Terminal-World is a skill-based synthesis pipeline that generates 5,723 training environments and produces Terminal-World-32B which outperforms baselines on Terminal-Bench 2.0 using only 1.2% of the data.
Webexplorer: Explore and evolve for training long-horizon web agents
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
baseline 1
citation-polarity summary
representative citing papers
SR²AM achieves competitive Pass@1 accuracy on diverse tasks with 25.8-95.3% fewer reasoning tokens than much larger models by using self-regulated simulative planning trained via supervised learning and RL.
Argus coordinates a Navigator and multiple Searchers via an evidence graph for deep research, reporting average gains of 5.5 points with one Searcher and 12.7 points with eight parallel Searchers across eight benchmarks, reaching 86.2 on BrowseComp with 64 Searchers.
SciResearcher automates creation of diverse scientific reasoning tasks from academic evidence to train an 8B model that sets new SOTA at 19.46% on HLE-Bio/Chem-Gold and gains 13-15% on SuperGPQA-Hard-Biology and TRQA-Literature.
Retrievers trained on agent trajectories via the LRAT framework improve evidence recall, task success, and efficiency in agentic search benchmarks.
MiroThinker shows that scaling agent-environment interactions via reinforcement learning lets a 72B open-source model reach up to 81.9% on GAIA and approach commercial performance on research benchmarks.
RAG reaches 0.66 weighted F1 on invalid bug report subclassification while agentic web search reaches 68.9% judge success on no-code fix generation, using a new gold-standard benchmark.
citing papers explorer
-
Terminal-World: Scaling Terminal-Agent Environments via Agent Skills
Terminal-World is a skill-based synthesis pipeline that generates 5,723 training environments and produces Terminal-World-32B which outperforms baselines on Terminal-Bench 2.0 using only 1.2% of the data.
-
Efficient Agentic Reasoning Through Self-Regulated Simulative Planning
SR²AM achieves competitive Pass@1 accuracy on diverse tasks with 25.8-95.3% fewer reasoning tokens than much larger models by using self-regulated simulative planning trained via supervised learning and RL.
-
Argus: Evidence Assembly for Scalable Deep Research Agents
Argus coordinates a Navigator and multiple Searchers via an evidence graph for deep research, reporting average gains of 5.5 points with one Searcher and 12.7 points with eight parallel Searchers across eight benchmarks, reaching 86.2 on BrowseComp with 64 Searchers.
-
SciResearcher: Scaling Deep Research Agents for Frontier Scientific Reasoning
SciResearcher automates creation of diverse scientific reasoning tasks from academic evidence to train an 8B model that sets new SOTA at 19.46% on HLE-Bio/Chem-Gold and gains 13-15% on SuperGPQA-Hard-Biology and TRQA-Literature.
-
Learning to Retrieve from Agent Trajectories
Retrievers trained on agent trajectories via the LRAT framework improve evidence recall, task success, and efficiency in agentic search benchmarks.
-
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling
MiroThinker shows that scaling agent-environment interactions via reinforcement learning lets a 72B open-source model reach up to 81.9% on GAIA and approach commercial performance on research benchmarks.
-
Automated Root-Cause Subclassification and No-Code Fix Generation for Invalid Bug Reports
RAG reaches 0.66 weighted F1 on invalid bug report subclassification while agentic web search reaches 68.9% judge success on no-code fix generation, using a new gold-standard benchmark.