MemDLM embeds a simulated denoising trajectory into DLM training via bi-level optimization, creating a parametric memory that improves convergence and long-context performance even when the memory is dropped at test time.
Matthew Effect
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
SimpleTES scales test-time evaluation in LLMs to discover state-of-the-art solutions on 21 scientific problems across six domains, outperforming frontier models and optimization pipelines with examples like 2x faster LASSO and new Erdos constructions.
SOLAR introduces a self-optimizing agent using meta-learning on model weights and RL-driven strategy discovery for lifelong adaptation in LLMs, claiming superior performance on reasoning tasks across domains.
SMARTER boosts LLM toxicity detection and explanation performance by up to 13% macro-F1 on three hate-speech benchmarks through self-generated synthetic data and minimal-supervision preference optimization.
The paper delivers the first systematic review of self-evolving agents, structured around what components evolve, when adaptation occurs, and how it is implemented.
citing papers explorer
-
MemDLM: Memory-Enhanced DLM Training
MemDLM embeds a simulated denoising trajectory into DLM training via bi-level optimization, creating a parametric memory that improves convergence and long-context performance even when the memory is dropped at test time.
-
Evaluation-driven Scaling for Scientific Discovery
SimpleTES scales test-time evaluation in LLMs to discover state-of-the-art solutions on 21 scientific problems across six domains, outperforming frontier models and optimization pipelines with examples like 2x faster LASSO and new Erdos constructions.
-
SOLAR: A Self-Optimizing Open-Ended Autonomous Agent for Lifelong Learning and Continual Adaptation
SOLAR introduces a self-optimizing agent using meta-learning on model weights and RL-driven strategy discovery for lifelong adaptation in LLMs, claiming superior performance on reasoning tasks across domains.
-
SMARTER: A Data-efficient Framework to Improve Toxicity Detection with Explanation via Self-augmenting Large Language Models
SMARTER boosts LLM toxicity detection and explanation performance by up to 13% macro-F1 on three hate-speech benchmarks through self-generated synthetic data and minimal-supervision preference optimization.
-
A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence
The paper delivers the first systematic review of self-evolving agents, structured around what components evolve, when adaptation occurs, and how it is implemented.