Agent-ValueBench is the first dedicated benchmark for agent values, showing they diverge from LLM values, form a homogeneous 'Value Tide' across models, and bend under harnesses and skill steering.
EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
abstract
Large language models (LLMs) are expected to be trained to act as agents in various real-world environments, but this process relies on rich and varied tool-interaction sandboxes. However, access to real systems is often restricted; LLM-simulated environments are prone to hallucinations and inconsistencies; and manually built sandboxes are hard to scale. In this paper, we propose EnvScaler, an automated framework for scalable tool-interaction environments via programmatic synthesis. EnvScaler comprises two components. First, SkelBuilder constructs diverse environment skeletons through topic mining, logic modeling, and quality evaluation. Then, ScenGenerator generates multiple task scenarios and rule-based trajectory validation functions for each environment. With EnvScaler, we synthesize 191 environments and about 7K scenarios, and apply them to Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) for Qwen3 series models. Results on three benchmarks show that EnvScaler significantly improves LLMs' ability to solve tasks in complex environments involving multi-turn, multi-tool interactions. We release our code and data at https://github.com/RUC-NLPIR/EnvScaler.
citation-role summary
background 3
dataset 1
citation-polarity summary
years
2026 9polarities
background 4representative citing papers
CurateEvo evolves executable data-curation code using failed agent trajectories, improving post-training performance by 3.2 and 2.7 points over baselines on labeled and wild data respectively.
Qwen-AgentWorld are language world models that simulate multi-domain agent environments and boost general agent capabilities via decoupled RL simulation and unified foundation model training.
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.
TRUSTEE uses an 8B LM to simulate complete dynamic environments for RL-based tool learning and outperforms baselines that require extra external resources.
LemonHarness constrains LLM agent state changes to a defined workspace, supplies callable rule knowledge, and adds time awareness, yielding 84.49% and 86.52% accuracy on Terminal-Bench 2.0 with two GPT-5 backbones.
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.
A survey that organizes existing work on LLM-based agents around code as the central harness, structured in three layers of interfaces, mechanisms, and multi-agent scaling, with applications across domains and listed open challenges.
Generalizable agents require environment scaling via diverse executable rule-sets, distinguished from trajectory and task scaling in a new taxonomy.
citing papers explorer
-
Agent-ValueBench: A Comprehensive Benchmark for Evaluating Agent Values
Agent-ValueBench is the first dedicated benchmark for agent values, showing they diverge from LLM values, form a homogeneous 'Value Tide' across models, and bend under harnesses and skill steering.
-
CurateEvo: Data-Curation Evolving for Agentic Post-Training
CurateEvo evolves executable data-curation code using failed agent trajectories, improving post-training performance by 3.2 and 2.7 points over baselines on labeled and wild data respectively.
-
Qwen-AgentWorld: Language World Models for General Agents
Qwen-AgentWorld are language world models that simulate multi-domain agent environments and boost general agent capabilities via decoupled RL simulation and unified foundation model training.
-
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.
-
Democratizing Tool Learning with Environments Fully Simulated by a Free 8B Language Model
TRUSTEE uses an 8B LM to simulate complete dynamic environments for RL-based tool learning and outperforms baselines that require extra external resources.
-
LemonHarness Technical Report
LemonHarness constrains LLM agent state changes to a defined workspace, supplies callable rule knowledge, and adds time awareness, yielding 84.49% and 86.52% accuracy on Terminal-Bench 2.0 with two GPT-5 backbones.
-
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.
-
Code as Agent Harness
A survey that organizes existing work on LLM-based agents around code as the central harness, structured in three layers of interfaces, mechanisms, and multi-agent scaling, with applications across domains and listed open challenges.
-
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.