SEAL co-evolves LLM agents and environments via shared turn-level failure diagnoses, yielding +8.25 to +26.25 point gains on tool-use tasks with only 400 samples.
Autoenv: Automated environments for measuring cross-environment agent learning
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
dataset 1
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5polarities
background 2representative citing papers
Agent-World autonomously synthesizes verifiable real-world tasks and uses continuous self-evolution to train 8B and 14B agents that outperform proprietary models on 23 benchmarks.
This survey categorizes agentic environments for LLMs by eight attributes and domains, introduces symbolic and neural synthesis paradigms with evaluation, and outlines four agent evolution pathways plus three environment evolution paradigms.
LAR learns a compact latent action space from trajectories that shortens the effective decision horizon for LLM agents, reducing token count and inference time while preserving task success.
Generalizable agents require environment scaling via diverse executable rule-sets, distinguished from trajectory and task scaling in a new taxonomy.
citing papers explorer
-
SEAL: Synergistic Co-Evolution of Agents and Learning Environments
SEAL co-evolves LLM agents and environments via shared turn-level failure diagnoses, yielding +8.25 to +26.25 point gains on tool-use tasks with only 400 samples.
-
Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence
Agent-World autonomously synthesizes verifiable real-world tasks and uses continuous self-evolution to train 8B and 14B agents that outperform proprietary models on 23 benchmarks.
-
Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application
This survey categorizes agentic environments for LLMs by eight attributes and domains, introduces symbolic and neural synthesis paradigms with evaluation, and outlines four agent evolution pathways plus three environment evolution paradigms.
-
Latent Action Reparameterization for Efficient Agent Inference
LAR learns a compact latent action space from trajectories that shortens the effective decision horizon for LLM agents, reducing token count and inference time while preserving task success.
-
Scalable Environments Drive Generalizable Agents
Generalizable agents require environment scaling via diverse executable rule-sets, distinguished from trajectory and task scaling in a new taxonomy.