A cascaded large-small model system generates edit sketches with the large model and applies them with the small model to make code editing both accurate and token-efficient.
OpenCoder: The open cookbook for top-tier code large language models
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
The paper maps agent memory research via three forms (token-level, parametric, latent), three functions (factual, experiential, working), and dynamics of formation/evolution/retrieval, plus benchmarks and future directions.
A three-stage training pipeline internalizes world-model simulation and success estimation in LLM agents for improved planning on search and math tasks.
Combines GRPO with teacher-guided on-policy distillation and introduces LongBlocks dataset to yield more stable long-context reasoning than either method alone.
citing papers explorer
-
Cascaded Code Editing: Large-Small Model Collaboration for Effective and Efficient Code Editing
A cascaded large-small model system generates edit sketches with the large model and applies them with the small model to make code editing both accurate and token-efficient.
-
Memory in the Age of AI Agents
The paper maps agent memory research via three forms (token-level, parametric, latent), three functions (factual, experiential, working), and dynamics of formation/evolution/retrieval, plus benchmarks and future directions.
-
Internalizing the Future: A Unified Agentic Training Paradigm for World Model Planning
A three-stage training pipeline internalizes world-model simulation and success estimation in LLM agents for improved planning on search and math tasks.
-
A Recipe for Long-Context Reasoning in Large Language Models via On-Policy Optimization and Distillation
Combines GRPO with teacher-guided on-policy distillation and introduces LongBlocks dataset to yield more stable long-context reasoning than either method alone.