SEER: Supervised Learning to Control Energetic Reasoning

• URL: http://arxiv.org/abs/2607.16523v1
• Date: Fri, 17 Jul 2026 21:52:59 GMT
• Title: SEER: Supervised Learning to Control Energetic Reasoning
• Abstract summary: We propose an oracle function, obtained via ML, to decide whether to run complex propagators for a target constraint.<n>A combination of design choices makes the approach flexible and easy to embed in state-of-the-art solvers.<n>Our experiments show that high prediction accuracy can be obtained, provide suggestions for classification features, and highlight important issues to address.
• Score: 8.681933369093125
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: One of the main strengths of Constraint Programming is the ability to reduce the search space via propagation. However, propagation is a double-edged sword, with more pruning power coming at the price of larger computation time. For each problem constraint, the best propagator depends on the specific instance and may change at search time. In the literature, Machine Learning (ML) techniques and activity-based heuristics have been applied respectively for choosing (statically) the propagators for a batch of problems and to adapt (dynamically) the propagation strength. We propose to merge those efforts by using an oracle function, obtained via ML, to decide whether to run complex propagators for a target constraint. A combination of design choices makes the approach flexible and easy to embed in state-of-the-art solvers. In this paper, we focus on investigating the feasibility of building an oracle for the Energetic Reasoning propagator. Our experiments show that high prediction accuracy can be obtained, provide suggestions for classification features, and highlight important issues to address when building such an oracle.

Related papers

• Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence [70.8951332710039]
  Multimodal large language models (MLLMs) have demonstrated significant potential in complex spatial scene understanding and reasoning tasks.<n>However, their open-ended reasoning process is prone to decision errors and error accumulation, leading to instability in answer quality.<n>We propose an advantage-guided gating framework that dynamically intervenes in and corrects deviations during the reasoning process.
  arXiv  Detail & Related papers  (2026-08-08T07:46:04Z)
• Domain-Specialized Tree of Thought through Plug-and-Play Predictors [32.191360225502386]
  We introduce DST, an adaptable, plug-and-play predictor that serves as a lightweight, supervised to guide the ToT search process.<n>Our predictor enables dynamic, context-aware pruning, allowing the search to proceed with near-greedy efficiency on simpler reasoning steps.<n>Our work effectively resolves the accuracy-efficiency trade-off in tree-based reasoning, transforming ToT into a scalable and practical paradigm for complex problem-solving in LLMs.
  arXiv  Detail & Related papers  (2026-03-14T10:22:01Z)
• Beyond Fast and Slow: Cognitive-Inspired Elastic Reasoning for Large Language Models [39.03483371038282]
  CogER is a framework inspired by human hierarchical reasoning.<n>For queries requiring external tools, we introduce Cognitive Tool-Assisted Reasoning.<n>CogER outperforms state-of-the-art Test-Time scaling methods.
  arXiv  Detail & Related papers  (2025-12-17T05:11:58Z)
• Efficient Heuristics Generation for Solving Combinatorial Optimization Problems Using Large Language Models [52.538586230181814]
  Recent studies exploited Large Language Models (LLMs) to autonomously generates for solving Combinatorial Optimization Problems (COPs)<n>The absence of task-specific knowledge in prompts often leads LLMs to provide unspecific search directions, obstructing derivation of well-performings.<n>We propose the Hercules algorithm, which leverages our designed Core Abstraction Prompting (CAP) method to abstract the core components from elite HGs and incorporate them as prior knowledge in prompts.
  arXiv  Detail & Related papers  (2025-05-19T02:20:46Z)
• Directed Exploration in Reinforcement Learning from Linear Temporal Logic [59.707408697394534]
  Linear temporal logic (LTL) is a powerful language for task specification in reinforcement learning.<n>We show that the synthesized reward signal remains fundamentally sparse, making exploration challenging.<n>We show how better exploration can be achieved by further leveraging the specification and casting its corresponding Limit Deterministic B"uchi Automaton (LDBA) as a Markov reward process.
  arXiv  Detail & Related papers  (2024-08-18T14:25:44Z)
• 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)
• Structured Reinforcement Learning for Incentivized Stochastic Covert Optimization [13.440621354486906]
  A gradient algorithm (SG) can be controlled to hide the estimate of the local stationary point from an eavesdropper. This paper studies how a gradient algorithm (SG) can be controlled to hide the estimate of the local stationary point from an eavesdropper.
  arXiv  Detail & Related papers  (2024-05-13T01:29:48Z)
• Enhancing Q-Learning with Large Language Model Heuristics [0.0]
  Large language models (LLMs) can achieve zero-shot learning for simpler tasks, but they suffer from low inference speeds and occasional hallucinations. We propose textbfLLM-guided Q-learning, a framework that leverages LLMs as hallucinations to aid in learning the Q-function for reinforcement learning.
  arXiv  Detail & Related papers  (2024-05-06T10:42:28Z)
• Disentangled Latent Spaces Facilitate Data-Driven Auxiliary Learning [9.571499333904969]
  Auxiliary tasks facilitate learning in situations where data is scarce or the principal task of interest is extremely complex.<n>We propose a novel framework, dubbed Detaux, whereby a weakly supervised disentanglement procedure is used to discover a new unrelated auxiliary classification task.<n>The disentanglement procedure works at the representation level, isolating the variation related to the principal task into an isolated subspace.
  arXiv  Detail & Related papers  (2023-10-13T17:40:39Z)
• Oracle-Efficient Smoothed Online Learning for Piecewise Continuous Decision Making [73.48977854003697]
  This work introduces a new notion of complexity, the generalized bracketing numbers, which marries constraints on the adversary to the size of the space. We then instantiate our bounds in several problems of interest, including online prediction and planning of piecewise continuous functions.
  arXiv  Detail & Related papers  (2023-02-10T18:45:52Z)
• A Trainable Optimal Transport Embedding for Feature Aggregation and its Relationship to Attention [96.77554122595578]
  We introduce a parametrized representation of fixed size, which embeds and then aggregates elements from a given input set according to the optimal transport plan between the set and a trainable reference. Our approach scales to large datasets and allows end-to-end training of the reference, while also providing a simple unsupervised learning mechanism with small computational cost.
  arXiv  Detail & Related papers  (2020-06-22T08:35:58Z)

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.