CPU-ARC caches LLM reasoning traces for cheaper CPU reuse
The paper reports on-par results with frontier models on hard math and science tasks at 16–291x lower cost.
Stories per day · 30 days
2 RSS
Related3d-reconstruction1authorization1cad1call-site-contracts1chain-of-thought1cpu-inference1digital-identity1engineering1enterprise-ai1entity-resolution1evaluation1fda-cleared-tools1financial-services1governance1gpt-6-astra1gpu-scheduling1guardrails1inference1
13 stories, newest first · one card per story
Stories tagged #agentic-systems
Agentic Systems Leverage FDA-Cleared Radiology Tools for Comprehensive Reporting
Agentic framework recovers under a third of actionable findings with cleared tools, improving substantially with unlimited catalogs.
TAC-CoT improves agentic LLM accuracy and efficiency
TAC-CoT interleaves compact latent reasoning segments with explicit tool calls, observations, and answers to enable tool-use without verbalizing every step.
Paper specifies a commit guardrail for agentic entity resolution
The design is conceptual only, with no implementation, empirical results, or proof of semantic correctness.
TAO jointly schedules LLM agent sessions and tool returns
Across 12 reported settings, TAO cuts latency by up to 26.8% and mean TTFT by up to 36.3% versus the best baseline for each metric.
Vanguard AI lead discusses foundations for scalable AI
The EmTech Future session covers data, platforms, governance and agentic systems in regulated settings.
SceneRig builds simulation-ready 3D scenes from single images
An agent edits and validates scenes in a physics simulator so reconstructed objects stay physically stable.
Most agent LLM call sites miss expected contracts
In 496 call sites across 40 open-source agents, 63% of expected constraints were unmet and 5.3% of sites met the full contract.
Study finds GPT-6 Astra useful but unreliable for engineering CAD
Tests cover model understanding, generation, editing, and evaluation, with recurring failures in freeform geometry, parameters, and mating.
EmbodiedRSI: Active Continual Robot Learning Through Hypothesis-Guided Co-Evolution
EmbodiedRSI reaches 77% success on RoboCasa365, nearly doubling the best baseline.
Recursive Game Creator: An Agentic Product-Level Experience-Oriented Game Harness
Recursive Game Creator uses four agent roles to turn prototypes into more enjoyable games.
Skill-Space Shooting for Autonomous Robot Policy Improvement
Paper introduces skill-space shooting, using foundation model guidance over reusable skills to turn robot failure corrections into autonomous policy improvement.
Evaluating Verified Autonomy in Quantum Engineering
Quantum-Harbor lab and QIQCBench (49 tasks) expose wide performance gaps across 17 frontier agentic systems in verified quantum engineering.