works on
credit assignment 1graph-structured retrieval 1question answering 1reinforcement learning 1search agents 1

From the 1 of 6 linked papers with an AI index.

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

TRIM: Hybrid Inference via Targeted Stepwise Routing in Multi-Step Reasoning Tasks

Vansh Kapoor, Aman Gupta, Hao Chen +3

Multi-step reasoning tasks like mathematical problem solving are vulnerable to cascading failures, where a single incorrect step leads to complete solution breakdown. Current LLM r…