4arXiv cs.AI (Artificial Intelligence)·
Semantic persistence model for LLM workflows as inspectable knowledge objects
A new arXiv preprint proposes a conceptual model for treating LLM workflow components — definitions, instances, inference records, context snapshots — as persistent, inspectable knowledge objects in a shared substrate. The framework draws on Lisp-inspired ideas (symbolic forms, object identity, live-image thinking) as explanatory lenses rather than implementation commitments. A central distinction is drawn between 'derive' (deterministic computation) and 'infer' (LLM-mediated judgment under declared context), with formal transition semantics left as future work. The work addresses a gap in how agentic workflow systems represent and reason about their own execution state.
Related guides (1)
Related events (8)
Theoretical framework proposes native meta-architecture to replace application-layer LLM cognitive simulation
A preprint from arXiv proposes a theoretical framework for embedding cognitive architecture natively into LLMs rather than simulating it via prompt engineering and context management. The framework introduces three mechanisms: Structural Tension (an endogenous loss function from information-manifold conflict), an Offline Recurrent Loop (sandboxed self-processing without external input), and Inference-time Plasticity (topology reconfiguration without weight modification). The authors argue these mechanisms could produce heterogeneous model instances with distinct topological structures through path-dependent evolution, while remaining within governance rails. The paper is primarily theoretical, offering operational definitions, reconfiguration operators, and falsification criteria rather than empirical results.
Agentic LLM collectives proposed as interpretable substrates for Artificial Life research
A preprint from arXiv argues that populations of agentic LLMs — equipped with persistent memory, tools, and autonomous action — can serve as a computational substrate for Artificial Life (ALife) research. The key claim is that because agents communicate in natural language, their collective emergent behaviors are directly interpretable by examining textual traces or querying the agents themselves. The paper extends existing notions of LLM interpretability to multi-agent collectives and surveys recent examples of agentic LLM systems in both controlled and deployed settings. This positions multi-agent LLM systems as a novel lens for studying emergence and complexity while retaining interpretability.
WorkflowView: LLM-based framework abstracts user action logs into interpretable workflows
Researchers introduce WorkflowView, a framework using LLMs to convert low-level interaction logs into high-level activity descriptions across diverse domains. The system achieves strong results on three tasks: zero-shot browser log reconstruction (semantic similarity 0.91), few-shot MOOC dropout prediction (F1=0.90 with five examples), and privacy-preserving analysis of AI tool usage in Microsoft Word. The work addresses limitations of prior deep learning clustering approaches, which struggled with noise and cross-application generalization, and discusses deployment considerations including computational efficiency and privacy.
Disentangling solvability knowledge from verbalization in LLM hidden states
A new arXiv preprint probes LLM internal representations to separately decode 'solvability knowledge' and 'verbalization' as distinct linear directions in hidden states. The authors find that fabrication (hallucination of solutions to unsolvable problems) is primarily driven by shifts in verbalization representations rather than underlying knowledge. Prompting with unsolvability cues and activation steering can mechanistically shift verbalization to improve model abstention. The work advances mechanistic understanding of why LLMs confabulate on unsolvable math problems.
Theoretical framework for grounding LLM reasoning under incomplete knowledge graph evidence
A new arXiv preprint develops a formal theoretical framework for understanding how LLMs reason when guided by incomplete knowledge graphs. The authors introduce constructs including entity anchors, typed relation residuals, path energies, and support regions, and prove that under open-world incompleteness no hard rule can simultaneously reject all false unsupported trajectories while retaining all true-but-unobserved ones. Soft grounding is characterized as a KL-regularized deformation of the LLM prior, with hard conditioning as an infinite-penalty limit. The framework yields stability bounds under evidence perturbations and has implications for GraphRAG, KGQA, graph agents, constrained decoding, and faithful generation.
Paper argues LLMs learn causal structure via difference-making logic, not Pearl/Rubin frameworks
A new arXiv preprint proposes that LLMs learn causal structure through 'variational induction' — a difference-making logic — rather than through the dominant formalisms of Judea Pearl's interventionist approach or the Neyman-Rubin potential outcomes framework. The author analyzes how this logic is realized during training and maps specific architectural features (token embeddings, self-attention) to their roles in this inductive process. The argument draws a parallel between LLM causal learning and the experimental method of systematically varying circumstances. This is a theoretical contribution to understanding how LLMs represent causal and world-model structure.
Paper argues LLMs are a degenerate special case of world models, maps continuous spectrum from NTP to JEPA
A new arXiv preprint reframes the LLM-vs-world-model debate by arguing that LLMs are a degenerate special case of world models rather than a fundamentally different paradigm, with the state space being token sequences and the only action being token appending. The paper maps a continuous spectrum from next-token prediction through multi-token prediction, future-summary prediction, and next-latent prediction up to JEPA-style architectures. It identifies two open research challenges in moving along this spectrum: the data cliff from self-supervised text to action-labeled environments, and whether transformers generalize to continuous-state prediction or require a new architectural primitive. The work directly engages with Yann LeCun's 2022 argument that general intelligence requires abandoning autoregressive prediction.
LLM Wiki: desktop app that builds persistent knowledge bases from documents using LLMs
LLM Wiki is an open-source cross-platform desktop application that uses LLMs to incrementally build and maintain a persistent, interlinked wiki from user documents rather than performing retrieval-augmented generation on each query. The project has accumulated 12,217 GitHub stars with 111 added today, suggesting notable community traction. It represents an alternative architectural pattern to standard RAG pipelines.