arXiv:2610.11299v1 Announce Type: new Abstract: Voice agents are converging on a collaboration pattern: a full-duplex interaction model stays on the live…
ORDO: Operation-level Round-aware Dynamic Ordering for MIP Presolve
arXiv:2610.11294v1 Announce Type: new Abstract: Presolve strongly affects mixed-integer programming (MIP) performance, yet learning-based methods only…
Finsler Flow Matching: Dynamics-Aware Geodesic Interpolation for Single-Snapshot Trajectory Inference
arXiv:2610.11318v1 Announce Type: new Abstract: Single-cell snapshot data can resolve a continuum of cellular states but do not uniquely determine the…
DivMoE: Fine-Grained MoE Upcycling via Cross-Domain Expert Composition
arXiv:2610.11317v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) architectures have become essential for scaling large language models, with…
AI News Brief Hourly Summary 2026-10-09 09h : 13 posts
13 posts published in the last hour 06:32Harness Compilation: Which Decisions Should a Small Vision-Language Model Keep? 06:32LLM-IDEA: Identifiability-Driven Experimental Agent for Autonomous Discovery of Mechanistic World Models 06:32When Lower Reconstruction Loss Hurts: Distributionally Robust Refinement for Low-Bit LLM Quantization…
Harness Compilation: Which Decisions Should a Small Vision-Language Model Keep?
arXiv:2610.11231v1 Announce Type: new Abstract: Small vision-language models may be able to read external evidence yet struggle to obtain it. We introduce…
LLM-IDEA: Identifiability-Driven Experimental Agent for Autonomous Discovery of Mechanistic World Models
arXiv:2610.11253v1 Announce Type: new Abstract: Large language model agents are being increasingly deployed as autonomous scientists, designing…
When Lower Reconstruction Loss Hurts: Distributionally Robust Refinement for Low-Bit LLM Quantization
arXiv:2610.11226v1 Announce Type: new Abstract: Weight-only post-training quantization (PTQ) relies heavily on reconstruction loss minimization to…
TaReD: Tool-Aware Recursive Decomposition for Long-Horizon Tasks
arXiv:2610.11268v1 Announce Type: new Abstract: Agents combine reasoning with tools to interact with external systems and complete real-world tasks. Early…
Google Research RRSI Guide: Mastering Self-Improving AI Agents
Explore a comprehensive coding guide to Google Research’s RRSI (Regularized Recursive Self-Improvement), detailing how noise bands, cost rules, and…
Open-ended Scientific Discovery with Possibilistic Reasoning
arXiv:2610.11289v1 Announce Type: new Abstract: Autonomous scientific discovery with LLMs requires generating and testing hypotheses adaptively as…
Balancing Reference Guidance and Free Generation in Trajectory Rollouts for Reasoning RL
arXiv:2610.11128v1 Announce Type: new Abstract: A verified reference solution provides a correct trajectory for training a reasoning model. Alternatively,…
What to Admit and How to Present: Governing Persistent Memory in LLM Agents
arXiv:2610.11188v1 Announce Type: new Abstract: Persistent memory can improve personalization in LLM agents but can also induce sycophancy and…
GameCommBench: A Unified Benchmark and Type-Aware Evaluation for AI-Generated Game Commentary
arXiv:2610.11129v1 Announce Type: new Abstract: Game commentary is an open-ended generation task requiring multimodal perception, strategic reasoning, and…
Social Pain Disrupts Emotion-Action Brain-State Dynamics in Adolescents with Non-Suicidal Self-Injury
arXiv:2610.11155v1 Announce Type: new Abstract: Non-suicidal self-injury (NSSI) is prevalent among adolescents with depression, but the rapid brain-state…
US venture deal value reaches record $515.8B as exits fail to keep pace
Giant artificial intelligence rounds have pushed U.S. venture capital deal value about 44% past its previous annual record with a quarter still to go,…
AliO: Output Alignment Matters in Long-Term Time Series Forecasing
arXiv:2610.11213v1 Announce Type: new Abstract: Long-term Time Series Forecasting (LTSF) tasks, which leverage the current data sequence as input to…
AI News Brief Hourly Summary 2026-10-09 08h : 11 posts
11 posts published in the last hour 05:32Beyond Imitation: A Framework and Benchmark for LLM-Assisted Peer Review 05:32OpenProblemBench: Benchmarking AI on Open Problems in the Foundational Theoretical Sciences 05:32AgentHorizon: Evaluating Agentic Judges for Long-Horizon Computer-Use Tasks 05:32When Interfaces Speak: Data-Aware…