Are LLMs Better Formalizers than Solvers on Complex Problems?

• URL: http://arxiv.org/abs/2505.13252v2
• Date: Fri, 19 Sep 2025 15:19:24 GMT
• Title: Are LLMs Better Formalizers than Solvers on Complex Problems?
• Authors: Rikhil Amonkar, May Lai, Ronan Le Bras, Li Zhang,
• Abstract summary: A trending line of recent work advocates for using large language models (LLMs) as formalizers instead of as end-to-end solvers.<n>We show that this superiority does not hold on real-life constraint satisfaction problems.
• Score: 9.711592497202401
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: A trending line of recent work advocates for using large language models (LLMs) as formalizers instead of as end-to-end solvers for logical reasoning problems. Instead of generating the solution, the LLM generates a formal program that derives a solution via an external solver. While performance gain of the seemingly scalable LLM-as-formalizer over the seemingly unscalable LLM-as-solver has been widely reported, we show that this superiority does not hold on real-life constraint satisfaction problems. On 4 domains, we systematically evaluate 6 LLMs including 4 large reasoning models with inference-time scaling, paired with 5 pipelines including 2 types of formalism. We show that in few-shot settings, LLM-as-formalizer underperforms LLM-as-solver. While LLM-as-formalizer promises accuracy, robustness, faithfulness, and efficiency, we observe that the present LLMs do not yet deliver any of those, as their limited ability to generate formal programs leads to failure to scale with complexity, hard-coded solutions, and excessive reasoning tokens. We present our detailed analysis and actionable remedies to drive future research that improves LLM-as-formalizer.

Related papers

• Multi-Agent Evolve: LLM Self-Improve through Co-evolution [53.00458074754831]
  Reinforcement Learning (RL) has demonstrated significant potential in enhancing the reasoning capabilities of large language models (LLMs)<n>Recent Self-Play RL methods, inspired by the success of the paradigm in games and Go, aim to enhance LLM reasoning capabilities without human-annotated data.<n>We propose Multi-Agent Evolve (MAE), a framework that enables LLMs to self-evolve in solving diverse tasks, including mathematics, reasoning, and general knowledge Q&A.
  arXiv  Detail & Related papers  (2025-10-27T17:58:02Z)
• Seemingly Simple Planning Problems are Computationally Challenging: The Countdown Game [26.665033202052257]
  We propose a procedure for creating a planning benchmark centered around the game called Countdown.<n>We discuss how this problem meets many of the desiderata associated with an ideal benchmark for planning capabilities evaluation.<n>Our results show that, unlike other domains like 24 Game (a special case of Countdown), our proposed dynamic benchmark remains extremely challenging for existing LLM-based approaches.
  arXiv  Detail & Related papers  (2025-08-04T21:01:03Z)
• LLM4VV: Evaluating Cutting-Edge LLMs for Generation and Evaluation of Directive-Based Parallel Programming Model Compiler Tests [7.6818904666624395]
  This paper proposes a dual-LLM system and experiments with the usage of LLMs for the generation of compiler tests.<n>It is evident that LLMs possess the promising potential to generate quality compiler tests and verify them automatically.
  arXiv  Detail & Related papers  (2025-07-29T02:34:28Z)
• Reasoning-Aligned Perception Decoupling for Scalable Multi-modal Reasoning [95.44766931218896]
  Multi-modal large language models (MLLMs) still lag behind text-based reasoning.<n>We introduce Perception-Reasoning Decoupling, which modularizes the MLLM's reasoning component and makes it easily replaceable.<n>We propose a novel reinforcement learning algorithm called Visual Perception Optimization (VPO) to align the MLLM's perceptual output with the final reasoning task.
  arXiv  Detail & Related papers  (2025-06-05T02:28:07Z)
• Self-Steering Language Models [113.96916935955842]
  DisCIPL is a method for "self-steering" language models.<n>DisCIPL uses a Planner model to generate a task-specific inference program.<n>Our work opens up a design space of highly-parallelized Monte Carlo inference strategies.
  arXiv  Detail & Related papers  (2025-04-09T17:54:22Z)
• Classical Planning with LLM-Generated Heuristics: Challenging the State of the Art with Python Code [8.971234046933349]
  Large language models (LLMs) fail to plan reliably, even when prompted with a detailed definition of a planning task.<n>We show how to use LLMs to generate correct plans, even for out-of-distribution tasks of increasing size.
  arXiv  Detail & Related papers  (2025-03-24T15:50:20Z)
• Plan-over-Graph: Towards Parallelable LLM Agent Schedule [53.834646147919436]
  Large Language Models (LLMs) have demonstrated exceptional abilities in reasoning for task planning.<n>This paper introduces a novel paradigm, plan-over-graph, in which the model first decomposes a real-life textual task into executable subtasks and constructs an abstract task graph.<n>The model then understands this task graph as input and generates a plan for parallel execution.
  arXiv  Detail & Related papers  (2025-02-20T13:47:51Z)
• Code Simulation as a Proxy for High-order Tasks in Large Language Models [6.71786454125056]
  We collect pairs of naturalistic and synthetic reasoning tasks to assess the capabilities of Large Language Models (LLM)<n>We leverage common constructs in programming as the counterpart of the building blocks of naturalistic reasoning tasks.<n>Our contribution builds upon synthetically testing the reasoning capabilities of LLMs as a scalable complement to handcrafted human-annotated problems.
  arXiv  Detail & Related papers  (2025-02-05T19:30:28Z)
• Systematic Analysis of LLM Contributions to Planning: Solver, Verifier, Heuristic [6.687149103409949]
  We provide a systematic analysis of how large language models (LLMs) contribute to solving planning problems.<n>Our analysis reveals that although it is difficult for LLMs to generate correct plans out-of-the-box, LLMs are much better at providing feedback signals to intermediate/incomplete solutions.
  arXiv  Detail & Related papers  (2024-12-12T18:16:46Z)
• Interactive and Expressive Code-Augmented Planning with Large Language Models [62.799579304821826]
  Large Language Models (LLMs) demonstrate strong abilities in common-sense reasoning and interactive decision-making. Recent techniques have sought to structure LLM outputs using control flow and other code-adjacent techniques to improve planning performance. We propose REPL-Plan, an LLM planning approach that is fully code-expressive and dynamic.
  arXiv  Detail & Related papers  (2024-11-21T04:23:17Z)
• Unlocking Reasoning Potential in Large Langauge Models by Scaling Code-form Planning [94.76546523689113]
  We introduce CodePlan, a framework that generates and follows textcode-form plans -- pseudocode that outlines high-level, structured reasoning processes. CodePlan effectively captures the rich semantics and control flows inherent to sophisticated reasoning tasks. It achieves a 25.1% relative improvement compared with directly generating responses.
  arXiv  Detail & Related papers  (2024-09-19T04:13:58Z)
• Q*: Improving Multi-step Reasoning for LLMs with Deliberative Planning [53.6472920229013]
  Large Language Models (LLMs) have demonstrated impressive capability in many natural language tasks. LLMs are prone to produce errors, hallucinations and inconsistent statements when performing multi-step reasoning. We introduce Q*, a framework for guiding LLMs decoding process with deliberative planning.
  arXiv  Detail & Related papers  (2024-06-20T13:08:09Z)
• Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration [68.29746557968107]
  We propose a novel framework for multi-agent collaboration that introduces Reinforced Advantage feedback (ReAd) for efficient self-refinement of plans.<n> Experiments on Over-AI and a difficult variant of RoCoBench show that ReAd surpasses baselines in success rate, and also significantly decreases the interaction steps of agents.
  arXiv  Detail & Related papers  (2024-05-23T08:33:19Z)
• Learning Logic Specifications for Policy Guidance in POMDPs: an Inductive Logic Programming Approach [57.788675205519986]
  We learn high-quality traces from POMDP executions generated by any solver. We exploit data- and time-efficient Indu Logic Programming (ILP) to generate interpretable belief-based policy specifications. We show that learneds expressed in Answer Set Programming (ASP) yield performance superior to neural networks and similar to optimal handcrafted task-specifics within lower computational time.
  arXiv  Detail & Related papers  (2024-02-29T15:36:01Z)
• Small Models, Big Insights: Leveraging Slim Proxy Models To Decide When and What to Retrieve for LLMs [60.40396361115776]
  This paper introduces a novel collaborative approach, namely SlimPLM, that detects missing knowledge in large language models (LLMs) with a slim proxy model. We employ a proxy model which has far fewer parameters, and take its answers as answers. Heuristic answers are then utilized to predict the knowledge required to answer the user question, as well as the known and unknown knowledge within the LLM.
  arXiv  Detail & Related papers  (2024-02-19T11:11:08Z)
• LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworks [18.068035947969044]
  There is considerable confusion about the role of Large Language Models (LLMs) in planning and reasoning tasks. We argue that auto-regressive LLMs cannot, by themselves, do planning or self-verification. We present a vision of bf LLM-Modulo Frameworks that combine the strengths of LLMs with external model-based verifiers.
  arXiv  Detail & Related papers  (2024-02-02T14:43:18Z)
• LLM-Assist: Enhancing Closed-Loop Planning with Language-Based Reasoning [65.86754998249224]
  We develop a novel hybrid planner that leverages a conventional rule-based planner in conjunction with an LLM-based planner. Our approach navigates complex scenarios which existing planners struggle with, produces well-reasoned outputs while also remaining grounded through working alongside the rule-based approach.
  arXiv  Detail & Related papers  (2023-12-30T02:53:45Z)
• LaGR-SEQ: Language-Guided Reinforcement Learning with Sample-Efficient Querying [71.86163159193327]
  Large language models (LLMs) have recently demonstrated their impressive ability to provide context-aware responses via text. This ability could potentially be used to predict plausible solutions in sequential decision making tasks pertaining to pattern completion. We introduce LaGR, which uses this predictive ability of LLMs to propose solutions to tasks that have been partially completed by a primary reinforcement learning (RL) agent.
  arXiv  Detail & Related papers  (2023-08-21T02:07:35Z)
• Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples! [43.51393135075126]
  Large Language Models (LLMs) have made remarkable strides in various tasks. We show that current advanced LLMs consistently exhibit inferior performance, higher latency, and increased budget requirements compared to fine-tuned SLMs. We propose an adaptive filter-then-rerank paradigm to combine the strengths of LLMs and SLMs.
  arXiv  Detail & Related papers  (2023-03-15T12:20:13Z)
• Self-planning Code Generation with Large Language Models [31.992593966465545]
  This paper proposes a self-planning code generation approach with large language models. In the planning phase, the model plans out concise solution steps from the intent combined with few-shot prompting. In the implementation phase, the model generates code step by step, guided by the preceding solution steps.
  arXiv  Detail & Related papers  (2023-03-12T15:36:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.