EvoGuard improves agent skill evolution by 11% on ALFWorld
EvoGuard uses pairwise rejection sampling on private test sets to select non-degrading skills at low latency.
Stories per day · 30 days
3 RSS
Relatedchain-of-thought1efficiency1language-agents1mathematics1reasoning-distillation1skill-evolution1student-models1
4 stories, newest first · one card per story
Stories tagged #rejection-sampling
CoTranslator: Reverse to Forward Chain-of-Thought Translator for Reasoning Distillation
CoTranslator turns reverse chain-of-thought into verified forward traces, cutting distillation compute while keeping most math accuracy.
Perplexity Trains Its Computer Agent on Real Mistakes With Hint-Guided Self-Distillation
Perplexity reports a 21.2% live drop in Computer agent tool failures after hint-guided self-distillation.
4
Agent-Editing World Model: Rethinking World Modeling for LLM Agents
AEWM edits contaminated agent state and improves six benchmarks by 3.2 to 6.7 points over the strongest baseline.