An LLM agent can improve itself at test time by rewriting its surrounding executable harness from unlabeled traces, using only proxy signals and a frozen model.
Teaching Large Language Models to Self-Debug , booktitle =
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
SAGE with MHFA improves failure recovery in autonomous research agents, raising metrics-bearing outputs from 42% to 92% on a 12-topic benchmark versus single-reflection baselines.
APMPO boosts average Pass@1 scores on math reasoning benchmarks by 3 points over GRPO by using an adaptive power-mean policy objective and feedback-driven clipping bounds in RLVR training.
FREIA applies free energy principles and adaptive advantage shaping to unsupervised RL, outperforming baselines by 0.5-3.5 Pass@1 points on math reasoning with a 1.5B model.
citing papers explorer
-
TTHE: Test-Time Harness Evolution
An LLM agent can improve itself at test time by rewriting its surrounding executable harness from unlabeled traces, using only proxy signals and a frozen model.
-
One Reflection Is Not Enough: Self-Correcting Autonomous Research via Multi-Hypothesis Failure Attribution
SAGE with MHFA improves failure recovery in autonomous research agents, raising metrics-bearing outputs from 42% to 92% on a 12-topic benchmark versus single-reflection baselines.
-
Adapt to Thrive! Adaptive Power-Mean Policy Optimization for Improved LLM Reasoning
APMPO boosts average Pass@1 scores on math reasoning benchmarks by 3 points over GRPO by using an adaptive power-mean policy objective and feedback-driven clipping bounds in RLVR training.
-
Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs
FREIA applies free energy principles and adaptive advantage shaping to unsupervised RL, outperforming baselines by 0.5-3.5 Pass@1 points on math reasoning with a 1.5B model.