Knowledge catalogue
Very interesting new work Amazon and colleagues. (bookmark it) This connects to the emerging theme of treating the corpus as part of the harness. Planning loops, tool protocols, and context management
arXiv:2608.17167v1 Announce Type: cross Abstract: Active inference selects actions by minimising an expected free energy functional over predicted futures. However, adding an expectation over yet-unob
arXiv:2608.17574v1 Announce Type: new Abstract: How cautious should an agent be while it is still learning its environment? We propose RATTL (Risk-Adversarial Total-Reward Learning), which ties cautio
Zep offers a knowledge graph for persistent user memory and shared organisational context through MCP, according to Zep.
arXiv:2608.16195v1 Announce Type: new Abstract: Achieving human-level competitive intelligence and physical agility in humanoid robots remains a profound challenge, particularly in contact-rich and hi
arXiv:2608.16707v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as decision-making agents in settings that require sophisticated environmental exploration. How
arXiv:2608.15089v1 Announce Type: new Abstract: Long-horizon agents can fail even when their underlying models can solve the constituent steps. They may lose track of mutable state, fail to reactivate
🚀Today we launched LangSmith Tuned Evaluators, starting with Perceived Error. Tuned Evaluators run on production traces to catch undesirable agent behavior and attach feedback that you can use in your
arXiv:2608.16747v1 Announce Type: cross Abstract: Many areas of AI research, such as language model interpretability and chain of thought faithfulness, seek to explain model behaviors. But what consti
😮 wow that’s huge 💰 🚀Today we launched LangSmith Tuned Evaluators, starting with Perceived Error. Tuned Evaluators run on production traces to catch undesirable agent behavior and attach feedback that
arXiv:2608.13719v1 Announce Type: new Abstract: Autonomous systems can fail in rare and heterogeneous ways, making real-world failure discovery difficult under limited testing budgets. Although cheape
arXiv:2608.14207v1 Announce Type: cross Abstract: Cooperative perception among multiple unmanned surface vehicles (USVs) combines complementary observations to extend maritime target sensing beyond th
arXiv:2608.13606v1 Announce Type: new Abstract: The next generation of AI agents is increasingly moving beyond systems that answer isolated questions toward persistent personal assistants that can und
Most document extraction APIs can't tell you where a value came from. For ExtractBench, we scored grounding strictly: a field only counts if the value AND its citation are correct, word-level box at I
arXiv:2608.13625v1 Announce Type: new Abstract: Signal temporal logic (STL) provides a formal language for specifying real-time properties of real-valued observations, along with a quantitative robust
Watching a team of bots split up a large game project based entirely on their own experience and specialties with little input from me is pretty crazy (and just a bit creepy) to watch. I made a short
https://preview.redd.it/wkg27e152qjh1.png?width=853&format=png&auto=webp&s=2e3f8b11ea6393041f501e95c5835f9bea0245dd So ive been trying different harnesses and coding agents with the new qwen 3.8 , and
Interesting new research from IBM. If you pick models from benchmark deltas, some of that delta belongs to the phrasing rather than the model. BenchDrift generates meaning-preserving variations of ben
Alix Coutures / The Information: Sources: Mercor and other firms gathering data for AI labs are driving demand to buy or license internal datasets from startups shutting down or being acquired — Eight
A fantastic show as always, thanks for having me on @PeterMcCormack ! AI Has Escaped... - OpenAI agents escaped from their sandbox - They sent messages to other agents on how to escape - They hacked a
arXiv:2608.12753v1 Announce Type: new Abstract: We study decentralized multi-player reinforcement learning in episodic tabular Markov decision processes (MDPs) under three forms of information asymmet
arXiv:2608.13096v1 Announce Type: new Abstract: Limit order book (LOB) simulators are most useful to practitioners when they combine realistic market dynamics, computationally efficient sampling, cont
I’ve experimented with Cursor, Antigravity, Claude Code/CLI, Ollama, Gemma 4B, MiniMax, Hermes Agent, and different local/cloud models. My problem isn’t knowing what these tools are—I don't know how t
arXiv:2608.13448v1 Announce Type: new Abstract: Social robots are expected to operate across diverse environments, where similar arrangements can imply different socially appropriate actions, e.g., st
arXiv:2512.19799v2 Announce Type: replace Abstract: Advances in LLM reasoning and tool use have enabled agentic science, yet frontier theoretical and computational physics remains challenging because
arXiv:2608.11247v1 Announce Type: new Abstract: Recent advances in language models have enabled collaborative settings in which multiple models leverage one another's capabilities, iteratively improvi
arXiv:2608.11876v1 Announce Type: new Abstract: Training and validation of Embodied AI for social navigation critically depends on realistic simulation environments, yet many current approaches fail t
arXiv:2608.11901v1 Announce Type: new Abstract: Vision-and-Language Navigation (VLN) has progressively expanded from indoor to outdoor environments. However, existing outdoor VLN datasets still rely o
— Google AI Pro and Ultra subscribers can experience 3.7 Flash today via Spark in the @GeminiApp — Access the model in the Gemini Enterprise Agent Platform and Gemini Enterprise app — Build in the Gem
arXiv:2608.11220v1 Announce Type: new Abstract: Nowadays, the creation of a process flow diagram (PFD) and its subsequent transformation into a piping and instrumentation diagram (P&ID) is predominant
arXiv:2608.11340v1 Announce Type: cross Abstract: Symbolic network verifiers can reason about correctness across vast spaces of routing inputs and failures, but only for the protocols and features an
arXiv:2608.11676v1 Announce Type: new Abstract: Heterogeneous multi-agent LLM systems, where agents are powered by different model families, can outperform homogeneous configurations by reducing redun
arXiv:2509.05624v3 Announce Type: replace-cross Abstract: How much information about an agent's underlying values can be recovered from its observable behavior? This question matters for any approach
arXiv:2608.10438v1 Announce Type: new Abstract: Large language models increasingly rely on external tools to access up-to-date information, perform computation, and interact with the outside world. Fo
arXiv:2608.10103v1 Announce Type: cross Abstract: High-performance Tensor Core kernels rely on a low-level PTX pipeline built from asynchronous data movement with cp.async, warp-level matrix loads wit
Live now: our Memory & Continual Learning Track from AI Engineer World's Fair 2026. Thesis: we scaled intelligence and got the world's smartest novice. https://www.youtube.com/watch?v=iqloyWCGYQQ&list
Shares of Nebius Group NV closed 34% higher today after it reported second-quarter earnings that topped expectations across the board. The Netherlands-based company operates a cloud platform optimized
arXiv:2608.10186v1 Announce Type: cross Abstract: LLMs are increasingly deployed in settings that require collective reasoning on complex, value-laden problems. Confidence in these deployments rests l
arXiv:2406.19930v4 Announce Type: replace Abstract: Swarm-based target localization in industrial environments faces two major challenges: navigating obstacle-rich spaces and managing intensive commun
arXiv:2511.22130v2 Announce Type: replace Abstract: To navigate ever-shifting real-world environments, agents must grapple with incomplete knowledge and adapt their strategies through experience. Howe
Had so much fun giving this talk at @sequoia about @harvey’s moneyball approach to building a research lab. The biggest mistake I made in the early days of Harvey was trying to play the Yankees baseba
arXiv:2608.07688v1 Announce Type: new Abstract: IT audits require auditors to judge whether heterogeneous organizational evidence satisfies semantic security and compliance controls. This judgment is
arXiv:2608.09410v1 Announce Type: new Abstract: Modern vision-language-action (VLA) policies have acquired broad manipulation skills, but typically generate each action chunk from the current observat
arXiv:2608.07779v1 Announce Type: new Abstract: Artificial intelligence is changing the task composition of computing work faster than curricula and training typically adapt. This is a curriculum-fram
arXiv:2608.09153v1 Announce Type: new Abstract: Production AI agents fail when their context sources -- system prompts, knowledge bases, tool descriptions, and procedural skills -- contain errors or g
arXiv:2608.07994v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) is essential for enterprise knowledge question answering (QA), particularly in domains with complex product documen
arXiv:2608.07457v1 Announce Type: new Abstract: What will happen when AI agents interact in daily life, e.g. when one AI starts bossing another around? We find a counterintuitive answer that opens new
arXiv:2603.06054v2 Announce Type: replace-cross Abstract: The use of Vision-Language Models (VLMs) in automated driving applications is becoming increasingly common, with the aim of leveraging their r
arXiv:2608.06668v1 Announce Type: new Abstract: As an important component of the supply chain industry, transportation has experienced rapid development in the past decade with the assistance of digit
Auto mode is now the default in Claude Code for Pro, Max, and Team plans Anthropic are really confident in Claude Code's auto mode, to the point that they are making it the default setting for new ses
arXiv:2608.05327v1 Announce Type: cross Abstract: Our results show that the existence of a short high-utility protocol already suffices for efficient communication. In particular, in a game with n pos
In this post, you learn how Cohere Health built a multi-tenant agentic architecture on AgentCore using AgentCore Runtime’s secure MicroVM isolation, unified tool access through AgentCore Gateway, Agen
arXiv:2608.05466v1 Announce Type: new Abstract: High-quality long-horizon training data for terminal agents is expensive to produce, often costing hundreds to thousands of dollars per task, because ea
upgraded my stack, and i can now work on almost anything from anywhere hands free: - talk to chief of staff (via remote codex voice or text) - chief assigns tasks to managers of various projects - man
In a fast-paced digital economy, data is your most critical engine. Yet, many enterprises find themselves trapped in a costly paradox, spending over 100 hours a week building and fixing fragile, in-ho
i guess this is a good time to mention that smol forge is open for the first 100 alpha users. get your usernames! (tire kickers who dont make any commits will be kicked out by eod) point clanker to fo
arXiv:2608.04384v1 Announce Type: new Abstract: Neural PDE solver auto-design is fundamentally a search-space representation problem. In the space of unrestricted Python programs, valid solvers form a
arXiv:2608.05141v1 Announce Type: new Abstract: Context lengths of language models (LMs) have dramatically increased, driven by the demands for in-context learning, self-improvement, and long-horizon
arXiv:2608.04896v1 Announce Type: new Abstract: Defensive driving scores are useful only when they preserve distinctions between policies that observe surrounding actors and those that do not. Re-simu
arXiv:2608.03171v1 Announce Type: cross Abstract: We study fair allocations of indivisible goods among agents with heterogeneous monotone valuations. As fair we consider the allocations that are envy-