Week of August 17, 2026
2026-W34
Automated weekly tranche (heuristic): 20 papers. MLLM-Routed Heterogeneous Ensembles for Robust Cross-Dataset Image Classification; Capability Sheaves for Compositional Agent-Harness Repair; A Unifying Perspective on Causal World Models; AaLLM. Prior week 2026-W33 remains in archive.
MLLM-Routed Heterogeneous Ensembles for Robust Cross-Dataset Image Classification
Heuristic score based on topical heat terms (4 hits) and claim-language signals. Editorial review recommended before publish.
Capability Sheaves for Compositional Agent-Harness Repair: Controlled Quotients and a Real-Repository Stress Test
Heuristic score based on topical heat terms (2 hits) and claim-language signals. Editorial review recommended before publish.
A Unifying Perspective on Causal World Models: From Observations to Representations to Structure
Heuristic score based on topical heat terms (3 hits) and claim-language signals. Editorial review recommended before publish.
AaLLM: An End-to-End Analog Circuit Design Framework from Topology Generation to Sizing Using Large Language Models
Heuristic score based on topical heat terms (2 hits) and claim-language signals. Editorial review recommended before publish.
Rules or Character? Scaling Laws for AI Safety Design
Heuristic score based on topical heat terms (2 hits) and claim-language signals. Editorial review recommended before publish.
RippleMem: From Isolated Retrieval to Associative Recollection for Long-Term Agent Memory
Heuristic score based on topical heat terms (2 hits) and claim-language signals. Editorial review recommended before publish.
Reasoning for Social Audio-Visual Question Answering: Where Do We Stand?
Heuristic score based on topical heat terms (2 hits) and claim-language signals. Editorial review recommended before publish.
GEM: A Generative Embedding Model Bridging Reasoning and Retrieval
Heuristic score based on topical heat terms (2 hits) and claim-language signals. Editorial review recommended before publish.
Foundation models for movement data: Are they ready for prime-time?
Heuristic score based on topical heat terms (1 hits) and claim-language signals. Editorial review recommended before publish.
MARC v1: An Open-Source Multi-Agent Framework for Clinical AI Reasoning and Coordination
Heuristic score based on topical heat terms (2 hits) and claim-language signals. Editorial review recommended before publish.
Enhancing Virtual Agents through SLMs and Edge-Computing: An Exploratory Evaluation of Think and Memory Processes
Heuristic score based on topical heat terms (2 hits) and claim-language signals. Editorial review recommended before publish.
StateBridge: Training-free Hidden-state Alignment for Latent Communication in LLM Multi-Agent Systems
Heuristic score based on topical heat terms (2 hits) and claim-language signals. Editorial review recommended before publish.
How Good are Foundation Models in Longitudinal MRI Disease Progression Reasoning?
Heuristic score based on topical heat terms (2 hits) and claim-language signals. Editorial review recommended before publish.
Teach the Magnitude, Not the Direction: Verifier-Bounded Credit Assignment for Multi-Turn Multi-step LLM Agents
Heuristic score based on topical heat terms (2 hits) and claim-language signals. Editorial review recommended before publish.
Beyond Local Accuracy: A Protocol-Level Identifiability Audit for Controlled LLM Reasoning Evaluation
Heuristic score based on topical heat terms (1 hits) and claim-language signals. Editorial review recommended before publish.
NestDex: Nested Policy Learning with Copilot Assisted Teleoperation for Dexterous Manipulation
Heuristic score based on topical heat terms (1 hits) and claim-language signals. Editorial review recommended before publish.
Evaluation of Clinically Steerable Retinal Image Generation from Foundation Model Latent Spaces
Heuristic score based on topical heat terms (1 hits) and claim-language signals. Editorial review recommended before publish.
LLM-Assisted Dynamic Threat Analysis for Attacker-Reachable Software Weaknesses in Autonomous Vehicles
Heuristic score based on topical heat terms (1 hits) and claim-language signals. Editorial review recommended before publish.
Algebraic Decomposition Theory for Transformer Length Generalization
Heuristic score based on topical heat terms (1 hits) and claim-language signals. Editorial review recommended before publish.
RAIL: An Automatic Classifier of the Artificial Intelligence Readiness Level
Heuristic score based on topical heat terms (1 hits) and claim-language signals. Editorial review recommended before publish.