Tool-use agents suffer large accuracy drops from reward and transition perturbations but domain-randomized RL on static perturbations closes about 27% of the unseen transition gap while retaining most clean performance.
Cybersecurity For Beginners
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
MulDimIF introduces a multi-dimensional constraint framework and generation pipeline that reveals sharp performance drops in LLMs as instruction complexity rises and shows targeted training gains from attention module updates.
Structured reflection makes error diagnosis and repair an explicit trainable step that improves reliability and reduces redundant calls in tool-using LLM agents.
citing papers explorer
-
When Simulation Lies: A Sim-to-Real Benchmark and Domain-Randomized RL Recipe for Tool-Use Agents
Tool-use agents suffer large accuracy drops from reward and transition perturbations but domain-randomized RL on static perturbations closes about 27% of the unseen transition gap while retaining most clean performance.
-
MulDimIF: A Multi-Dimensional Constraint Framework for Evaluating and Improving Instruction Following in Large Language Models
MulDimIF introduces a multi-dimensional constraint framework and generation pipeline that reveals sharp performance drops in LLMs as instruction complexity rises and shows targeted training gains from attention module updates.
-
Failure Makes the Agent Stronger: Enhancing Accuracy through Structured Reflection for Reliable Tool Interactions
Structured reflection makes error diagnosis and repair an explicit trainable step that improves reliability and reduces redundant calls in tool-using LLM agents.