← Back to all news
arXiv Machine Learning By Jingwei Ni, Dmitry Abulkhanov, Vladislav Smirnov, Markus Leippold, Elliott Ash, Timothy Baldwin, Artem Shelmanov, Mrinmaya Sachan

Same Beliefs, Different Policies: Learning Reusable Representations for Early Stopping in LLM Reasoning

Read the original on arXiv Machine Learning →

The paper introduces BELT (BELief-based Termination), a method that decouples outcome prediction from stopping control in large language models (LLMs). BELT learns beliefs about current and future answers from a frozen LLM’s hidden states and applies a linear stopping policy, enabling a single probe to adapt to various token‑price trade‑offs without retraining. Across five out‑of‑distribution math benchmarks, BELT cuts token usage by up to 51% while maintaining accuracy, and its lightweight probe outperforms stronger baselines in both efficiency and parameter count, also transferring effectively to coding and agentic tasks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Aug 21

Learning When to Think: Adaptive Reasoning for Test-Time Compute Allocation

arXiv:2608. 20256v1 Announce Type: new Abstract: Reasoning language models trained with reinforcement learning typically operate under a fixed token budget rather than an explicitly adaptive one, which can lead to over-computation on easy problems and insufficient computation on difficult ones.

By Gijs Kassenaar, Zhao Yang, Vincent Fran\c{c}ois-Lavet
llmsreinforcement-learningbenchmarks
More like this →
arXiv AI
Oct 21

PORA: Learning When More Reasoning Pays Off for LLM Agents

The paper introduces PORA, a method that teaches large language model agents to decide when to allocate more reasoning steps versus fewer, based on the expected downstream benefit. PORA trains by running each state twice—once with short reasoning and once with long reasoning—and learns to predict the value of extended reasoning. During inference, a controller uses this prediction and remaining budget information to choose the appropriate reasoning length without running both options, improving performance across diverse tasks.

By Bo Yan, Qi Zhang, Zhen Tan, Tianlong Chen, Song Wang
llmsagents
More like this →
arXiv Computation and Language
Oct 21

Adaptive Stopping of Streamed Reasoning for Language Model Agents

The paper introduces StreamStop, a lightweight stopping policy for reasoning-enabled language model agents that learns offline from prefix-level action agreement. By encoding available reasoning text with a frozen prefix reader and a stop head, StreamStop can decide when to stop reasoning without needing internal signals from the model. Experiments on WebShop and ScienceWorld show that StreamStop achieves higher success rates than many fixed-budget baselines while using fewer reasoning tokens, notably reducing token usage by 42% on WebShop with Qwen3.8-27B.

By JunHyeok Oh, Byung-Jun Lee
llmsagents
More like this →