Giving Credit Where It's Due: Redundancy-Aware Learning for Efficient Reasoning
arXiv:2609.27156v1 Announce Type: new Abstract: Large reasoning models can produce correct yet unnecessarily long reasoning traces. Existing methods improve reasoning efficiency with trajectory-level objectives or local token- and step-level signals, but rarely model inter-step semantic dependencie…
Read the full story at arXiv cs.CL ↗
Timeline · 1 report
- 2026-09-24 04:00 · arXiv cs.CL
Giving Credit Where It's Due: Redundancy-Aware Learning for Efficient Reasoning