Search: “agents”

arXiv:2604.28001v1 Announce Type: new Abstract: Integrating multimodal foundation models into enterprise ecosystems presents a fundamental software architecture challenge. Architects must balance comp

Real-time voice artificial intelligence startup Deepgram Inc. today announced the general availability of Flux Multilingual, an extension of its Flux conversational speech recognition model to 10 lang

arXiv:2604.25914v1 Announce Type: new Abstract: Real-world data visualization (DV) requires native environmental grounding, cross-platform evolution, and proactive intent alignment. Yet, existing benc

Rogo Technologies Inc., a startup using artificial intelligence to make financial professionals more productive, today announced that it has raised 160 million in funding. Kleiner Perkins led the Seri

arXiv:2604.21629v1 Announce Type: cross Abstract: We compare lightweight automata-based models (n-grams) with neural architectures (LSTM, Transformer) for next-activity prediction in streaming event l

arXiv:2505.21410v2 Announce Type: replace Abstract: Hierarchical reinforcement learning (HRL) decomposes the policy into a manager and a worker, enabling long-horizon planning but introducing a perfor

arXiv:2604.14261v1 Announce Type: new Abstract: The rapid rise in AI conference submissions has driven increasing exploration of large language models (LLMs) for peer review support. However, LLM-base

arXiv:2602.21480v4 Announce Type: replace-cross Abstract: Text-to-SQL and Big Data are both extensively benchmarked fields, yet there is limited research that evaluates them jointly. In the real world

arXiv:2604.11462v1 Announce Type: new Abstract: Large Language Models (LLMs) struggle with long-horizon tasks due to the 'context bottleneck' and the 'lost-in-the-middle' phenomenon, where accumulated

Customer relationship management vendor HubSpot Inc. today introduced a set of product updates aimed at helping sales and marketing teams adapt to a shift in how buyers research and engage with vendor

Cloudflare's mission has always been to help build a better Internet. Sometimes that means building for the Internet as it exists. Sometimes it means building for the Internet as it's about to become.

arXiv:2610.18157v1 Announce Type: cross Abstract: Inside organizations, a question's data often sit with several owners, who query their own tables but never hand them over. An LLM coordinator can fan

arXiv:2610.20240v1 Announce Type: new Abstract: A multiplayer world model must predict how the independent actions of several players change a shared environment, including changes outside a player's

arXiv:2610.19349v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) provides no reward-relative learning signal when all rollouts receive identical rewards. In long-horizon tas

arXiv:2610.11573v1 Announce Type: new Abstract: The memory capabilities of Large Language Models (LLMs) have garnered increasing attention recently. Despite great success achieved, existing retrieval-

arXiv:2609.40306v1 Announce Type: cross Abstract: Pretrained robot policies provide useful action priors, but long-horizon manipulation still requires coordination between semantic reasoning and physi

arXiv:2609.36611v1 Announce Type: new Abstract: Retrieval-augmented fact-checkers often receive a reliability label, such as HIGH or LOW trust, for each evidence source. These labels should adjust the

arXiv:2609.36829v1 Announce Type: new Abstract: An executor can respond strongly to a change in a supplied plan's priority while showing a small change in the same information-selection probability wh

arXiv:2609.32870v1 Announce Type: cross Abstract: Self-play proposer--solver methods improve reasoning by generating tasks and learning from verified solutions. However, for evidence-identifiable task

arXiv:2609.32801v1 Announce Type: cross Abstract: Embodied task planners may produce multi-step plans whose subtask dependencies and interactions with the environment create physical risks during exec

arXiv:2609.33180v1 Announce Type: cross Abstract: As recursive self-improvement (RSI) rapidly advances, reliable evaluation becomes critical for guiding adaptive search. RSI typically relies on finite

Would be interesting right? Models are starting to score higher and higher on benchmarks like Parametric CAD Bench, but can they pass an actual exam? The Certified SOLIDWORKS Associate (CSWA) exam mig

arXiv:2609.28765v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) performs well on problems with clear rewards, such as mathematics and coding, but whether it also

arXiv:2609.23315v1 Announce Type: cross Abstract: Graph databases are frequently positioned as categorically necessary for connected-data workloads, yet the systems dimension along which they actually

arXiv:2609.22850v1 Announce Type: new Abstract: Contrastive activation directions are often interpreted from what they decode or how strongly they steer behavior. But what evidence is sufficient to id

arXiv:2609.22043v1 Announce Type: new Abstract: Memory systems for large language models have focused predominantly on efficient retrieval, whereas the decision of whether retrieved memories should be

arXiv:2605.13481v2 Announce Type: replace Abstract: We introduce PersonalAI 2.0 (PAI-2), a novel framework designed to enhance LLM-based systems through integration of external knowledge graphs (KGs).

arXiv:2609.19090v1 Announce Type: cross Abstract: Can an attacker turn influence over an artificial intelligence (AI) adviser into a harmful quantum error-correction update? We identify an ambiguity i

arXiv:2606.17467v3 Announce Type: replace-cross Abstract: Prompt injection defenses evaluated on synthetic benchmarks do not generalize to real enterprise documents, which are longer, denser, and inte

This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology. The AI industry has taken a doomer turn. What now? AI chiefs D

Amazon Bedrock AgentCore Identity now offers a Consent portal, a managed web experience and session binding endpoint for AgentCore Gateway. This post walks through provisioning a portal, configuring G

arXiv:2609.04773v1 Announce Type: cross Abstract: Distillation is common in LLM post-training, where on-policy knowledge distillation (OPKD) uses student-generated trajectories to prepare the student

Hey everyone, I'm trying to set up a local LLM on my machine. My goal is to use it with Qwen Code or OpenCode to help me out with small to medium sized tasks, but nothing too big. I tested many differ

arXiv:2608.23329v1 Announce Type: cross Abstract: Open-world video understanding often requires a model to locate sparse visual evidence and acquire external knowledge that is absent from the video an

If you maintain an AGENTS.md or a CLAUDE.md, this one is worth your time. (bookmark it) Researchers traced 94K development events across 557 agentic coding sessions, plus 690K file-level change record

arXiv:2608.18008v1 Announce Type: cross Abstract: Combining large language models with reinforcement learning is increasingly explored, yet the theoretical status of LLM-derived reward signals is ofte

arXiv:2608.15109v1 Announce Type: new Abstract: Generating structurally valid synthetic tabular data remains difficult: outputs with high statistical fidelity and downstream utility can still violate

arXiv:2608.13604v1 Announce Type: new Abstract: Detection of misunderstanding is an urgent problem to solve because communication has moved away from real-time, in-person interaction and is increasing

arXiv:2608.09485v1 Announce Type: new Abstract: Cooperative capabilities in language models are dual-use. The same social reasoning that supports civic deliberation can also enable strategic omission,

really excited to see this release AND integrate it with deepagents!! https://www.langchain.com/blog/switchyard-agent-routing-benchmark Lightning strikes for continuous and long-run agents! Nemotron 3

arXiv:2608.06530v1 Announce Type: new Abstract: Planning a degree from official university sources requires solving two problems in order. The institution's curriculum must first be reconstructed from

arXiv:2608.05999v1 Announce Type: new Abstract: Vision-language-action (VLA) models have demonstrated remarkable capabilities in robotic manipulation by leveraging pretrained vision-language models. H

arXiv:2608.04804v1 Announce Type: cross Abstract: Frontier language models can resolve repository-level software issues, but each attempt is expensive, and existing routers select a model from the iss

arXiv:2608.03970v1 Announce Type: new Abstract: Human input reaches language models by typing or speaking, and each channel leaves a distinct signature: orthographic noise for keyboards; for voice, di

MIT Technology Review Explains: Let our writers untangle the complex, messy world of technology to help you understand what’s coming next. You can read more from the series here. When two OpenAI model

If you maintain an AGENTS.md or a CLAUDE.md, this is worth a read. (bookmark it) 288 gold-test evaluated runs across Claude Code and Codex, 17 real tasks from 3 repositories, with context-injection st