Generalizable Reasoning through Compositional Energy Minimization

• URL: http://arxiv.org/abs/2510.20607v1
• Date: Thu, 23 Oct 2025 14:38:36 GMT
• Title: Generalizable Reasoning through Compositional Energy Minimization
• Authors: Alexandru Oarga, Yilun Du,
• Abstract summary: Generalization is a key challenge in machine learning, specifically in reasoning tasks.<n>We propose a novel approach to reasoning generalization by learning energy landscapes over the solution spaces of smaller, more tractable subproblems.<n>Our method outperforms existing state-of-the-art methods, demonstrating its ability to generalize to larger and more complex problems.
• Score: 91.76056742068813
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generalization is a key challenge in machine learning, specifically in reasoning tasks, where models are expected to solve problems more complex than those encountered during training. Existing approaches typically train reasoning models in an end-to-end fashion, directly mapping input instances to solutions. While this allows models to learn useful heuristics from data, it often results in limited generalization beyond the training distribution. In this work, we propose a novel approach to reasoning generalization by learning energy landscapes over the solution spaces of smaller, more tractable subproblems. At test time, we construct a global energy landscape for a given problem by combining the energy functions of multiple subproblems. This compositional approach enables the incorporation of additional constraints during inference, allowing the construction of energy landscapes for problems of increasing difficulty. To improve the sample quality from this newly constructed energy landscape, we introduce Parallel Energy Minimization (PEM). We evaluate our approach on a wide set of reasoning problems. Our method outperforms existing state-of-the-art methods, demonstrating its ability to generalize to larger and more complex problems. Project website can be found at: https://alexoarga.github.io/compositional_reasoning/

Related papers

• A Knapsack by Any Other Name: Presentation impacts LLM performance on NP-hard problems [64.05451567422342]
  We introduce the dataset of Everyday Hard Optimization Problems (EHOP), a collection of NP-hard problems expressed in natural language.<n>EHOP includes problem formulations that could be found in computer science textbooks (e.g., graph coloring), versions that are dressed up as problems that could arise in real life.<n>We find that state-of-the-art LLMs, across multiple prompting strategies, solve textbook problems more accurately than their real-life and inverted counterparts.
  arXiv  Detail & Related papers  (2025-02-19T14:39:59Z)
• State Combinatorial Generalization In Decision Making With Conditional Diffusion Models [48.91240871813614]
  We show how existing value-based reinforcement learning algorithms struggle due to unreliable value predictions in unseen states.<n>We argue that this problem cannot be addressed with exploration alone, but requires more expressive and generalizable models.<n>We show that conditioned diffusion models outperform traditional RL techniques and highlight the broad applicability of our problem formulation.
  arXiv  Detail & Related papers  (2025-01-22T21:48:40Z)
• Learning Iterative Reasoning through Energy Diffusion [90.24765095498392]
  We introduce iterative reasoning through energy diffusion (IRED), a novel framework for learning to reason for a variety of tasks. IRED learns energy functions to represent the constraints between input conditions and desired outputs. We show IRED outperforms existing methods in continuous-space reasoning, discrete-space reasoning, and planning tasks.
  arXiv  Detail & Related papers  (2024-06-17T03:36:47Z)
• Efficient Imitation Learning with Conservative World Models [54.52140201148341]
  We tackle the problem of policy learning from expert demonstrations without a reward function. We re-frame imitation learning as a fine-tuning problem, rather than a pure reinforcement learning one.
  arXiv  Detail & Related papers  (2024-05-21T20:53:18Z)
• Divide-or-Conquer? Which Part Should You Distill Your LLM? [38.62667131299918]
  We devise a similar strategy that breaks down reasoning tasks into a problem decomposition phase and a problem solving phase. We show that the strategy is able to outperform a single stage solution.
  arXiv  Detail & Related papers  (2024-02-22T22:28:46Z)
• Faith and Fate: Limits of Transformers on Compositionality [109.79516190693415]
  We investigate the limits of transformer large language models across three representative compositional tasks. These tasks require breaking problems down into sub-steps and synthesizing these steps into a precise answer. Our empirical findings suggest that transformer LLMs solve compositional tasks by reducing multi-step compositional reasoning into linearized subgraph matching.
  arXiv  Detail & Related papers  (2023-05-29T23:24:14Z)
• Learning Iterative Reasoning through Energy Minimization [77.33859525900334]
  We present a new framework for iterative reasoning with neural networks. We train a neural network to parameterize an energy landscape over all outputs. We implement each step of the iterative reasoning as an energy minimization step to find a minimal energy solution.
  arXiv  Detail & Related papers  (2022-06-30T17:44:20Z)
• Learning Solution Manifolds for Control Problems via Energy Minimization [32.59818752168615]
  A variety of control tasks are commonly formulated as energy minimization problems. Numerical solutions to such problems are well-established, but are often too slow to be used directly in real-time applications. We propose an alternative to behavioral cloning (BC) that is efficient and numerically robust.
  arXiv  Detail & Related papers  (2022-03-07T14:28:57Z)
• SQALER: Scaling Question Answering by Decoupling Multi-Hop and Logical Reasoning [34.015606782134206]
  We show that multi-hop and more complex logical reasoning can be accomplished separately without losing expressive power. We propose an approach to multi-hop reasoning that scales linearly with the number of relation types in the graph. This produces a set of candidate solutions that can be provably refined to recover the solution to the original problem.
  arXiv  Detail & Related papers  (2021-10-27T08:40:16Z)

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.