SemanticALLI: Caching Reasoning, Not Just Responses, in Agentic Systems

• URL: http://arxiv.org/abs/2601.16286v1
• Date: Thu, 22 Jan 2026 19:42:21 GMT
• Title: SemanticALLI: Caching Reasoning, Not Just Responses, in Agentic Systems
• Authors: Varun Chillara, Dylan Kline, Christopher Alvares, Evan Wooten, Huan Yang, Shlok Khetan, Cade Bauer, Tré Guillory, Tanishka Shah, Yashodhara Dhariwal, Volodymyr Pavlov, George Popstefanov,
• Abstract summary: We introduce SemanticALLI, a pipeline-aware architecture within PMG's marketing intelligence platform.<n>By decomposing generation into Analytic Intent Resolution (AIR) and Visualization Synthesis (VS), SemanticALLI structured intermediate representations (IRs) to first-class, cacheable artifacts.<n>Our structured approach allows for an additional stage, the Visualization Synthesis stage, to achieve an 83.10% hit rate, bypassing 4,023 LLM calls with a median latency of just 2.66 ms.
• Score: 4.029672905329379
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Agentic AI pipelines suffer from a hidden inefficiency: they frequently reconstruct identical intermediate logic, such as metric normalization or chart scaffolding, even when the user's natural language phrasing is entirely novel. Conventional boundary caching fails to capture this inefficiency because it treats inference as a monolithic black box. We introduce SemanticALLI, a pipeline-aware architecture within Alli (PMG's marketing intelligence platform), designed to operationalize redundant reasoning. By decomposing generation into Analytic Intent Resolution (AIR) and Visualization Synthesis (VS), SemanticALLI elevates structured intermediate representations (IRs) to first-class, cacheable artifacts. The impact of caching within the agentic loop is substantial. In our evaluation, baseline monolithic caching caps at a 38.7% hit rate due to linguistic variance. In contrast, our structured approach allows for an additional stage, the Visualization Synthesis stage, to achieve an 83.10% hit rate, bypassing 4,023 LLM calls with a median latency of just 2.66 ms. This internal reuse reduces total token consumption, offering a practical lesson for AI system design: even when users rarely repeat themselves, the pipeline often does, at stable, structured checkpoints where caching is most reliable.

Related papers

• Beyond Scattered Acceptance: Fast and Coherent Inference for DLMs via Longest Stable Prefixes [10.877713536966601]
  Longestahead Prefix (LSP) scheduler is a training-free and model-agnostic inference paradigm based on monolithic prefix absorption.<n>LSP evaluates token stability via a single forward pass, dynamically identifies a contiguous left-aligned block of stable predictions.<n>It snaps its boundary to natural linguistic or structural acceptances before an atomic commitment.
  arXiv  Detail & Related papers  (2026-03-05T18:25:26Z)
• Arbor: A Framework for Reliable Navigation of Critical Conversation Flows [0.19573380763700712]
  We present Arbor, a framework that decomposes decision tree navigation into specialized, node-level tasks.<n>Abort improves mean turn accuracy by 29.4 percentage points, reduces per-turn latency by 57.1%, and an average 14.4x reduction in per-turn cost.
  arXiv  Detail & Related papers  (2026-02-16T11:09:02Z)
• Prism: Efficient Test-Time Scaling via Hierarchical Search and Self-Verification for Discrete Diffusion Language Models [96.0074341403456]
  Inference-time compute has re-emerged as a practical way to improve LLM reasoning.<n>Most test-time scaling (TTS) algorithms rely on autoregressive decoding.<n>We propose Prism, an efficient TTS framework for dLLMs.
  arXiv  Detail & Related papers  (2026-02-02T09:14:51Z)
• SimpleMem: Efficient Lifelong Memory for LLM Agents [73.74399447715052]
  We introduce SimpleMem, an efficient memory framework based on semantic lossless compression.<n>We propose a three-stage pipeline designed to maximize information density and token utilization.<n> Experiments on benchmark datasets show that our method consistently outperforms baseline approaches in accuracy, retrieval efficiency, and inference cost.
  arXiv  Detail & Related papers  (2026-01-05T21:02:49Z)
• ExplicitLM: Decoupling Knowledge from Parameters via Explicit Memory Banks [4.099810580680816]
  Large language models suffer from knowledge staleness and lack of interpretability due to implicit knowledge storage.<n>We propose ExplicitLM, a novel architecture featuring a million-scale external memory bank storing human-readable knowledge as token sequences.
  arXiv  Detail & Related papers  (2025-11-03T13:53:19Z)
• Latent Chain-of-Thought? Decoding the Depth-Recurrent Transformer [0.8738725605667471]
  Chain-of-thought (CoT) reasoning has enabled transformer-based language models to excel at complex mathematics and multi-step planning.<n>In standard decoder-only architectures, these reasoning steps are externalized in natural language, improving interpretability at the cost of efficiency.<n>We investigate whether such reasoning structures emerge in Huginn-3.5B, a depth-recurrent Transformer that reuses layers at inference time without increasing parameter count.
  arXiv  Detail & Related papers  (2025-07-02T23:35:21Z)
• vCache: Verified Semantic Prompt Caching [95.16654660556975]
  This paper proposes vCache, the first verified semantic cache with user-defined error rate guarantees.<n>It employs an online learning algorithm to estimate an optimal threshold for each cached prompt, enabling reliable cache responses without additional training.<n>Our experiments show that vCache consistently meets the specified error bounds while outperforming state-of-the-art static-threshold and fine-tuned embedding baselines.
  arXiv  Detail & Related papers  (2025-02-06T04:16:20Z)
• ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts [71.91042186338163]
  ALoRE is a novel PETL method that reuses the hypercomplex parameterized space constructed by Kronecker product to Aggregate Low Rank Experts.<n>Thanks to the artful design, ALoRE maintains negligible extra parameters and can be effortlessly merged into the frozen backbone.
  arXiv  Detail & Related papers  (2024-12-11T12:31:30Z)
• Dynamic layer selection in decoder-only transformers [21.18795712840146]
  We empirically examine two common dynamic inference methods for natural language generation. We find that a pre-trained decoder-only model is significantly more robust to layer removal via layer skipping. We also show that dynamic computation allocation on a per-sequence basis holds promise for significant efficiency gains.
  arXiv  Detail & Related papers  (2024-10-26T00:44:11Z)
• EPIC: Efficient Position-Independent Caching for Serving Large Language Models [19.510078997414606]
  Caching improves serving performance by reusing Key-Value vectors across requests.<n>Existing context caching requires exact prefixes across requests.<n>We introduce Position-Independent Caching (PIC), which enables modular reuse of KV vectors regardless of prefixes.<n>We also introduce EPIC, a serving system incorporating our new LegoLink algorithm, which mitigates the inappropriate "attention sink" effect at every document beginning.
  arXiv  Detail & Related papers  (2024-10-20T08:42:29Z)
• Training-Free Exponential Context Extension via Cascading KV Cache [49.608367376911694]
  We introduce a novel mechanism that leverages cascading sub-cache buffers to selectively retain the most relevant tokens.<n>Our method reduces prefill stage latency by a factor of 6.8 when compared to flash attention on 1M tokens.
  arXiv  Detail & Related papers  (2024-06-24T03:59:17Z)
• Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching [56.286064975443026]
  We make an interesting and somehow surprising observation: the computation of a large proportion of layers in the diffusion transformer, through a caching mechanism, can be readily removed even without updating the model parameters. We introduce a novel scheme, named Learningto-Cache (L2C), that learns to conduct caching in a dynamic manner for diffusion transformers. Experimental results show that L2C largely outperforms samplers such as DDIM and DPM-r, alongside prior cache-based methods at the same inference speed.
  arXiv  Detail & Related papers  (2024-06-03T18:49:57Z)
• ARCH: Efficient Adversarial Regularized Training with Caching [91.74682538906691]
  Adversarial regularization can improve model generalization in many natural language processing tasks. We propose a new adversarial regularization method ARCH, where perturbations are generated and cached once every several epochs. We evaluate our proposed method on a set of neural machine translation and natural language understanding tasks.
  arXiv  Detail & Related papers  (2021-09-15T02:05:37Z)

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.