Pith. sign in

REVIEW 18 cited by

Token-Budget-Aware LLM Reasoning

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 2412.18547 v5 pith:KIERGE5Z submitted 2024-12-24 cs.CL cs.AIcs.LG

Token-Budget-Aware LLM Reasoning

classification cs.CL cs.AIcs.LG
keywords reasoningtokenbudgetcostsllmsperformancetoken-budget-awareaccuracy
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Reasoning is critical for large language models (LLMs) to excel in a wide range of tasks. While methods like Chain-of-Thought (CoT) reasoning and enhance LLM performance by decomposing problems into intermediate steps, they also incur significant overhead in token usage, leading to increased costs. We find that the reasoning process of current LLMs is unnecessarily lengthy and it can be compressed by including a reasonable token budget in the prompt, but the choice of token budget plays a crucial role in the actual compression effectiveness. We then propose a token-budget-aware LLM reasoning framework that dynamically adjusts the number of reasoning tokens based on the reasoning complexity of each problem. Experiments show that our method effectively reduces token costs in CoT reasoning with only a slight performance reduction, offering a practical solution to balance efficiency and accuracy in LLM reasoning. Code: https://github.com/GeniusHTX/TALE

discussion (0)

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

Forward citations

Cited by 18 Pith papers

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

  1. Post Reasoning: Improving the Performance of Non-Thinking Models at No Cost

    cs.AI 2026-05 conditional novelty 7.0

    Post-Reasoning boosts LLM accuracy by reversing the usual answer-after-reasoning order, delivering mean relative gains of 17.37% across 117 model-benchmark pairs with zero extra cost.

  2. Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs

    cs.CL 2024-12 unverdicted novelty 7.0

    o1-like models overthink easy tasks; self-training reduces compute use without accuracy loss on GSM8K, MATH500, GPQA, and AIME.

  3. The Harness Effect: How Orchestration Design Sets the Token Economics of Enterprise Agentic AI

    cs.AI 2026-07 conditional novelty 6.0

    Swapping only the orchestration layer around six AI models cut token cost per task 41% and latency 44% with quality at parity, making orchestration a bigger cost lever than model choice.

  4. POIROT: Interrogating Agents for Failure Detection in Multi-Agent Systems

    cs.AI 2026-06 unverdicted novelty 6.0

    POIROT protocol repurposes agents in LLM multi-agent systems as an internal diagnostic layer for failure detection, outperforming single-LLM evaluators with gains that increase with complexity, agent count, and fault types.

  5. Thinking with Reasoning Skills: Fewer Tokens, More Accuracy

    cs.AI 2026-04 unverdicted novelty 6.0

    Distilling and retrieving reusable reasoning skills lets LLMs solve coding and math problems with fewer tokens and higher accuracy.

  6. How Much Thinking is Enough? Quantifying and Understanding Redundancy in LLM Reasoning

    cs.AI 2026-04 conditional novelty 6.0

    Across four frontier reasoning models, 61–93% of correct chain-of-thought steps are redundant, and this over-thinking is provably optimal under any length-agnostic outcome reward.

  7. LightThinker++: From Reasoning Compression to Memory Management

    cs.CL 2026-04 unverdicted novelty 6.0

    LightThinker++ adds explicit adaptive memory management and a trajectory synthesis pipeline to LLM reasoning, cutting peak token use by ~70% while gaining accuracy in standard and long-horizon agent tasks.

  8. Retrieval-of-Thought: Efficient Reasoning via Reusing Thoughts

    cs.AI 2025-09 unverdicted novelty 6.0

    Retrieval-of-Thought organizes prior reasoning into a thought graph for retrieval and reward-guided recombination, reducing output tokens by up to 40% and latency by 82% while preserving accuracy on reasoning benchmarks.

  9. Trading Human Curation for Synthetic Augmentation in RLVR

    cs.LG 2026-06 conditional novelty 5.0

    Gated synthetic augmentations of a 10-task human base substitute for ~87 extra human RLVR tasks on aggregate held-out pass@1, with cost-adjusted trade rate ρ_cost in [1.4×, 11.6×].

  10. Early Stopping Chain-of-thoughts in Large Language Models

    cs.CL 2025-09 conditional novelty 5.0

    ES-CoT shortens LLM chain-of-thought generation by tracking runs of identical step answers after linguistic markers, cutting tokens 16% on average while keeping accuracy comparable to full CoT across six datasets and ...

  11. Self-Aligned Reward: Towards Effective and Efficient Reasoners

    cs.LG 2025-09 unverdicted novelty 5.0

    Self-aligned reward uses relative perplexity differences to encourage concise, query-specific reasoning in LLMs, yielding 4% accuracy gains and 30% lower inference cost when added to PPO or GRPO.

  12. Search-Based Multi-Trajectory Refinement for Safe C-to-Rust Translation with Large Language Models

    cs.PL 2025-05 unverdicted novelty 5.0

    LAC2R uses MCTS to systematically explore multiple LLM refinement trajectories for C-to-Rust translation and reports superior safety and correctness on small-scale benchmarks.

  13. Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models

    cs.CL 2025-03 accept novelty 5.0

    A survey organizing techniques to achieve efficient reasoning in LLMs by shortening chain-of-thought outputs.

  14. Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models

    cs.AI 2025-03 unverdicted novelty 5.0

    The paper unifies perspectives on Long CoT in reasoning LLMs by introducing a taxonomy, detailing characteristics of deep reasoning and reflection, and discussing emergence phenomena and future directions.

  15. The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes

    cs.CL 2026-06 unverdicted novelty 4.0

    A literature survey that introduces a taxonomy for LLM reasoning paradigms, analyzes methodological trends, and synthesizes failure modes from over 300 papers.

  16. Trading Human Curation for Synthetic Augmentation in RLVR

    cs.LG 2026-06 unverdicted novelty 4.0

    Gated synthetic augmentations can substitute for additional human-authored RLVR tasks at a cost-adjusted trade rate of 1.4x-11.6x while retaining held-out generalization on ten benchmarks spanning code, instruction fo...

  17. Tokalator: A Context Engineering Toolkit for Artificial Intelligence Coding Assistants

    cs.SE 2026-04 unverdicted novelty 4.0

    Tokalator is a toolkit with VS Code extension, calculators, and community resources to monitor and optimize token usage in AI coding environments.

  18. Token-Operations-Oriented Inference Optimization Techniques for Large Models

    cs.SE 2026-06 unverdicted novelty 3.0

    The paper introduces a four-layer technical architecture for token-operations-oriented inference optimization in large models and reviews key technologies and industry status at each layer.