Agentic-Ideation uses oracle-guided multi-agent synthesis to generate efficient training trajectories for scientific ideation agents, reporting 11.91% quality gains and over 10x sample efficiency versus workflow baselines.
hub
Towards general agentic intelligence via environment scaling.arXiv preprint arXiv:2509.13311
14 Pith papers cite this work. Polarity classification is still indexing.
14
Pith papers citing it
hub tools
citation-role summary
background 1
dataset 1
citation-polarity summary
polarities
background 2representative citing papers
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.
WRIT is a synthesis pipeline that generates write-read intensive trajectories along axes of write-decision count and per-decision evidence burden, enabling a 4B model to outperform GPT-5.1 on τ²-bench with reduced inference tokens.
GAIS synthesizes diverse, high-fidelity agentic tasks from real-world MCP servers and adversarial planning, outperforming LLM-only baselines on BFCL, τ²-Bench, and ACEBench with greater data efficiency.
OpenComputer introduces a verifier-grounded framework with state verifiers, self-evolving layers, task synthesis, and auditable evaluation for 33 desktop apps and 1000 tasks to support computer-use AI agents.
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.
An 8B LLM agent with code-based spatiotemporal analytics, procedural memory, and multi-stage agentic RL coordinates six coupled traffic-control tasks across three NYC boroughs in SUMO.
SIE framework automatically constructs scalable, verifiable reasoning environments from structured data, improving in-domain performance and enabling generalization to out-of-domain math and logic tasks.
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.
Longer action horizons bottleneck LLM agent training through instability, but training with reduced horizons stabilizes learning and enables better generalization to longer horizons.
STITCH trains superior agentic coding and reasoning LLMs by using fewer high-quality trajectories filtered to keep only critical decision tokens, delivering up to 63% relative gains on SWE-bench Verified.
Technical report announcing Ling-2.6 and Ring-2.6 models with hybrid linear attention, evolutionary CoT, and KPop RL for efficient agentic intelligence at scale.
MAVEN is a modular verification scaffold that lifts an open 120b model's tool-calling accuracy from 48% to 71% on MAVEN-Bench without retraining.
citing papers explorer
-
Agentic-Ideation: Sample Efficient Agentic Trajectories Synthesis for Scientific Ideation Agents
Agentic-Ideation uses oracle-guided multi-agent synthesis to generate efficient training trajectories for scientific ideation agents, reporting 11.91% quality gains and over 10x sample efficiency versus workflow baselines.
-
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.
-
WRIT: Write-Read Intensive Trajectory Synthesis for Multi-Turn User-Facing Agents
WRIT is a synthesis pipeline that generates write-read intensive trajectories along axes of write-decision count and per-decision evidence burden, enabling a 4B model to outperform GPT-5.1 on τ²-bench with reduced inference tokens.
-
Scaling Agentic Capabilities via Grounded Interaction Synthesis
GAIS synthesizes diverse, high-fidelity agentic tasks from real-world MCP servers and adversarial planning, outperforming LLM-only baselines on BFCL, τ²-Bench, and ACEBench with greater data efficiency.
-
OpenComputer: Verifiable Software Worlds for Computer-Use Agents
OpenComputer introduces a verifier-grounded framework with state verifiers, self-evolving layers, task synthesis, and auditable evaluation for 33 desktop apps and 1000 tasks to support computer-use AI agents.
-
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.
-
TrafficClaw: A Generalizable LLM Agent in the Unified Physical Environment for Urban Traffic Control
An 8B LLM agent with code-based spatiotemporal analytics, procedural memory, and multi-stage agentic RL coordinates six coupled traffic-control tasks across three NYC boroughs in SUMO.
-
Structured In-context Environment Scaling for Large Language Model Reasoning
SIE framework automatically constructs scalable, verifiable reasoning environments from structured data, improving in-domain performance and enabling generalization to out-of-domain math and logic tasks.
-
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.
-
On Training Large Language Models for Long-Horizon Tasks: An Empirical Study of Horizon Length
Longer action horizons bottleneck LLM agent training through instability, but training with reduced horizons stabilizes learning and enables better generalization to longer horizons.
-
Yet Even Less Is Even Better For Agentic, Reasoning, and Coding LLMs
STITCH trains superior agentic coding and reasoning LLMs by using fewer high-quality trajectories filtered to keep only critical decision tokens, delivering up to 63% relative gains on SWE-bench Verified.
-
Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale
Technical report announcing Ling-2.6 and Ring-2.6 models with hybrid linear attention, evolutionary CoT, and KPop RL for efficient agentic intelligence at scale.
-
MAVEN: Improving Generalization in Agentic Tool Calling
MAVEN is a modular verification scaffold that lifts an open 120b model's tool-calling accuracy from 48% to 71% on MAVEN-Bench without retraining.