Skip to content
conftrace_

test-time reinforcement learning

5 papers

Explore in graph

Also known as

TTRL

Co-occurring keywords · papers mentioning both

selective-complementary reinforcement learning (1) positive pseudo-labeling (1) subgroup partitioning (1) confidence-based reward (1) enterprise log integration (1) region consistency (1) pseudo-label estimation (1) dense reward (1) schema mapping (1) gui grounding (1)

Papers

Beyond Majority Voting: Towards Fine-grained and More Reliable Reward Signal for Test-Time Reinforcement Learning ACL 2026 On-the-Fly VLA Adaptation via Test-Time Reinforcement Learning ACL 2026 Test-Time Reinforcement Learning for GUI Grounding via Region Consistency AAAI 2026 What If Consensus Lies? Selective-Complementary Reinforcement Learning at Test Time ACL 2026 Mapping Smarter, Not Harder: A Test-Time Reinforcement Learning Agent That Improve Without Labels or Model Updates EMNLP 2025