mlsanityData to 14 Oct 2026

JevSpawn: Adaptive Agentic Inference through Compositional Action Spaces

arXiv 2610.00437 ↗First posted 30 Sep 2026cs.AIcited by 0

On the map: LLM reasoning → Reasoning for agents, planning and code

also in 1 more
Abstract (arXiv)

LLM agents generate intermediate reasoning and actions token by token, making extended interactions slow and computationally expensive. Jev-style models offer fast probabilistic predictions over finite fields, but require those fields to be specified in advance. This requirement limits autonomous task solving, where the available actions must be derived from natural language instructions and adapted through interaction. We introduce JevSpawn, a compositional policy that connects natural language task specifications to finite probabilistic exploration. Parallel action spawning is coupled with feedback driven branch selection, representation revision, and recovery from retained alternatives. Shared action structure and model prefixes reduce repeated generation and context computation without additional training. Evaluations on eight benchmark tasks against seven agent baselines and a TypeSafe Jev variant establish JevSpawn as a promising approach to structured agentic inference, with improved task performance and faster navigation.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 64 of its 81 references that are in the map. First posted on arXiv 30 Sep 2026.

Builds on

64 of 81 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025Latent Collaboration in Multi-Agent Systems25 Nov
  2. 2024AFlow: Automating Agentic Workflow Generation14 Oct
  3. 2024HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model18 Aug
  4. 2023An LLM Compiler for Parallel Function Calling7 Dec
  5. 2023Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models6 Oct

Other references · 59

  1. 2017Attention Is All You Needcited by 60,361
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  3. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  4. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  5. 2023FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioningcited by 2,598
  6. 2020Transformers are RNNs: Fast Autoregressive Transformers with Linear Attentioncited by 2,022
  7. 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,850
  8. 2020Big Bird: Transformers for Longer Sequencescited by 1,684
  9. 2020Reformer: The Efficient Transformercited by 1,668
  10. 2022Fast Inference from Transformers via Speculative Decodingcited by 1,653
  11. 2020Rethinking Attention with Performerscited by 1,601
  12. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,392
38 more
  1. 2023SGLang: Efficient Execution of Structured Language Model Programscited by 1,141
  2. 2021Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivitycited by 1,135
  3. 2023Accelerating Large Language Model Decoding with Speculative Samplingcited by 1,006
  4. 2024Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Headscited by 843
  5. 2023Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formattingcited by 817
  6. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 769
  7. 2023Discrete Diffusion Modeling by Estimating the Ratios of the Data Distributioncited by 745
  8. 2019Compressive Transformers for Long-Range Sequence Modellingcited by 726
  9. 2019Fast Transformer Decoding: One Write-Head is All You Needcited by 717
  10. 2024KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cachecited by 637
  11. 2024EAGLE: Speculative Sampling Requires Rethinking Feature Uncertaintycited by 578
  12. 2023FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPUcited by 575
  13. 2023Splitwise: Efficient generative LLM inference using phase splittingcited by 558
  14. 2023Large Language Models Are Not Robust Multiple Choice Selectorscited by 486
  15. 2017Non-Autoregressive Neural Machine Translationcited by 463
  16. 2023Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Timecited by 439
  17. 2024PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funnelingcited by 432
  18. 2021PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Modelscited by 411
  19. 2022DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scalecited by 407
  20. 2024Automated Design of Agentic Systemscited by 407
  21. 2024EAGLE-2: Faster Inference of Language Models with Dynamic Draft Treescited by 370
  22. 2023SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verificationcited by 365
  23. 2025EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Testcited by 331
  24. 2024LayerSkip: Enabling Early Exit Inference and Self-Speculative Decodingcited by 307
  25. 2024Break the Sequential Dependency of LLM Inference Using Lookahead Decodingcited by 298
  26. 2023Prompt Cache: Modular Attention Reuse for Low-Latency Inferencecited by 268
  27. 2024CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusioncited by 223
  28. 2023PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPUcited by 217
  29. 2023Grammar-Constrained Decoding for Structured NLP Tasks without Finetuningcited by 197
  30. 2023SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefillscited by 193
  31. 2022Synchromesh: Reliable code generation from pre-trained language modelscited by 156
  32. 2025Scaling Long-Horizon LLM Agent via Context-Foldingcited by 148
  33. 2024Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systemscited by 141
  34. 2019Insertion Transformer: Flexible Sequence Generation via Insertion Operationscited by 125
  35. 2024MiniCache: KV Cache Compression in Depth Dimension for Large Language Modelscited by 125
  36. 2022Prompting Is Programming: A Query Language for Large Language Modelscited by 110
  37. 2024Guiding LLMs The Right Way: Fast, Non-Invasive Constrained Generationcited by 101
  38. 2024vAttention: Dynamic Memory Management for Serving LLMs without PagedAttentioncited by 98

50 most cited of 59 All 59 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents
  2. 2026Latent Action Reparameterization for Efficient Agent Inference
  3. 2024Active Inference for Self-Organizing Multi-LLM Systems: A Bayesian Thermodynamic Approach to Adaptation
  4. 2026ChunkAct: Action Chunking for Agentic Robotics
  5. 2026SkillComposer: Learning to Evolve Agent Skills for Specification and Generalization
  6. 2026From Assumptions to Actions: Turning LLM Reasoning into Uncertainty-Aware Planning for Embodied Agents
  7. 2026AOrchestra: Automating Sub-Agent Creation for Agentic Orchestration
  8. 2026AgentAbstain: Do LLM Agents Know When Not to Act?