Pith. sign in

REVIEW 2 cited by

DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories Search

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.03864 v2 pith:T5VHAMGE submitted 2024-10-04 cs.AI cs.CLcs.LG

DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories Search

classification cs.AI cs.CLcs.LG
keywords reasoningllmstask-solvingcapabilityoptimaltrajectoriesactionactions
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Enhancing the capability of large language models (LLMs) in reasoning has gained significant attention in recent years. Previous studies have demonstrated the effectiveness of various prompting strategies in aiding LLMs in reasoning (called "reasoning actions"), such as step-by-step thinking, reflecting before answering, solving with programs, and their combinations. However, these approaches often applied static, predefined reasoning actions uniformly to all questions, without considering the specific characteristics of each question or the capability of the task-solving LLM. In this paper, we propose DOTS, an approach enabling LLMs to reason dynamically via optimal reasoning trajectory search, tailored to the specific characteristics of each question and the inherent capability of the task-solving LLM. Our approach involves three key steps: i) defining atomic reasoning action modules that can be composed into various reasoning action trajectories; ii) searching for the optimal action trajectory for each training question through iterative exploration and evaluation for the specific task-solving LLM; and iii) using the collected optimal trajectories to train an LLM to plan for the reasoning trajectories of unseen questions. In particular, we propose two learning paradigms, i.e., fine-tuning an external LLM as a planner to guide the task-solving LLM, or directly fine-tuning the task-solving LLM with an internalized capability for reasoning actions planning. Our experiments across eight reasoning tasks show that our method consistently outperforms static reasoning techniques and the vanilla instruction tuning approach. Further analysis reveals that our method enables LLMs to adjust their computation based on problem complexity, allocating deeper thinking and reasoning to harder problems.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. TIME: Temporally Intelligent Meta-reasoning Engine for Context-Triggered Explicit Reasoning

    cs.LG 2026-01 unverdicted novelty 7.0

    TIME trains LLMs to trigger compact, context-triggered reasoning via time tags and tick events, improving TIMEBench scores while cutting explicit reasoning tokens by an order of magnitude.

  2. DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments

    cs.AI 2025-04 conditional novelty 6.0

    End-to-end RL in authentic web environments produces LLM research agents that outperform prompt-engineering and RAG-based baselines by up to 28.9 and 7.2 points respectively while exhibiting emergent planning, cross-v...