Pith. sign in

REVIEW 14 cited by

AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning

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 2505.11896 v2 pith:3C76NJUK submitted 2025-05-17 cs.LG cs.AI

AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning

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

Large Language Models (LLMs) have demonstrated remarkable capabilities but often face challenges with tasks requiring sophisticated reasoning. While Chain-of-Thought (CoT) prompting significantly enhances reasoning, it indiscriminately generates lengthy reasoning steps for all queries, leading to substantial computational costs and inefficiency, especially for simpler inputs. To address this critical issue, we introduce AdaCoT (Adaptive Chain-of-Thought), a novel framework enabling LLMs to adaptively decide when to invoke CoT. AdaCoT framed adaptive reasoning as a Pareto optimization problem that seeks to balance model performance with the costs associated with CoT invocation (both frequency and computational overhead). We propose a reinforcement learning (RL) based method, specifically utilizing Proximal Policy Optimization (PPO), to dynamically control the CoT triggering decision boundary by adjusting penalty coefficients, thereby allowing the model to determine CoT necessity based on implicit query complexity. A key technical contribution is Selective Loss Masking (SLM), designed to counteract decision boundary collapse during multi-stage RL training, ensuring robust and stable adaptive triggering. Experimental results demonstrate that AdaCoT successfully navigates the Pareto frontier, achieving substantial reductions in CoT usage for queries not requiring elaborate reasoning. For instance, on our production traffic testset, AdaCoT reduced CoT triggering rates to as low as 3.18\% and decreased average response tokens by 69.06%, while maintaining high performance on complex tasks.

discussion (0)

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

Forward citations

Cited by 14 Pith papers

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

  1. Thinking Without Words: Efficient Latent Reasoning with Abstract Chain-of-Thought

    cs.CL 2026-04 unverdicted novelty 7.0

    Abstract-CoT lets models reason with short discrete latent token sequences from a reserved vocabulary, using warm-up training and RL to match verbal CoT performance with up to 11.6x fewer tokens.

  2. Beyond Majority Voting: Towards Fine-grained and More Reliable Reward Signal for Test-Time Reinforcement Learning

    cs.CL 2025-12 unverdicted novelty 7.0

    SCOPE uses step-wise confidence and dynamic subgroups to create finer pseudo-labels in test-time RL, delivering 13.1% relative gains on AIME 2025 over majority-voting baselines.

  3. APIVOT: Adaptive Planning with Interleaved Vision-Language Thoughts

    cs.CV 2026-07 conditional novelty 6.0

    A VLM planner that adaptively inserts latent visual thoughts of future states into its reasoning trace beats language-only and prior VLM planners on long-horizon kitchen tasks, especially under tight free space.

  4. DyCon: Dynamic Reasoning Control via Evolving Difficulty Modeling

    cs.AI 2026-06 unverdicted novelty 6.0

    DyCon dynamically controls reasoning depth in LRMs by modeling evolving difficulty from step-level embeddings, reducing redundant steps across multiple benchmarks.

  5. Efficient Agentic Reasoning Through Self-Regulated Simulative Planning

    cs.AI 2026-05 unverdicted novelty 6.0

    SR²AM achieves competitive Pass@1 accuracy on diverse tasks with 25.8-95.3% fewer reasoning tokens than much larger models by using self-regulated simulative planning trained via supervised learning and RL.

  6. Taming the Thinker: Conditional Entropy Shaping for Adaptive LLM Reasoning

    cs.CL 2026-05 unverdicted novelty 6.0

    CES applies conditional bidirectional entropy control on top of DAPO to improve accuracy and shorten responses on mathematical benchmarks for 7B and 1.5B LLMs.

  7. Case-Based Calibration of Adaptive Reasoning and Execution for LLM Tool Use

    cs.AI 2026-05 unverdicted novelty 6.0

    CAST extracts complexity and failure profiles from historical tool-use trajectories to drive adaptive reasoning and fine-grained rewards in RL, yielding up to 5.85 pp higher execution accuracy and 26% shorter reasonin...

  8. CoWorld-VLA: Thinking in a Multi-Expert World Model for Autonomous Driving

    cs.CV 2026-05 unverdicted novelty 6.0

    CoWorld-VLA encodes world information into four expert tokens that condition a diffusion-based planner, yielding competitive collision avoidance and trajectory accuracy on the NAVSIM benchmark.

  9. CoWorld-VLA: Thinking in a Multi-Expert World Model for Autonomous Driving

    cs.CV 2026-05 unverdicted novelty 6.0

    CoWorld-VLA extracts semantic, geometric, dynamic, and trajectory expert tokens from multi-source supervision and feeds them into a diffusion-based hierarchical planner, achieving competitive collision avoidance and t...

  10. CODA: Difficulty-Aware Compute Allocation for Adaptive Reasoning

    cs.CL 2026-03 unverdicted novelty 6.0

    CODA uses rollout-based difficulty signals to drive two gates that penalize verbosity on easy instances and promote deliberation on hard ones, cutting token use over 60% on simple tasks while maintaining accuracy.

  11. Spatial Reasoning via Modality Switching Between Language and Symbolic Representation

    cs.AI 2026-06 unverdicted novelty 5.0

    Introduces a trustworthiness-and-complexity switching metric that lets LLMs choose between language and grid modalities for spatial reasoning, yielding up to 42% gains in tested settings.

  12. Spatial Reasoning via Modality Switching Between Language and Symbolic Representation

    cs.AI 2026-06 unverdicted novelty 5.0

    Introduces a modality-switching mechanism for LLMs on spatial reasoning tasks using a trustworthiness and complexity based metric, showing up to 42% performance improvement.

  13. SuCo: Sufficiency-guided Continuous Adaptive Reasoning

    cs.CL 2026-06 unverdicted novelty 4.0

    SuCo defines minimal sufficient CoT and applies a two-stage fine-tuning plus RL framework to enable continuous adaptive reasoning control, claiming gains in both accuracy and token efficiency on math, code, and science tasks.

  14. Seedream 4.0: Toward Next-generation Multimodal Image Generation

    cs.CV 2025-09 unverdicted novelty 3.0

    Seedream 4.0 unifies text-to-image synthesis, image editing, and multi-image composition in an efficient diffusion transformer pretrained on billions of pairs and accelerated to 1.8 seconds for 2K output.