Lifting Traces to Logic: Programmatic Skill Induction with Neuro-Symbolic Learning for Long-Horizon Agentic Tasks

• URL: http://arxiv.org/abs/2605.01293v1
• Date: Sat, 02 May 2026 07:06:01 GMT
• Title: Lifting Traces to Logic: Programmatic Skill Induction with Neuro-Symbolic Learning for Long-Horizon Agentic Tasks
• Abstract summary: Neuro-Symbolic Skill Induction (NSI) is a framework that lifts interaction traces into modular, textitlogic-grounded programs.<n>NSI enables the efficient generalization, allowing agents to induce skills from few-shot examples and flexibly adapt to unseen goals.
• Score: 34.41996714138771
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Foundation model-driven agents often struggle with long-horizon planning due to the transient nature of purely prompting-based reasoning. While existing skill induction methods mitigate this by distilling experience into state-blind parameterized scripts, they fail to capture the conditional logic required for robust execution in dynamic environments. In this paper, we propose Neuro-Symbolic Skill Induction (NSI), a framework that lifts interaction traces into modular, \textit{logic-grounded} programs. By synthesizing explicit control flows and dynamic variable binding, NSI empowers agents to discover \textit{when} and \textit{why} to act. This paradigm enables the efficient generalization, allowing agents to induce skills from few-shot examples and flexibly adapt to unseen goals. Experiments on a series of agentic tasks demonstrate that NSI consistently outperforms state-of-the-art baselines, empowering agents to self-evolve into architects of logic-grounded skills.

Related papers

• From Knowing to Acting: Benchmarking Self-Awareness Capability of LLM Agents [69.07911499189129]
  We introduce KAPRO, a framework that evaluates cognitive-behavioral alignment by decoupling an agent's metacognitive judgment (Knowing) from its spontaneous execution (Acting)<n>Experiments show that self-awareness capability is strongly correlated with task success but degrades sharply in internal-capability settings.<n> proprietary and reasoning-oriented models demonstrate more reliable cognitive gating.
  arXiv  Detail & Related papers  (2026-06-09T17:17:08Z)
• Provably Secure Agent Guardrail [89.79561918065122]
  Existing defense architectures rely on empirical semantic guardrails and probabilistic large model adjudicators.<n>This paper proposes a new security paradigm for agents based on the fundamental limitations of logical reasoning.
  arXiv  Detail & Related papers  (2026-05-28T02:12:41Z)
• ATLAS: Agentic or Latent Visual Reasoning? One Word is Enough for Both [55.182037225013836]
  ATLAS is a framework in which a single discrete 'word', termed as a functional token, serves both as an agentic operation and a latent visual reasoning unit.<n> ATLAS achieves superior performance on challenging benchmarks while maintaining clear interpretability.
  arXiv  Detail & Related papers  (2026-05-14T17:59:55Z)
• Towards a Virtual Neuroscientist: Autonomous Neuroimaging Analysis via Multi-Agent Collaboration [53.772014300855375]
  We introduce NIAgent, a multi-agent system for autonomous end-to-end neuroimaging analysis.<n>Unlike conventional flat tool-calling agents, NIAgent adopts a code-centric execution paradigm.<n>We propose a hierarchical verification framework for autonomous quality control, integrating cohort-level metric screening with agentic visual inspection.
  arXiv  Detail & Related papers  (2026-05-10T06:30:19Z)
• Emergent Neural Automaton Policies: Learning Symbolic Structure from Visuomotor Trajectories [14.475289544849007]
  ENAP (Emergent Neural Automaton Policy) is a framework that allows a bi-level neuro-symbolic policy adaptively emerge from visuomotor demonstrations.<n>By explicitly modeling the task structure with discrete transitions and continuous residuals, ENAP achieves high sample efficiency and interpretability without requiring task-specific labels.
  arXiv  Detail & Related papers  (2026-03-26T20:50:36Z)
• Zero-Shot Instruction Following in RL via Structured LTL Representations [50.41415009303967]
  We study instruction following in multi-task reinforcement learning, where an agent must zero-shot execute novel tasks not seen during training.<n>In this setting, linear temporal logic has recently been adopted as a powerful framework for specifying structured, temporally extended tasks.<n>While existing approaches successfully train generalist policies, they often struggle to effectively capture the rich logical and temporal structure inherent in specifications.
  arXiv  Detail & Related papers  (2026-02-15T23:22:50Z)
• Prompt-Driven Low-Altitude Edge Intelligence: Modular Agents and Generative Reasoning [20.552503613122067]
  Large artificial intelligence models (LAMs) show strong capabilities in perception, reasoning, and multi-modal understanding.<n>The deployment of LAMs at the edge remains constrained by some fundamental limitations.<n>We propose a prompt-to-agent edge cognition framework (P2AECF) to enable the flexible, efficient, and adaptive edge intelligence.
  arXiv  Detail & Related papers  (2026-02-15T06:09:04Z)
• PhyNiKCE: A Neurosymbolic Agentic Framework for Autonomous Computational Fluid Dynamics [0.0]
  This work introduces PhyNiKCE, a neurosymbolic agentic framework for trustworthy engineering.<n>Unlike standard black-box agents, PhyNiKCE decouples neural planning from symbolic validation.<n>This architecture offers a scalable, auditable paradigm for Trustworthy Artificial Intelligence in broader industrial automation.
  arXiv  Detail & Related papers  (2026-02-12T07:37:56Z)
• AgentLongBench: A Controllable Long Benchmark For Long-Contexts Agents via Environment Rollouts [78.33143446024485]
  We introduce textbfAgentLongBench, which evaluates agents through simulated environment rollouts based on Lateral Thinking Puzzles.<n>This framework generates rigorous interaction trajectories across knowledge-intensive and knowledge-free scenarios.
  arXiv  Detail & Related papers  (2026-01-28T16:05:44Z)
• Auxiliary Metrics Help Decoding Skill Neurons in the Wild [52.148049490080496]
  We introduce a simple, lightweight, and broadly applicable method for isolating neurons that encode specific skills.<n>We correlate neuron activations with auxiliary metrics, such as external labels and the model's own confidence score.<n>We empirically validate our method on tasks spanning open-ended text generation and natural language inference.
  arXiv  Detail & Related papers  (2025-11-26T17:31:53Z)
• Fundamentals of Building Autonomous LLM Agents [64.39018305018904]
  This paper reviews the architecture and implementation methods of agents powered by large language models (LLMs)<n>The research aims to explore patterns to develop "agentic" LLMs that can automate complex tasks and bridge the performance gap with human capabilities.
  arXiv  Detail & Related papers  (2025-10-10T10:32:39Z)
• Performant LLM Agentic Framework for Conversational AI [1.6114012813668932]
  We introduce the Performant Agentic Framework (PAF), a novel system that assists Large Language Models (LLMs) in selecting appropriate nodes and executing actions in order when traversing complex graphs.<n>PAF combines LLM-based reasoning with a mathematically grounded vector scoring mechanism, achieving both higher accuracy and reduced latency.<n>Experiments demonstrate that PAF significantly outperforms baseline methods, paving the way for scalable, real-time Conversational AI systems in complex business environments.
  arXiv  Detail & Related papers  (2025-03-09T02:58:34Z)
• Skill Machines: Temporal Logic Skill Composition in Reinforcement Learning [13.049516752695613]
  We propose a framework where an agent learns a sufficient set of skill primitives to achieve all high-level goals in its environment. The agent can then flexibly compose them both logically and temporally to provably achieve temporal logic specifications in any regular language. This provides the agent with the ability to map from complex temporal logic task specifications to near-optimal behaviours zero-shot.
  arXiv  Detail & Related papers  (2022-05-25T07:05:24Z)

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.