Jul 2026· Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2· pp. 12279-12290· 1 citation· 46 references
Computer Science
TL;DR
This work proposes SpaCellAgent, an autonomous large language model (LLM) multi-agent framework that automates end-to-end spatiotemporal analysis and narrative generation and establishes a scalable, agent-driven paradigm for computational biology.
Abstract
Spatial and Single-cell transcriptomics are transformative in deciphering cellular dynamics. As the fundamental paradigm for reconstructing cell developmental paths, trajectory inference (TI) is critical. However, existing methods require extensive manual intervention and proficiency in heterogeneous tools, posing a significant barrier to efficient TI analysis. To bridge this gap, we propose SpaCellAgent, an autonomous large language model (LLM) multi-agent framework that automates end-to-end spatiotemporal analysis and narrative generation. SpaCellAgent utilizes a multi-agent architecture for strategic workflow planning, a dynamic tool-orchestration engine for adaptive algorithm selection, and a self-evolution module that iteratively refines performance through feedback. We evaluate SpaCellAgent on six heterogeneous datasets encompassing complex temporal developmental trajectories, diverse sequencing platforms, and spatially-resolved tissue architectures. SpaCellAgent consistently demonstrates over 40% improvement in analytical efficiency while maintaining expert-aligned performance. By converting natural language specifications into optimized analytical workflows and fully automating the pipeline, SpaCellAgent democratizes advanced spatiotemporal modeling and establishes a scalable, agent-driven paradigm for computational biology. The code and materials are available at https://github.com/LittleXH-shw/SpaCellAgent.
VCAgent is proposed, a self-evolving framework that optimizes how biological knowledge from external APIs is structured and integrated into LLM reasoning, and introduces a schema-based slot filling mechanism that transforms raw API responses into compact, typed representations, replacing unstructured text concatenation.
Zhiyun Li, Rong Han, Xiao-Yong Wang et al.· Proceedings of the 32nd ACM...· 0 citations
Large language models can annotate cell types from marker gene lists, but they typically operate after preprocessing and clustering are complete, treating annotation as a terminal labeling step rather than controlling the analytical decisions that produce the evidence for cell identity. We present CellPilot, an agentic framework that guides a locally deployable small language model through the full single-cell analysis workflow, from raw count matrices to cluster-level annotation. CellPilot combines standard single-cell analysis tools with structured workflow control and observation-guided reasoning, allowing the model to plan analyses, execute tools, inspect intermediate results and revise decisions within a traceable session. On GTEx, structured workflow orchestration raised the same 8B model from 0.39 in a prompt-only setting to 0.89, closing most of the gap to GPT-4o (0.92) within the same framework; the framework gain was substantially larger for the smaller backbone across datasets (+0.35 versus +0.19). Across GTEx, Tabula Sapiens, and Mouse Cell Atlas, CellPilot achieves cluster-level annotation accuracies of 0.891, 0.750, and 0.773, outperforming representative reference-based, marker-based, and LLM-based methods. CellPilot confidence scores were associated with annotation correctness and supported post hoc filtering, while complete execution traces were retained for each analysis. These results suggest that structured workflow orchestration can be a critical determinant of performance in multi-step single-cell analysis, enabling locally deployable small language models to approach larger proprietary models while preserving transparency and practical usability.
This work presents OptiMAS, a task-agnostic agentic optimizer that leverages textual interaction trajectories and task feedback as loss signals for end-to-end MAS evolution and sustains performance improvement over extended optimization horizons.
Yuxin Cheng, Chang Liu, Hanxin Yu et al.· 0 citations
Agent-based models (ABMs) offer a compelling framework for simulating complex systems but scale poorly with conventional software execution paradigms. When modelling millions of interacting agents with complex lifecycles and spatial dynamics, conventional ABMs encounter severe computational bottlenecks, e.g., from memory fragmentation and loop-based state updates. We introduce ASCENT (agent-based simulation using computationally efficient nested tensors), a tensor-oriented approach that reformulates agent state, interactions, and transitions as tensor programs, which enables population-level vectorised computation on commodity GPU hardware. ASCENT supports heterogeneous agent attributes, stochastic state transitions, spatially explicit movement, and machine-learning–driven behaviours, while substantially reducing the traditional trade-off between expressiveness and computational scale. Applied to modelling of gene drive mosquito dynamics on Príncipe Island, ASCENT can simulate millions of individual agents with full lifecycle, genetic inheritance, and spatial dispersal fidelity, demonstrating that a single strategically placed release achieves 95% allele prevalence within approximately 73 days. The emergent Allee effect threshold at
$${\sim }$$
300 individuals further validates the model’s ecological fidelity. These results demonstrate that our tensor-oriented reformulation enables population-scale agent-based simulation without sacrificing behavioural richness.
Imran Mahmood, Sureni Wickramasooriya, Richard M. Bailey et al.· Scientific Reports· 0 citations
Large language models (LLMs) demonstrate remarkable reasoning capabilities, yet their stateless architecture fundamentally limits deployment in long-horizon research workflows requiring multi-session continuity and quantitative rigor. Here we present Ensemble QSP, a multi-agent framework featuring a three-layer hierarchical memory architecture that keeps injected context bounded and constant in project duration (mid-term project state: median 301 tokens, max 4,050, across 104 runs) by capping each state category and evicting completed work, enabling continuous autonomous operation without context degradation. The system orchestrates five specialist worker agents under domain-expert principal investigators, enforcing physical constraints through physics-based checklists and structured-domain knowledge. Comprehensive benchmarking demonstrates robust autonomous pharmacokinetic-pharmacodynamic model selection without human intervention, consistent result quality across both lower-cost and frontier LLMs, improved PK parameter recovery relative to single-agent baselines, and stable model selection across linguistically diverse prompts of the same task. Feature-level ablation across physiologically based pharmacokinetic (PBPK) models spanning a broad complexity range shows that PI-agent oversight improves debugging efficiency while preserving final accuracy across conditions. The architecture is structurally domain-agnostic, adding a new scientific domain requires only a new PI agent configuration.
This work introduces AgentSearch, a cost-aware Monte Carlo Tree Search (MCTS) framework that constructs agentic workflows through deliberative lookahead search and attains single-episode success while reducing computational costs by up to 47%, thereby eliminating the trial-and-error exploration required by previous adaptive methods.
D. Attota, Ying Xie· Proceedings of the 15th Inte...· 0 citations