the search primitive for your agents. Create instances dynamically, upload files, and search across instances with hybrid retrieval and relevance boosting. Just create a search instance,
arXiv:2512.20798v4 Announce Type: replace Abstract: As autonomous AI agents are deployed in high-stakes environments, ensuring their safety has become a paramount concern. Existing safety benchmarks p
arXiv:2604.12147v1 Announce Type: cross Abstract: Agents aspire to eliminate the need for task-specific prompt crafting through autonomous reason-act-observe loops. Still, they are commonly instructed
arXiv:2604.11465v1 Announce Type: new Abstract: Large language model (LLM) agents show promise on realistic tool-use tasks, but deploying capable agents on modest hardware remains challenging. We stud
LiteParse is the best document parsing library for coding agents. It's free, fast, integrates natively with the LLM's native visual understanding capabilities, and comes with support for 50+ formats a
Databricks Research introduced **MemAlign**, a memory framework for AI agents that stores past interactions as episodic memories and uses an LLM to distill them into generalized semantic rules, whi...
arXiv:2610.21147v1 Announce Type: new Abstract: Large language models increasingly rely on external memory to answer queries grounded in long-horizon histories such as multi-session dialogues and leng
arXiv:2610.21561v1 Announce Type: cross Abstract: Large language models (LLMs) deployed as conversational agents are increasingly expected to follow procedural logic. While factual hallucination has r
arXiv:2610.21405v1 Announce Type: new Abstract: Long-term memory has become a crucial component of large language model (LLM) agents, with most research focusing on retrieving relevant information acc
arXiv:2610.21900v1 Announce Type: new Abstract: An agent's memory must remain useful as information changes across conversations. A new fact may replace an earlier value without making that value irre
arXiv:2610.22039v1 Announce Type: cross Abstract: Real-world software engineering rarely consists of isolated changes. Features, migrations, and systematic fixes often unfold across multiple pull requ
arXiv:2610.18602v1 Announce Type: new Abstract: Point-in-time (PIT) agents can recall post-cutoff facts even when their external evidence respects a historical cutoff. We examine whether this access p
arXiv:2610.14790v1 Announce Type: new Abstract: Reflective language agents reuse feedback and memory to adapt across tasks without updating model weights. However, existing guarantees for policy selec
arXiv:2610.18378v1 Announce Type: new Abstract: Applying process-based Earth science models to new sites and questions often requires expert calibration decisions. Reliable delegation to language-mode
arXiv:2610.18784v2 Announce Type: new Abstract: Long-horizon agents accumulate progress in persistent task state, yet repeatedly process interaction histories describing how that progress was achieved
arXiv:2610.14163v1 Announce Type: cross Abstract: Terminal agents solve tasks in software engineering and scientific research by executing commands in a terminal. Training them via reinforcement learn
Keeping a city running means making decisions that affect residents every day — from when to repair a road to how to use energy more efficiently. Across the EMEA region, cities and local software, inf
arXiv:2610.16919v1 Announce Type: cross Abstract: Machine learning engineering (MLE) agents are emerging as a new paradigm for automating end-to-end ML pipeline development. Using large language model
arXiv:2610.15258v1 Announce Type: cross Abstract: We introduce Sequent-Prover, a family of verifier-using language-model agents, and the post-training framework that produces them. Agents reason in an
After much testing and talking to actual users across all three proactive AI agents: Muse - best one for your parents, heavy IG/FB users, people who like or need easy setups, people who don’t want to
arXiv:2610.13829v1 Announce Type: cross Abstract: A central challenge in embodied recursive self-improvement is enabling agents to convert interaction history into capabilities that persist beyond one
The Bitter Lesson for harness design and formal math! Instead of hand-designing how an AI should prove (decompose, plan, assign agents), what if we just give a frontier model good Lean feedback and le
A new work suggesting that division of labor among self-improving AI agents can help them avoid reinforcing their own errors. I found this work interesting from a metascience perspective. Science is a
arXiv:2610.11447v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as coding agents that edit files, run builds and tests, inspect execution results, and repair s
arXiv:2610.10961v1 Announce Type: cross Abstract: Coding agents increasingly share a workstation while drawing on separate providers and subscription allowances. A second agent can inspect a completed
arXiv:2510.00536v2 Announce Type: replace Abstract: Graphical user interface (GUI) agents built on vision-language models have emerged as a promising approach to automate human-computer workflows. How
arXiv:2512.14014v2 Announce Type: replace Abstract: World models have shown great utility in improving the task performance of embodied agents. While prior work largely focuses on pixel-space world mo
arXiv:2610.11008v1 Announce Type: cross Abstract: Language-model agents favor their own group because they have watched their members favor each other. The group label alone does little once the decis
arXiv:2609.32701v2 Announce Type: replace-cross Abstract: In security-sensitive applications, language-model agents are often required to coordinate without disclosing confidential information. Yet re
Enterprise search and security company Elastic N.V. today introduced AlertZero, a team of specialized artificial intelligence agents for security operations. Built into Elastic Security, the agents ta
arXiv:2610.07967v1 Announce Type: new Abstract: As large language model (LLM) agents become increasingly autonomous, they may pursue task performance through deception, raising concerns about their re
arXiv:2603.04364v2 Announce Type: replace-cross Abstract: Multimodal web agents that process both screenshots and accessibility trees are increasingly deployed to interact with web interfaces, yet the
arXiv:2610.07863v1 Announce Type: cross Abstract: Long-horizon LLM agents act on an append-only interaction history that is re-sent to the model at every step, so the context and its cost grow with st
arXiv:2610.07327v1 Announce Type: cross Abstract: Agent tasks require sequences of interdependent decisions. Autoregressive models support more flexible decision interfaces than conventional classifie
arXiv:2610.06748v1 Announce Type: cross Abstract: In decentralized consumer-to-consumer (C2C) marketplaces, people list goods, negotiate with strangers, and rate one another, so trust rests on reputat
arXiv:2610.06830v1 Announce Type: cross Abstract: Memory has become integral to the LLM agent ecosystem, supporting information retention and reuse across interactions. However, most existing agent me