pith. sign in

Parallel-probe: Towards efficient parallel thinking via 2d probing

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.CL 2

years

2026 2

roles

background 1

polarities

background 1

representative citing papers

LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling

cs.CL · 2026-05-08 · conditional · novelty 8.0 · 2 refs

AutoTTS discovers width-depth test-time scaling controllers through agentic search in a pre-collected trajectory environment, yielding better accuracy-cost tradeoffs than hand-designed baselines on math reasoning tasks at low cost.

Process Rewards with Learned Reliability

cs.CL · 2026-05-15 · unverdicted · novelty 6.0

BetaPRM learns distributional step rewards with explicit reliability via Beta-Binomial modeling, enabling ACA that cuts token use by up to 33.57% while raising final-answer accuracy on reasoning benchmarks.

citing papers explorer

Showing 2 of 2 citing papers.

  • LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling cs.CL · 2026-05-08 · conditional · none · ref 6 · 2 links

    AutoTTS discovers width-depth test-time scaling controllers through agentic search in a pre-collected trajectory environment, yielding better accuracy-cost tradeoffs than hand-designed baselines on math reasoning tasks at low cost.

  • Process Rewards with Learned Reliability cs.CL · 2026-05-15 · unverdicted · none · ref 74

    BetaPRM learns distributional step rewards with explicit reliability via Beta-Binomial modeling, enabling ACA that cuts token use by up to 33.57% while raising final-answer accuracy on reasoning benchmarks.