Showing 2026Show all
2 papers · 1 filter
cs.AI2026
ThinkRetrieve: Retrieval-Augmented Reasoning Traces for Test-Time Scaling
Vaibhav Singh, Soumya Suvra Ghosal, Sarvesh Gharat +3
Large Reasoning Models (LRMs) improve performance by allocating additional inference-time compute to generate extended chain-of-thought reasoning. However, recent studies reveal th…
cs.CL2026
Safety Recovery in Reasoning Models Is Only a Few Early Steering Steps Away
Soumya Suvra Ghosal, Souradip Chakraborty, Vaibhav Singh +3
Reinforcement learning (RL) based post-training for explicit chain-of-thought (e.g., GRPO) improves the reasoning ability of multimodal large-scale reasoning models (MLRMs). But re…