Robust Function Calling for LLM Agents Under Interface Drift
SchemaShield-Lite restores Qwen3.5-9B function-calling accuracy after tool-interface drift without retraining.
Stories per day · 30 days
Relatedllm-agents2robustness2cipr1interface-drift1policy-regularization1post-training1qwen1schemashield1tool-use1
7 stories, newest first · one card per story
Stories tagged #function-calling
One Task, Many Interfaces: Simple Cross-Interface Consistency Training Improves LLM Agent Robustness
CIPR trains LLM agents to stay consistent across renamed or notationally changed interfaces.
A Coding Guide to TypeSafe AI Jev: Typed Decisions, Calibrated Confidence, and Speculative Fan-Out with a System One Model
Tutorial covers TypeSafe AI's Jev, a non-generative System One model returning typed choices, scores, and calibrated probabilities.
3
Verifiable Hidden Dynamics Play: Generating Agentic RL Environments from Solved Mechanisms
VHD-Play builds 3,300 agentic RL environments and lifts Qwen3.6-35B-A3B's mean score from 0.204 to 0.815.
Google Research Releases ToolGrad: Answer-First Framework Hits 99.8% Pass Rate for Tool-Use Data Generation
Google Research and partners introduce ToolGrad, a verified tool-chain-first data generation framework reaching 99.8% pass rate and boosting Gemma-3-12B to 83.1 on BFCL.
10
Explainability Assistant: A Conversational XAI Interface for Interpreting Energy Consumption Models
Researchers release Explainability Assistant, an open-source conversational XAI tool using LLM function calling, lifting intent-parsing accuracy from 76.8% to 94%.
ToolLoop: Closed-Loop Tool-Use Data Synthesis via Decomposed Generation and Dynamic Self-Feedback
ToolLoop introduces a closed-loop synthetic data framework whose 11K examples lift a 4B model to 86.40% on BFCL tool-use evaluation.