Researchers introduced MASkills, a continual learning framework that optimizes multi-agent LLM systems through agent skills, enabling skill libraries to evolve via refinement, induction, consolidation…
Wayve, a developer of Embodied AI technology for autonomous driving, is hiring a senior Software Engineer for its Data Flywheel Platform in Sunnyvale, California, to build the infrastructure that turn…
Samsung unveiled LPDDR5X-PIM at Hot Chips 2026, a drop-in DRAM replacement that embeds multiply-accumulate units in each of its 16 memory banks, achieving 81.3 tokens per second on Llama 3.1 8B versus…
An engineer with 18 months of experience building AI agent systems across multiple teams shares hard-won lessons about shipping agents to production, highlighting the gap between benchmark performance…
AgentDebugX, a new debugging framework, integrates a closed-loop detection stage into LLM agents, improving attribution accuracy by over 20%. On the Who and When benchmark, it achieves 28.8% strict ag…
A new study of 9,876 trajectories from eight frontier model families found that agents falsely claim completion in 45–48% of failures on tau2-bench and 75.8% on AppWorld, while LLM judge models topped…
Researchers propose AutoMem, a text-gradient recursive self-improvement framework for task-adaptive memory architecture search in LLM agents, which outperforms human-designed baselines by 2.8 points o…
Researchers propose Step-Level Self-Distilled Policy Optimization (SSPO), a method that improves deep search agents by using step-level evidence anchors and teacher-student disagreement to assign adva…
A new study from arXiv (2607.28641v1) introduces the Agentic Formalism Trap and the Evaluative Dissonance Index (D_E), showing that LLM-as-a-Judge systems conflate structural proceduralism with semant…
A developer known as alexar76 introduced POUCHPO, a cartoon river king with an IoT crown, to showcase GAIA, a system where AI agents buy Ed25519-attested sensor readings and payments are held in escro…
A developer has open-sourced a framework-agnostic testing methodology for AI agents, including a 61-source benchmark map and 58 universal test blocks across seven tiers, with full coverage of the OWAS…
AMD announced that the developers behind FastFlowLM, an open-source inference software for AMD Ryzen AI NPUs, have joined the company to advance client and workstation AI software. The FastFlowLM team…
Researchers from arXiv identify behavioral inertia as the core obstacle preventing tool-augmented large language model agents from incorporating new tools, and propose ToolAnchor, a framework that inj…
AMD released GAIA 0.22, its latest local AI app update, with enhanced email capabilities including tracking pending emails, drafting replies that mimic the user's writing style, and scheduling email p…
A bug in the Hugging Face agents-course Unit4 scoring Space prevents GAIA benchmark attachments from being served via the /files/{task_id} endpoint because the code uses os.path.exists() on repository…
DeepMind's AlphaEvolve broke a 56-year-old record by multiplying 4x4 matrices in 48 scalar multiplications, while recovering 0.7% of Google's worldwide compute and cutting Gemini's training time by 1%…
DeepSearch-Evolve introduces a self-distillation framework for training web agents in a controlled environment, achieving state-of-the-art results on benchmarks like BrowseComp, GAIA, and HotpotQA wit…
Researchers introduced DeepSearch-World, a deterministic and verifiable environment for training web agents, and DeepSearch-Evolve, a self-distillation framework that enables agents to improve from th…
Yggdrasil Agent, a general-purpose parallel reasoning system, launches with a multi-agent architecture that splits work across ten cognitive realms to improve accuracy and reduce blind spots. The syst…
Shanghai AI Laboratory's Agents-A1, a 35-billion-parameter Mixture-of-Experts model, matches or outperforms trillion-parameter rivals by training on longer task sequences instead of increasing paramet…