mlsanityData to 7 Oct 2026

BRAID: Bounded Reasoning for Autonomous Inference and Decisions

arXiv 2512.15959 ↗First posted 17 Dec 2025cs.CL cs.AIcited by 0

On the map: LLM reasoning → Prompting and chain-of-thought reasoning

Abstract (arXiv)

Large Language Models (LLMs) exhibit nonlinear relationships between performance, cost, and token usage. This paper presents a quantitative study on structured prompting using BRAID (Bounded Reasoning for Au tonomous Inference and Decisions) across multiple GPT model tiers, eval uated on the AdvancedIF, GSM-Hard, and the SCALE MultiChallenge benchmark datasets. BRAID introduces a bounded reasoning framework using Mermaid-based instruction graphs that enable models to reason struc turally rather than through unbounded natural-language token expansion. We show that structured machine-readable prompts substantially increase reasoning accuracy and cost efficiency for agents in production systems. The findings establish BRAID as an effective and scalable technique for optimizing inference efficiency in autonomous agent systems. All datasets and detailed result logs are available at https://benchmark.openserv.ai.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning. Builds on 17 of its 18 references that are in the map. First posted on arXiv 17 Dec 2025.

Builds on

17 of 18 references.

Closest ancestors · 9

Same direction, newest first

  1. 2024Can Language Models Perform Robust Reasoning in Chain-of-thought Prompting with Noisy Rationales?31 Oct
  2. 2024To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning18 Sep
  3. 2024How to think step-by-step: A mechanistic understanding of chain-of-thought reasoning28 Feb
  4. 2023Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models6 May
  5. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks22 Nov
  6. 2022Large Language Models are Zero-Shot Reasoners24 May
  7. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Models21 May
  8. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Models21 Mar
  9. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Models28 Jan

Other references · 8

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  3. 2022PAL: Program-aided Language Modelscited by 635
  4. 2025MultiChallenge: A Realistic Multi-Turn Conversation Evaluation Benchmark Challenging to Frontier LLMscited by 171
  5. 2023Structured Chain-of-Thought Prompting for Code Generationcited by 136
  6. 2025AdvancedIF: Rubric-Based Benchmarking and Reinforcement Learning for Advancing LLM Instruction Followingcited by 46
  7. 2023Universal Self-Adaptive Promptingcited by 14
  8. 2024Toward Realistic Cinema: The State of the Art in Mechatronics for Modern Animatroniccited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Prompt Architecture Determines Reasoning Quality: A Variable Isolation Study on the Car Wash Problem
  2. 2026Tyler: Typed Latent Reasoning for Language Models -- When to Think, What to Compute, and How Much to Allocate
  3. 2023Noisy Exemplars Make Large Language Models More Robust: A Domain-Agnostic Behavioral Analysis
  4. 2026Harnessing LLMs as Agents: What Does It Cost?
  5. 2023Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models
  6. 2025Benefits and Limitations of Communication in Multi-Agent Reasoning
  7. 2025Reasoning-Aware Prompt Orchestration: A Foundation Model for Multi-Agent Language Model Coordination
  8. 2024Combinatorial Reasoning: Selecting Reasons in Generative AI Pipelines via Combinatorial Optimization