arXiv:2610.21214v1 Announce Type: new Abstract: Rubric-based evaluation is widely used to assess large language model (LLM) outputs by decomposing quality…
Who May Release an Agent’s Promise? Standing over Commitments in Multi-Party Chat
arXiv:2610.21203v1 Announce Type: new Abstract: When an assistant serving a team makes a promise to Alice, who may cancel it? We call this standing: only…
Auditing Escalation Reliability in Healthcare LLM Agents: A Perturbation-Controlled Benchmark of Workflow-State Failures
arXiv:2610.21270v1 Announce Type: new Abstract: Trustworthy biomedical AI requires reliable action selection when evidence is missing, stale, conflicting,…
Mine, Sample, Render: Test-Time Diversity Alignment Of Generative Models
arXiv:2610.21185v1 Announce Type: new Abstract: Modern generative models produce high-quality individual outputs but struggle to sample diversely, even…
Condition-Contrastive Extrapolation for On-Policy Distillation of Language Models
arXiv:2610.21195v1 Announce Type: new Abstract: On-policy distillation (OPD) improves a student language model by training on its own generated…
MemScope: Evolving Agent Memory Architectures through Localized Code Repair
arXiv:2610.21170v1 Announce Type: new Abstract: Agent memory architectures define how LLM agents store and reuse experience across tasks, but they are…
Does Latent Chain-of-Thought Actually Reason? A Single, Unifying Taxonomy for Latent Reasoning
arXiv:2610.21182v1 Announce Type: new Abstract: Latent chain-of-thought replaces written reasoning steps with continuous hidden states, giving models…
Figma announces new features to define how agents work on its platform
Figma is also releasing its code layers feature in open beta.
AgentEval: Evidence-Bounded Assessment of Stateful Agents
arXiv:2610.21177v1 Announce Type: new Abstract: Task completion alone does not determine whether a stateful agent satisfied its obligations, and a…
AI News Brief Hourly Summary 2026-10-16 10h : 20 posts
20 posts published in the last hour 07:34Datalab Releases OmniParseBench: An Open OCR Benchmark With 16,288 Pass/Fail Tests to Audit OCR Parsers 07:34All-in-One Memory: Process-Rewarded Reinforcement Learning for Memory Agents 07:34Ricursive Intelligence is betting on AI-designed chips to help solve…
Datalab Releases OmniParseBench: An Open OCR Benchmark With 16,288 Pass/Fail Tests to Audit OCR Parsers
Datalab released OmniParseBench, an open OCR benchmark with 16,288 yes/no tests on 2,937 pages in 92 languages. Every score is a pass rate you can slice…
All-in-One Memory: Process-Rewarded Reinforcement Learning for Memory Agents
arXiv:2610.21147v1 Announce Type: new Abstract: Large language models increasingly rely on external memory to answer queries grounded in long-horizon…
Ricursive Intelligence is betting on AI-designed chips to help solve the compute crisis
The founders detailed how their startup is developing AI that can design chips, learn from each iteration, and improve subsequent designs, all with the…
GRADS: Graph-Regulated Agentic Data Synthesis with Controllable Difficulty
arXiv:2610.21167v1 Announce Type: new Abstract: Deep research agents are increasingly deployed to retrieve precise information from large corpora, yet…
Ahead of IPO, Anthropic reveals its revenue grew 45% sequentially to $16.8B in Q3
Anthropic PBC pulled in $16.8 billion in revenue during the third quarter, according to a report today by the Financial Times — and also achieved…
Planning Commitment of LLM under Partial Observability
arXiv:2610.21108v1 Announce Type: new Abstract: LLM-based planning agents commit to plans of different lengths before interacting with a partially…
Liquid AI Releases d1-ultra: A Multimodal Decision Model That Scores 65 on the AA Decision Index
Liquid AI released d1-ultra, a text and image decision model that returns calibrated probabilities in 1 forward pass. It scores 65 on the Artificial…
Kolab: Benchmarking Human-Agent Collaboration in Long-Horizon Workflows
arXiv:2610.21109v1 Announce Type: new Abstract: When humans collaborate with AI agents on long-horizon tasks, what happens to the agents’ contributions?…