PIE-APT: A Unified Framework for Temporal Planning and Contradiction Hunting via Incremental Direct-Derivation Abduction

• URL: http://arxiv.org/abs/2607.27287v1
• Date: Wed, 29 Jul 2026 14:44:46 GMT
• Title: PIE-APT: A Unified Framework for Temporal Planning and Contradiction Hunting via Incremental Direct-Derivation Abduction
• Abstract summary: This paper introduces a unified framework with two integrated modules---textbfPIE-Abducer (incremental direct-derivation abduction) and textbfPIE-APT (Abductive Planning for Temporal KGs)<n>Treating the incremental reasoner as a black-box and representing actions in OWL without external operators preserves logical decidability.<n>Results demonstrate qualitative superiority over classical planners and prove our direct-derivation approach quantitatively outperforms an MHS-faithful baseline during abductive enrichment.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reasoning and planning over Dynamic Knowledge Graphs (DKGs) present significant challenges, especially in open-world environments with incomplete information. Existing action formalisms often face decidability issues and the Ramification Problem, while managing incomplete knowledge via structural abduction requires expansive combinatorial search. This paper introduces a unified framework with two integrated modules---\textbf{PIE-Abducer} (incremental direct-derivation abduction) and \textbf{PIE-APT} (Abductive Planning for Temporal KGs)---operating natively on the highly expressive Description Logic. We model state transitions along a linear timeline as non-monotonic updates to deductively closed DL theories. Treating the incremental reasoner as a black-box and representing actions natively in OWL without external modal operators preserves logical decidability. To address incomplete knowledge, \textbf{PIE-Abducer} circumvents traditional Minimal Hitting Set (MHS) enumeration. Instead of combinatorial syntactic search, it injects the logical negation of a target goal into a consistent branch and extracts missing premises via direct refutation consequences. \textbf{PIE-APT} then employs a recursive \textit{Generate-and-Test} architecture, interleaving backward-chaining A* search with \textbf{PIE-Abducer} up to a bounded causal depth, followed by strict validation via forward-chaining Temporal Projection. We evaluate four OWL benchmarks stressing semantic abilities absent in classical planning: parameterized goals with witness search, mid-search DL entailment, open-world assumption injection, and adversarial contradiction hunting. Results demonstrate qualitative superiority over classical planners and prove our direct-derivation approach quantitatively outperforms an MHS-faithful baseline during abductive enrichment.

Related papers

• R-APS: Compositional Reasoning and In-Context Meta-Learning for Constrained Design via Reflective Adversarial Pareto Search [18.8323743697237]
  Large language models (LLMs) are fluent on open-ended tasks, yet in agentic settings, fluency does not ensure reliable delivery.<n>We trace this gap to three coupled structural failures: errors propagate without localization, worst-case perturbations go unevaluated, and accumulated knowledge is never invalidated.<n>We argue these share a root cause: abductive, counterfactual, meta-inductive, corrective, and inductive reasoning pull a shared context in incompatible directions.
  arXiv  Detail & Related papers  (2026-06-03T12:45:39Z)
• From Prompts to Pavement Through Time: Temporal Grounding in Agentic Scene-to-Plan Reasoning [1.2777067998526854]
  This work explores whether temporal conditioning within inter-agent communication can preserve or enhance coherence without introducing degradation in semantic or logical consistency.<n>Results show that while temporal conditioning reshapes reasoning style, it yields no statistically significant improvements in standard NLP-based correctness metrics.<n>These findings clarify the limits of prompt-based temporal grounding and establish the first empirical benchmark for temporal scene-to-plan reasoning.
  arXiv  Detail & Related papers  (2026-05-19T13:18:35Z)
• Deep Reasoning in General Purpose Agents via Structured Meta-Cognition [58.185853639335896]
  We introduce an inference-time approach for constructing task-specific scaffolds through structured meta-reasoning.<n>We instantiate this approach in a general-purpose agent that distributes complex tasks across more controlled reasoning threads.
  arXiv  Detail & Related papers  (2026-05-12T01:21:37Z)
• Perception Without Engagement: Dissecting the Causal Discovery Deficit in LMMs [68.58207076756237]
  We introduce ProCauEval, a perturbation-based evaluation protocol that shifts from outcome assessment to mechanism diagnosis.<n>We find that models faithfully perceive video content yet systematically underexploit it during causal reasoning.<n>We propose Anti-Distillation Policy Optimization (ADPO), a reinforcement learning framework built on negative teacher alignment.
  arXiv  Detail & Related papers  (2026-05-10T08:48:58Z)
• Shorthand for Thought: Compressing LLM Reasoning via Entropy-Guided Supertokens [4.0704009036918025]
  Reasoning in Large Language Models incurs significant inference-time compute.<n>We show that reasoning tokens split into two functional types: low-entropy textitstructural tokens (recurring phrases that scaffold the reasoning process) and higher-entropy textitorganic tokens (problem-specific content that drives toward a solution)<n>We derive textitsupertokens that capture frequent structural patterns, then teach the model to adopt them via supervised fine-tuning.
  arXiv  Detail & Related papers  (2026-04-29T07:06:43Z)
• On Multi-Step Theorem Prediction via Non-Parametric Structural Priors [50.16583672681106]
  In this work, we explore training-free theorem prediction through the lens of in-context learning (ICL)<n>We propose Theorem Precedence Graphs, which encode temporal dependencies from historical solution traces as directed graphs, and impose explicit topological constraints that effectively prune the search space during inference.<n>Experiments on the FormalGeo7k benchmark show that our method achieves 89.29% accuracy, substantially outperforming ICL baselines and matching state-of-the-art supervised models.
  arXiv  Detail & Related papers  (2026-03-05T06:08:50Z)
• LaSER: Internalizing Explicit Reasoning into Latent Space for Dense Retrieval [74.72139580745511]
  LaSER is a novel self-distillation framework that internalizes explicit reasoning into the latent space of retrievers.<n>Our method successfully combines the reasoning depth of explicit CoT pipelines with the inference efficiency of standard dense retrievers.
  arXiv  Detail & Related papers  (2026-03-02T04:11:18Z)
• Reason-IAD: Knowledge-Guided Dynamic Latent Reasoning for Explainable Industrial Anomaly Detection [85.29900916231655]
  Reason-IAD is a knowledge-guided dynamic latent reasoning framework for explainable industrial anomaly detection.<n>Experiments demonstrate that Reason-IAD consistently outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-02-10T14:54:17Z)
• CoG: Controllable Graph Reasoning via Relational Blueprints and Failure-Aware Refinement over Knowledge Graphs [53.199517625701475]
  CoG is a training-free framework inspired by Dual-Process Theory that mimics the interplay between intuition and deliberation.<n>CoG significantly outperforms state-of-the-art approaches in both accuracy and efficiency.
  arXiv  Detail & Related papers  (2026-01-16T07:27:40Z)
• LAG: Logic-Augmented Generation from a Cartesian Perspective [7.2022636966543745]
  This paper introduces Logic-Augmented Generation (LAG), a novel paradigm that reframes knowledge augmentation through systematic question decomposition and dependency-aware reasoning.<n>Experiments on four benchmark datasets demonstrate that LAG significantly enhances reasoning robustness, reduces hallucination, and aligns LLM problem-solving with human cognition.
  arXiv  Detail & Related papers  (2025-08-07T15:42:00Z)
• Test-time Prompt Intervention [22.35022545068874]
  We propose PI, a novel framework for Test-time Prompt Intervention.<n> PI provides an interface to dynamically guide and regulate reasoning paths during inference.<n>This allows human problem-solving expertise and cognitive science principles to be seamlessly integrated into LLMs' reasoning processes.
  arXiv  Detail & Related papers  (2025-08-04T15:17:13Z)

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.