arXiv:2608.29028v1 Announce Type: new Abstract: Multi-agent LLM systems often coordinate by compressing an upstream interaction into a handoff artifact…
Category: AI
Selective Forgetting: A Graph-Based Memory Framework for Long-Term LLM Agents
arXiv:2608.28978v1 Announce Type: new Abstract: Knowledge graphs have been proposed as a structured alternative to flat retrieval-augmented generation for…
Efficient GPU Retrieval for Semantic Search
arXiv:2608.28968v1 Announce Type: new Abstract: Semantic Search on LinkedIn must retrieve relevant profiles from a corpus of hundreds of millions in…
Agentic AI uncovers conserved cross-tissue protein co-abundance programs inaccessible to single-dataset analysis
arXiv:2608.28990v1 Announce Type: new Abstract: Protein co-abundance clusters preserved across tissues can reveal shared disease mechanisms and candidate…
From Analytics to Tumor Boards: An Evidence-Linked Multi-Agent Workflow for Oncology Feature Extraction
arXiv:2608.28974v1 Announce Type: new Abstract: Clinically relevant oncology information is distributed across heterogeneous, longitudinal documentation,…
The Role of Network Topology and Opponent Information in Shaping Cooperation in Multi-Agent Reinforcement Learning Systems
arXiv:2608.28977v1 Announce Type: new Abstract: Several works have investigated the influence of graph topology on cooperation among artificial agents,…
Automated Researchers Can Reliably Mitigate Alignment Failures
arXiv:2608.28945v1 Announce Type: new Abstract: Automating alignment research may accelerate progress toward aligned AI, but whether it does is hard to…
Evaluating the Hidden Costs of Personalization in Large Language Models
arXiv:2608.28833v1 Announce Type: new Abstract: While Large language models (LLMs) incorporate user personalization signals to improve usability and…
From Location Phrases to Geographic Entities: Task-Adapted Retrieval for People Search
arXiv:2608.28965v1 Announce Type: new Abstract: People search must map free-form location phrases to geographic entities used as structured retrieval…
Oculi: A Conversational Agentic Platform for Automated Credit Risk Analysis
arXiv:2608.28944v1 Announce Type: new Abstract: Credit risk analysis in financial institutions traditionally requires analysts to manually write SQL…