R2V-Agent combines an SLM policy trained via BC and DPO with a step-level risk-calibrated router using Brier scores and CVaR to escalate to LLM only on high residual failure risk, improving success-cost tradeoffs on HumanEval+, TextWorld, and TerminalBench.
TDD for Embedded Systems: A Basic Approach and Toolset
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
The evolution of information technology and electronics in general has been consistently increasing the use of embedded systems. While hardware development for these systems is already consistent, software development for embedded systems still lacks a consolidated methodology. This paper describes a process and toolset for Embedded Systems Validation and Verification using FSM (Finite State Machines) and TDD (Test Driven Development).
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
R2V Agent: Teaching SLMs When to Ask for Help
R2V-Agent combines an SLM policy trained via BC and DPO with a step-level risk-calibrated router using Brier scores and CVaR to escalate to LLM only on high residual failure risk, improving success-cost tradeoffs on HumanEval+, TextWorld, and TerminalBench.