arXiv:2610.36877v1 Announce Type: new Abstract: Mobile GUI agents are typically fine-tuned 7B-scale vision-language models (VLMs) that generate each…
Noise Steering: Exploiting Wake Steering and Acoustic Directivity for Noise-Constrained Wind Farm Control via Reinforcement Learning
arXiv:2610.36888v1 Announce Type: new Abstract: Existing noise mitigation strategies for wind farms usually consist in reducing turbines power output,…
Evolving Agent Teams
arXiv:2610.36848v1 Announce Type: new Abstract: The rapid progress of software engineering agents drives interest in applying them to open-ended problems…
Conservative Policy Iteration For Zero-Sum POSGs
arXiv:2610.36847v1 Announce Type: new Abstract: Occupancy-state reductions make dynamic programming possible for zero-sum partially observable stochastic…
Cisco Partner Summit: Five insights that will define the channel in the AI era
For most of its 30-year history, Cisco Partner Summit has focused on how partners sell Cisco Systems Inc. technology. This year’s event in Vancouver was…
RubricAtlas: Mining Type-Level Rubrics from Expert Reports to Evaluate Deep Research Agents
arXiv:2610.36878v1 Announce Type: new Abstract: Deep research agents conduct multi-step Web searches and synthesise retrieved information into analytical…
Who Knows What – and What Does It Support? Perspective-Bounded Evidence Calibration for Multimodal Theory of Mind
arXiv:2610.36824v1 Announce Type: new Abstract: Theory of Mind (ToM), the ability to infer others’ beliefs, goals, and intentions, is a cornerstone of…
Dependency Graphs of Mathematical Arguments: Representation, Structural Measurement, and Proof Review
arXiv:2610.36776v1 Announce Type: new Abstract: We propose a source-grounded framework for representing and measuring mathematical arguments with…
Batching the Reflective Optimization Loop: Parallel Proposals Make GEPA Faster and Better
arXiv:2610.36774v1 Announce Type: new Abstract: Reflective text optimization makes agentic systems better, but the optimization loop is itself a…
When the Critic Falls Behind: Co-Evolving Rubrics and Harnesses for Continual Agent Self-Improvement
arXiv:2610.36826v1 Announce Type: new Abstract: Autonomous agents increasingly depend on harnesses that govern interaction, memory, tools, and execution…
[AINews] Anthropic ends Coding Interviews: “Hunger beats tenure”
Since coding is solved, why code for the job?
An Incremental Knowledge-Graph Learner Digital Twin for Evidence-Grounded Early Warning
arXiv:2610.36820v1 Announce Type: new Abstract: Early-warning models in learning analytics can identify learners at risk of failure or withdrawal, but the…
AI News Brief Hourly Summary 2026-10-28 10h : 13 posts
13 posts published in the last hour 08:45The View from Nowhere: Population-Centered Agent Evolution 08:45Can LLMs Reliably Grade Olympiad Proofs? A Study of Mathematical Verification with LLMs 08:45Beyond the Evidence Coherence Trap: Agent-Driven Evidence Selection for Temporally Disordered Fake News…
The View from Nowhere: Population-Centered Agent Evolution
arXiv:2610.36660v1 Announce Type: new Abstract: Self-improving AI systems can revise the designs that govern their own behavior. Yet existing approaches…
Can LLMs Reliably Grade Olympiad Proofs? A Study of Mathematical Verification with LLMs
arXiv:2610.36767v1 Announce Type: new Abstract: Large Language Models (LLMs) have made remarkable progress on solving competition-level mathematics, yet…
Beyond the Evidence Coherence Trap: Agent-Driven Evidence Selection for Temporally Disordered Fake News Detection
arXiv:2610.36764v1 Announce Type: new Abstract: Fake news undermines public trust and the integrity of online information ecosystems. Temporally…
PsyJev: Psychological Analysis via System-1 Judgment
arXiv:2610.36689v1 Announce Type: new Abstract: Self-disclosures on the Web support diverse psychological analyses, from recognizing expressed experiences…
Polymathic AI and Princeton Researchers Release FlashMap, a Flow Map Drafter for 6.14x Faster LLM Decoding
FlashMap is a speculative decoding drafter from Polymathic AI, Princeton and USC ISI researchers. It drafts 16 tokens jointly in one pass and reaches up…