Pith. sign in

REVIEW 3 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

classification cs.AIcs.CLcs.LG
keywords reasoningllmstask-solvingcapabilityoptimaltrajectoriesactionactions
verification ladder T0 review T1 audit T2 compute T3 formal
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). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

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

  1. Route to Reason: Adaptive Routing for LLM and Reasoning Strategy Selection

    cs.CL 2025-05 conditional novelty 6.0 of 10

    Route-To-Reason learns to predict the accuracy and token usage of each model-strategy pair and routes every query to the pair that maximizes a tunable accuracy-cost score.

  2. LETToT: Label-Free Evaluation of Large Language Models On Tourism Using Expert Tree-of-Thought

    cs.CL 2025-08 reject novelty 5.0 of 10

    LETToT scores LLM tourism answers by counting coverage of expert-designed reasoning elements, and finds reasoning-enhanced small models beat larger non-reasoning models on that rubric.

  3. PresentAgent: Multimodal Agent for Presentation Video Generation

    cs.CV 2025-07 reject novelty 5.0 of 10

    PresentAgent chains LLM segmentation, slide rendering, TTS, and ffmpeg to turn documents into narrated presentation videos, but the human-level claim rests on five documents and an unvalidated VLM judge.

Pith tools