Topic
adaptive
New Tool Synthesizes Adaptive Probabilistic Processors for Combinatorial Optimization Using Ising Model
Researchers have developed a tool for the synthesis and simulation of probabilistic architectures that map combinatorial optimization problems to the Ising model. The tool automatically constructs the Ising Hamiltonian and selects the best update algorithm among Gibbs Sampling, Simulated Annealing, Simulated Quantum Annealing, and cluster-based methods. Experimental results on benchmark problems demonstrate improved convergence behavior, supporting future hardware implementations based on MTJs and p-bits.
Adaptive Log-Correntropy Loss Boosts Deep Learning Under Heavy-Tailed Noise
Researchers propose ALCL, an adaptive log-correntropy loss function that learns its robustness parameters during training, outperforming standard losses in high-noise image benchmarks. The method improves median accuracy by up to 4.75% on grayscale and 4.51% on RGB datasets under heavy-tailed and impulsive noise.
Fast LLM-Based Semantic Filtering: Unified Framework and Adaptive Two-Phase Method Deliver 1.6–2.0x Speed Gains
A new research paper from Kim, Catheland, and Ailamaki introduces a unified framework and adaptive two-phase method for LLM-based semantic filtering. By composing model-free clustering and online-trained proxies adaptively, and using oracle confidence for multiple purposes, the method achieves 1.6–2.0x faster performance than prior cascades while meeting a 90% accuracy target on 95% of queries across three 10K-document corpora.
LectūraAgents Multi-Agent Framework Promises Adaptive Personalized AI-Assisted Learning
Researchers propose LectūraAgents, a multi-agent framework for adaptive personalized AI-assisted learning. It uses a hierarchical architecture with a ProfessorAgent leading specialized agents to generate and deliver tailored lecture content with embodied teaching actions. The system was validated on diverse courses and showed gains in content quality and personalization.
Adaptive kNN Graph Model Decouples Inference Latency from Complexity, Achieving Real-Time Classification
Researchers present an adaptive k-nearest neighbors graph model that decouples inference latency from computational complexity by integrating a Hierarchical Navigable Small World (HNSW) graph with a pre-computed voting mechanism. Benchmarking against eight baselines across six datasets shows real-time performance without compromising classification accuracy.
AdaMame: New Training Recipe Solves Language Collapse in Multilingual Reasoning Models
AdaMame, a two-stage training recipe for multilingual mathematical reasoning, addresses language collapse in large reasoning models. It adaptively aligns reasoning language to the query language without compromising accuracy, achieving Pareto-optimal performance across 12 languages.
MAGE-RAG: Multigranular Adaptive Graph Evidence Framework Improves Long-Document Multimodal QA Accuracy
The MAGE-RAG research paper introduces a multigranular adaptive graph evidence framework for multimodal retrieval-augmented generation (RAG) in long-document question answering. By building an evidence graph with page and element nodes and using an online controller to iteratively activate and prune evidence, it balances coverage and noise. Experiments show accuracy improvements over existing methods on LongDocURL and MMLongBench-Doc benchmarks.
APEX Adaptive Principle Extraction Framework Enables Multi-Dimensional Self-Evolution for Production AI Agents
Researchers propose APEX (Adaptive Principle EXtraction), a three-layer self-evolution framework that simultaneously improves an AI agent's prompt harness, behavioural principles, and workflow topology. Tested on the production-grade Joe AI agent built on NVIDIA Nemotron, APEX achieved a 90% improvement in Health Score over baseline, distilling six novel reusable principles and selecting a research-first workflow scoring 0.900 (+20%). The framework outperforms single-axis harness optimisation and requires only 4 LLM calls (~270 seconds).