Hista and Numca C

AI benchmark · Machine Learning

Domains
Machine Learning
Tier
C why
Snapshot

Full listing name: Hista and Numca: Estimate State Value Effectively for LLM Reinforcement Learning

What is Hista and Numca?

Reinforcement learning (RL) refines large language models (LLMs) by directly optimizing model behavior through reward signals. While accurate state value estimation is critical for stable training in classical RL, it remains an underexplored challenge in LLM post-training. In this work, we introduce the State Value Estimation Benchmark (SVEB) to assess state estimation within existing RL frameworks and show that critics in standard approaches like PPO collapse to a coarse group-average baseline. To address this, we propose two techniques: Numca, which leverages numerical spans as gradable milestones for state value estimation, and Hista, a framework that uses LLM's hidden states as representation to weighted average disjoint rollouts and their return. Extensive experiments demonstrate that both methods yield more accurate state value estimates and enhance training performance across different RL algorithms and model sizes without incurring significant computational overhead.

Tier C · a leaderboard, listed apart

C

Niche: a handful of models scored, or built by an RL vendor.

How much stands behind a tier: usage, who backs it, a confirmed line from its own site or paper, and a clear read on X. High with three of the four, medium with two, low otherwise.

  • 7 models scored
  • in curated RL directories (1 pt)
How we got to tier C
  1. Adoption: 7 models scored. Tier C.
  2. Not yet read on X.
  3. In curated RL directories: 1 point, a floor of none.
  4. Not yet confirmed by a line from its own site or paper.
  5. Judged a leaderboard, arena or index rather than one benchmark (or not a benchmark at all): listed apart.

A clear view on X moves a tier one step up or down; most entries don't move. How tiers work.

Not on the map yet: no line from its own site or paper places it in a domain.

More Machine Learning AI benchmarks

Next: browse all benchmarks. Entry from the RL Research daily scrape of public sources, 2026-10-11 snapshot.