arXiv:2609.08407v2 Announce Type: replace Abstract: In this study, we identify depth-dependent prefix redundancy in final-readout LLM embedding models,…
GoAnt: Quality-Diversity Multi-Agent Search for Alpha Factor Discovery in Market Microstructure Data
arXiv:2609.08719v2 Announce Type: replace Abstract: Automated alpha factor discovery searches symbolic trading signals from price-volume panels and…
Reason Through the Latent! Making Latent Visual Reasoning Necessary
arXiv:2609.06746v2 Announce Type: replace Abstract: Latent visual reasoning aims to perform multimodal reasoning through hidden-state computation rather…
Optimizing Three Critical Factors for Practical and Effective OOD Detection Fine-Tuning
arXiv:2308.01030v2 Announce Type: replace-cross Abstract: In out-of-distribution (OOD) detection, fine-tuning with auxiliary outlier data often improves…
Cognition Releases SWE-2: A Kimi K3 Post-Trained Coding Model That Matches Fable 5.1 on FrontierCode at 64% Lower Cost
Cognition, the company behind the Devin coding agent, has released SWE-2, its most capable coding model to date. SWE-2 is post-trained with reinforcement…
Why Sample What You Can Enumerate? Exact Policy Optimization for Genomic Tool Selection
arXiv:2609.10221v2 Announce Type: replace Abstract: Reinforcement learning over a frozen reasoner has become a common recipe for teaching a policy which…
AI News Brief Hourly Summary 2026-09-13 02h : 11 posts
11 posts published in the last hour 23:32Learning What to Retain: Gated-Memory Routing for Efficient Collaboration in Multi-Agent LLM Systems 23:32HarvestBench: Measuring Whether LLM Agents Will Pay to Avoid Killing Animals 23:32Planning and Scheduling Business Processes under Control-Flow Uncertainty: Extended…
Learning What to Retain: Gated-Memory Routing for Efficient Collaboration in Multi-Agent LLM Systems
arXiv:2609.00237v2 Announce Type: replace Abstract: Large language model (LLM)-based multi-agent systems tackle complex reasoning by orchestrating how…
HarvestBench: Measuring Whether LLM Agents Will Pay to Avoid Killing Animals
arXiv:2609.04444v2 Announce Type: replace Abstract: HarvestBench is the first benchmark to 1) put a price on avoiding a side effect and 2) name the side…
Planning and Scheduling Business Processes under Control-Flow Uncertainty: Extended Version
arXiv:2609.05578v2 Announce Type: replace Abstract: Scheduling activities in business processes can improve efficiency (e.g., reduce makespan), but is…
SimSkill: A Self-Evolving LLM Agent for Skill and Knowledge Accumulation in Traffic Simulation
arXiv:2609.03753v2 Announce Type: replace Abstract: Cumulative culture enables humans to preserve, reuse, and extend knowledge and skills across…
GameWAM: A World Action Model for Video Games
arXiv:2608.26200v2 Announce Type: replace Abstract: Modern video games combine first-person perception, rapid visual changes, persistent world state, and…
VALG: An Agentic System for ML Theory Research
arXiv:2608.13060v2 Announce Type: replace Abstract: Machine learning theory studies learning procedures through mathematical setups in which the data…
A Density-Matrix Framework for Electronic-Structure Analysis of Electrolytes for Lithium Batteries
arXiv:2607.25597v3 Announce Type: replace Abstract: Electrolyte reactivity in lithium batteries is shaped by molecular functional groups, Li$^{+}$…
Clearing the Fog: Towards Installing and Refining Proactive Exploration Capabilities in LLM Agents
arXiv:2608.14339v2 Announce Type: replace Abstract: We study proactive exploration in LLM agents, i.e., the ability to explore an environment to acquire…
Efficient Adaptation of LLMs for Hate Speech Detection in Low-Resource Languages: A Comparative Study on Roman Urdu
arXiv:2608.18142v2 Announce Type: replace Abstract: It is challenging to detect hate speech in Low Resource Languages (LRLs) because of the absence of…
Improving Natural-Language Combinatorial-Optimization Accuracy in Resource-Constrained Language Models via Formal Abstractions
arXiv:2608.18409v2 Announce Type: replace Abstract: Combinatorial scheduling poses a significant challenge for language models, requiring them to identify…
AI News Brief Hourly Summary 2026-09-13 01h : 15 posts
15 posts published in the last hour 22:32Ceci n’est pas une pipe: AI systems as semantic abstractions 22:32Verification of Adaptive Agentic Controllers through Finite Rule Revision 22:32SGA: Plug&Play Geometric Verification for Educational Video Synthesis 22:32Relevance Is Not Permission: Localizing and…