Knowledge catalogue
arXiv:2605.21958v1 Announce Type: new Abstract: When a multi-module LLM agent fails, the module most responsible for the failure is not necessarily the best place to intervene. We demonstrate this Dia
arXiv:2605.20867v1 Announce Type: cross Abstract: Multimodal sarcasm detection requires reasoning over cross-modal incongruities between literal expression and intended meaning, yet the specific analy
arXiv:2605.19156v1 Announce Type: new Abstract: Recent auto-research systems can produce complete papers, but feasibility is not the same as quality, and the field still lacks a systematic study of ho
very belated but in retrospect i think @sama's mythical 'build a business that gets better when models get better' is basically what I called Agent Labs here. seeing a very direct correlation with mod
Very cool - Grok Build is clearly getting better by the day. Two nights ago I ran an overnight build and it failed. Last night, success. I really like the multi-agent orchestration behavior, it does a
arXiv:2212.02098v5 Announce Type: replace Abstract: Inspired by the cognitive science theory of the explicit human memory systems, we have modeled an agent with short-term, episodic, and semantic memo
arXiv:2511.11654v2 Announce Type: replace-cross Abstract: Rapid urbanization in cities like Bangalore has led to severe traffic congestion, making efficient Traffic Signal Control (TSC) essential. Mul
arXiv:2605.16857v1 Announce Type: new Abstract: Experience-driven learning has emerged as a promising paradigm for enabling agents to improve from interaction trajectories by accumulating and reusing
arXiv:2605.17044v1 Announce Type: new Abstract: Large language models (LLMs) increasingly serve as interactive social agents, yet their ability to maintain coherent and authentic persona-level role-pl
arXiv:2605.16297v1 Announce Type: cross Abstract: Which tasks inside an enterprise workflow can a large-language-model agent reliably handle, and under what conditions? Most business process modeling
arXiv:2605.15224v1 Announce Type: new Abstract: Large language model-based agents make mistakes, yet critique can often guide the same model toward correct behavior. However, when critique is removed,
arXiv:2603.23433v2 Announce Type: replace Abstract: AI agents are becoming active decision-makers on the Internet. As they make decisions in the same environments as humans, the environments themselve
arXiv:2605.16191v1 Announce Type: new Abstract: We present a case study for how AI coding systems can be used to generate novel scientific hypotheses. We combine a generic coding agent (Google's AntiG
arXiv:2605.14350v1 Announce Type: new Abstract: Multi-task reinforcement learning (MTRL) aims to train a single agent to efficiently optimize performance across multiple tasks simultaneously. However,
arXiv:2605.13438v1 Announce Type: new Abstract: Existing agent memory remains predominantly reactive and retrieval-based, lacking the capacity to autonomously organize experience into persistent cogni
arXiv:2605.13534v1 Announce Type: new Abstract: Deep search agents have proven effective in enhancing LLMs by retrieving external knowledge during multi-step reasoning. However, existing methods often
SmithDB is a feat of engineering. A new database for a new data shape Huge work from @ankush_gola11 and team We built SmithDB: the database purpose built for agent observability workloads that now pow
arXiv:2605.11463v1 Announce Type: new Abstract: Learning and representing the subjectivities of agents has become a challenging but crucial problem in the trajectory prediction task. Such subjectiviti
arXiv:2602.01682v2 Announce Type: replace Abstract: We study online inverse linear optimization, also known as contextual recommendation, where a learner sequentially infers an agent's hidden objectiv
arXiv:2605.11688v1 Announce Type: new Abstract: Zero-shot coordination (ZSC) aims to enable agents to cooperate with independently trained partners without prior interaction, a key requirement for rea
arXiv:2605.10585v1 Announce Type: new Abstract: Multi-objective reinforcement learning (MORL) allows a user to express preference over outcomes in terms of the relative importance of the objectives, b
love seeing my discord stay in sync with Hermes Kanban..everything here was done in plain English. I just asked my coordinator to check if we have an update and the system understood the intent, route
arXiv:2508.07722v2 Announce Type: replace Abstract: Traditional Reinforcement Learning (RL) frameworks generally assume that the agent perceives the state of the underlying Markov process instantaneou
arXiv:2605.08450v1 Announce Type: cross Abstract: Imitation learning is effective for training agents when expert demonstrations are available, but collecting demonstrations for every complex task in
arXiv:2605.06976v1 Announce Type: cross Abstract: Many ranking and agent trace datasets are recorded as linear orders even though their latent structure is only partially ordered. This is especially c
arXiv:2605.07910v1 Announce Type: new Abstract: Reconstructing dynamic scenes from Vehicle-to-Infrastructure Cooperative Autonomous Driving (VICAD) data is fundamentally complicated by temporal asynch
Your AI coding agent, the one you use to write code, needs to reduce your maintenance costs. Not by a little bit, either. You write code twice as quick now? Better hope you’ve halved your maintenance
Nous Research has developed a ComfyUI skill integration for their Hermes agent framework that enables creative workflows through ComfyUI's node-based image generation system. This skill allows the Her
arXiv:2605.04202v1 Announce Type: new Abstract: Strategic classification studies the problem where self-interested individuals or agents manipulate their response to obtain favorable decision outcomes
arXiv:2604.01707v2 Announce Type: replace Abstract: Memory emerges as the core module in the large language model (LLM)-based agents for long-horizon complex tasks (e.g., multi-turn dialogue, game pla
Ha love to see this port of flue to python Harness engineering is a fun time! Need more people exploring! 🎉Introducing PyFlue: The Python-Native Agent Harness Framework.🧰 💡Flue for Python: Fred K. Sch
A lot of work around AI in 2023 was spent on building picks and shovels. I would know this because that was basically the core goal of the original @llama_index framework. Today, a lot of that is no l
arXiv:2604.27539v1 Announce Type: cross Abstract: As information ecosystems grow more heterogeneous, both humans and artificial agents increasingly face a simple yet unresolved question: when seeking
Codex CLI 0.128.0 adds /goal The latest version of OpenAI's Codex CLI coding agent adds their own version of the Ralph loop: you can now set a /goal and Codex will keep on looping until it evaluates t
Every year for AI Ascent, @gradypb, @Konstantine and I get to share some perspectives on AI and where things are headed. This year's talk was about the arrival of agents and the race to deploy them ac
ComfyUI is a node-based UI framework for composing and executing complex workflows, likely used within the Nous Research Hermes Agent system for creative tasks involving image generation or AI model o
arXiv:2604.25325v1 Announce Type: cross Abstract: Modern Text-to-SQL systems generate multiple candidate SQL queries and rank them to judge a final prediction. However, existing methods face two limit
arXiv:2603.01421v2 Announce Type: replace-cross Abstract: Automated scientific discovery with large language models is transforming the research lifecycle from ideation to experimentation, yet existin
arXiv:2604.23072v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly tasked with complex real-world analysis (e.g., in financial forecasting, scientific discovery), yet t
arXiv:2604.22973v1 Announce Type: new Abstract: Predicting future trajectories of surrounding traffic agents is critical for safe autonomous navigation and collision avoidance. Despite all advances in
arXiv:2602.17315v2 Announce Type: replace-cross Abstract: We introduce Flickering Multi-Armed Bandits (FMAB) to model sequential decision-making in environments with changing action availability, wher
arXiv:2604.23716v1 Announce Type: new Abstract: Information-theoretic (IT) measures are ubiquitous in artificial intelligence: entropy drives decision-tree splits and uncertainty quantification, cross
arXiv:2604.22760v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly operate as autonomous agents that reason over external APIs to perform complex tasks. However, their reliabi
arXiv:2604.24326v1 Announce Type: cross Abstract: The decentralization of modern energy systems is transforming consumers into prosumers who continuously exchange data with aggregators, peers, and mar
Symphony is an open-source specification for orchestration released by OpenAI, designed to provide standardized patterns and tools for coordinating complex AI workflows and system interactions. The sp
arXiv:2604.22110v1 Announce Type: new Abstract: Standard supervised classification trains models to imitate the exact labels provided by a perfect oracle. This imitation happens in a single pass, rest
The EU AI Act is the first comprehensive regulation for AI systems, and it’s right around the corner. With the clock running down, we took a deeper look at what these requirements mean for your agents
We wrote a custom terminal rendering library in Rust to make the UI as fast and snappy as possible. We even got it working on a real VT-100, the first terminal from the 1970s. Try it out today http://
arXiv:2604.21993v1 Announce Type: new Abstract: We study the detection of transient liquidity erosion ('crumbling quotes') in electronic limit order books, where observable quote deterioration may ref
Devin, an AI coding assistant, enables developers to hand off work from their local laptop to cloud-based processing via CLI commands, allowing tasks to continue running in the cloud environment witho
Free API credits to beta testers to coordinate frontier models dynamically. See more below 👇🏼 We’re launching the beta for our new commercial AI product: Sakana Fugu 🐡, a multi-agent orchestration sys
Hermes Kanban Bridge v1.3.0 Your Obsidian vault is now a command center for AI-driven project management. New in v1.3.0: • Velocity Reports — weekly throughput analytics across all boards, auto-writte
Enterprise AI deployments are accelerating, but the velocity of change in models, tools and platforms is quietly creating a new and costly trap: costly failure to build for AI architectural replaceabi
arXiv:2604.20586v1 Announce Type: new Abstract: The ongoing shift towards decentralization of the electric energy sector, driven by the growing electrification across end-use sectors, and widespread a
Are you coming to @DeepLearningAI AI's AI Dev 26 x SF next week? Our Chief Product & Strategy Officer, Or Dagan, will be giving a talk diving into what our product and R&D teams are doing to automate
@benswerd there are tradeoffs but we've spoken to folks doing both inside and outside and the split is pretty much 50:50 in our experience. I've found @hwchase17's list of tradeoffs the most accurate
LangChain, an open-source framework for developing applications with large language models, is recruiting new team members as shared by co-founder Harrison Chase on X (Twitter). The careers page invit
Harrison Chase, co-founder and CEO of LangChain, appeared in a startup spotlight interview with Stephanie Wong. The discussion likely covered LangChain's development, its applications in AI and langua
AI investment is surging to manic heights, but C-suites have yet to see it translate into measurable business outcomes — a gap that is now one of the defining strategic challenges of the current techn
arXiv:2604.19945v1 Announce Type: new Abstract: In this paper, we investigate the problem of how to effectively master tool-use to solve complex visual reasoning tasks for Multimodal Large Language Mo