The rapid shift from stateless large language models (LLMs) to autonomous, goal-driven agents raises a central question: When is agentic AI truly necessary? While agents enable multi-step reasoning, persistent memory, and tool orchestration, deploying them indiscriminately leads to higher cost, complexity, and risk. We present STRIDE (Systematic Task Reasoning Intelligence Deployment Evaluator), a framework that provides principled recommendations for selecting between three modalities: (i) direct LLM calls, (ii) guided AI assistants, and (iii) fully autonomous agentic AI. STRIDE integrates structured task decomposition, dynamism attribution, and self-reflection requirement analysis to produce an Agentic Suitability Score, ensuring that full agentic autonomy is reserved for tasks with inherent dynamism or evolving context. Evaluated across 30 real-world tasks spanning SRE, compliance, and enterprise automation, STRIDE achieved 92% accuracy in modality selection, reduced unnecessary agent deployments by 45%, and cut resource costs by 37%. Expert validation over six months in SRE and compliance domains confirmed its practical utility, with domain specialists agreeing that STRIDE effectively distinguishes between tasks requiring simple LLM calls, guided assistants, or full agentic autonomy. This work reframes agent adoption as a necessity-driven design decision, ensuring autonomy is applied only when its benefits justify the costs.

Large Language Models (LLMs) are increasingly being used to plan, reason, and execute tasks across diverse scenarios. In use cases like repeatable workflows and agentic settings, prompts are often reused with minor variations while having a similar structure for recurring tasks. This opens up opportunities for caching. However, exact prompt matching fails on such structurally similar prompts, while semantic caching may produce incorrect responses by ignoring critical differences. To address this, we introduce \ourmethod{}, a generative cache that produces variation-aware responses for structurally similar prompts. \ourmethod{} identifies reusable response patterns across similar prompt structures and synthesizes customized outputs for new requests. We show that \ourmethod{} achieves 83\% cache hit rate, while having minimal incorrect hits on datasets without prompt repetition. In agentic workflows, it improves cache hit rate by $\sim$20\% and reduces end-to-end execution latency by $\sim$34\% compared to standard prompt matching.

Enabling agentic AI systems to adapt their problem-solving approaches based on post-training interactions remains a fundamental challenge. While systems that update and maintain a memory at inference time have been proposed, existing designs only steer the system by modifying textual input to a language model or agent, which means that they cannot change sampling parameters, remove tools, modify system prompts, or switch between agentic and workflow paradigms. On the other hand, systems that adapt more flexibly require offline optimization and remain static once deployed. We present Experience-Guided Reasoner (EGuR), which generates tailored strategies -- complete computational procedures involving LLM calls, tools, sampling parameters, and control logic -- dynamically at inference time based on accumulated experience. We achieve this using an LLM-based meta-strategy -- a strategy that outputs strategies -- enabling adaptation of all strategy components (prompts, sampling parameters, tool configurations, and control logic). EGuR operates through two components: a Guide generates multiple candidate strategies conditioned on the current problem and structured memory of past experiences, while a Consolidator integrates execution feedback to improve future strategy generation. This produces complete, ready-to-run strategies optimized for each problem, which can be cached, retrieved, and executed as needed without wasting resources. Across five challenging benchmarks (AIME 2025, 3-SAT, and three Big Bench Extra Hard tasks), EGuR achieves up to 14% accuracy improvements over the strongest baselines while reducing computational costs by up to 111x, with both metrics improving as the system gains experience.

A popular method to adapt large language models (LLMs) to new tasks is in-context learning (ICL), which is effective but incurs high inference costs as context length grows. In this paper we propose a method to perform instruction induction, where we take training examples and reduce them to a compact but descriptive prompt that can achieve performance comparable to ICL over the full training set. Specifically, we propose PROMPT-MII, a reinforcement learning (RL) based framework to meta-learn an instruction induction model that can generate compact instructions on the fly for an arbitrary new dataset. We train on over 3,000 diverse classification datasets from the HuggingFace hub, and evaluate on 90 unseen tasks. PROMPT-MII improves downstream model quality by 4-9 F1 points (10-20% relative), matching ICL performance while requiring 3-13x fewer tokens.

Large Language Models (LLMs) have recently been applied to reranking tasks in information retrieval, achieving strong performance. However, their high computational demands often hinder practical deployment. Existing studies evaluate the efficiency of LLM-based rerankers using proxy metrics such as latency, the number of forward passes, input tokens, and output tokens. However, these metrics depend on hardware and running-time choices (\eg parallel or not, batch size, etc), and often fail to account for model size, making it difficult to interpret and obscuring the evaluation of the efficiency-effectiveness tradeoff. To address this issue, we propose \ours\footnote{https://github.com/zhiyuanpeng/EER-FLOPs.} for LLM-based rerankers: RPP (ranking metrics per PetaFLOP), measuring how much ranking quality (e.g., NDCG or MRR) a method achieves per PetaFLOP, and QPP (queries per PetaFLOP), measuring how many queries can be processed per PetaFLOP. Accompanied by the new metrics, an interpretable FLOPs estimator is developed to estimate the FLOPs of an LLM-based reranker even without running any experiments. Based on the proposed metrics, we conduct comprehensive experiments to evaluate a wide range of LLM-based rerankers with different architectures, studying the efficiency-effectiveness trade-off and bringing this issue to the attention of the research community.

Systems often repeat the same prompt to large language models (LLMs) and aggregate responses to improve reliability. Common approaches include self-consistency or simple majority voting (sample multiple outputs and choose the mode), prompt ensembling (rephrasing prompts to reduce wording sensitivity), and multi-agent debate (running multiple instances and aggregating their conclusions). Such consensus methods can stabilize outputs and improve accuracy, especially on multi-step reasoning tasks [1]. This short note analyzes an estimator of the self-consistency of LLMs and the tradeoffs it induces under a fixed compute budget B = mn, where m is the number of prompts sampled from the task distribution and n is the number of repeated LLM calls per prompt; the resulting analysis favors a rough split m,n B. It complements recent work on self-consistency prompting that aggregates multiple sampled reasoning paths to stabilize predictions [2, 3]. Consider a prompt x that requires a binary response.

Large Language Models (LLMs) have demonstrated remarkable capabilities in interactive decision-making tasks, but existing methods often struggle with error accumulation and lack robust self-correction mechanisms. We introduce "Reflect before Act" (REBACT), a novel approach that enhances LLM-based decision-making by introducing a critical reflect step prior to taking the next action. This approach allows for immediate error correction, ensuring smooth action path and adaptibity to environment feedback. We evaluate REBACT on three diverse interactive environments: ALFWorld, WebShop, and TextCraft. Our results demonstrate that REBACT significantly outperforms strong baselines, improving success rates by up to 24% on WebShop (achieving 61%), 6.72% on ALFWorld (achieving 98.51%), and 0.5% on TextCraft (achieving 99.5%) using Claude3.5-sonnet as the underlying LLM. Further analysis reveals that REBACT's performance improvements are achieved with only a few modification steps, demonstrating its computational efficiency.

When using LLMs to rank items based on given criteria, or evaluate answers, the order of candidate items can influence the model's final decision. This sensitivity to item positioning in a LLM's prompt is known as position bias. Prior research shows that this bias exists even in large models, though its severity varies across models and tasks. In addition to position bias, LLMs also exhibit varying degrees of low repetition consistency, where repeating the LLM call with the same candidate ordering can lead to different rankings. To address both inconsistencies, a common approach is to prompt the model multiple times with different candidate orderings and aggregate the results via majority voting. However, this repetition strategy, significantly increases computational costs. Extending prior findings, we observe that both the direction -- favoring either the earlier or later candidate in the prompt -- and magnitude of position bias across instances vary substantially, even within a single dataset. This observation highlights the need for a per-instance mitigation strategy. To this end, we introduce a dynamic early-stopping method that adaptively determines the number of repetitions required for each instance. Evaluating our approach across three LLMs of varying sizes and on two tasks, namely re-ranking and alignment, we demonstrate that transitioning to a dynamic repetition strategy reduces the number of LLM calls by an average of 81%, while preserving the accuracy. Furthermore, we propose a confidence-based adaptation to our early-stopping method, reducing LLM calls by an average of 87% compared to static repetition, with only a slight accuracy trade-off relative to our original early-stopping method.

Generative AI is being leveraged to solve a variety of computer-use tasks involving desktop applications. State-of-the-art systems have focused solely on improving accuracy on leading benchmarks. However, these systems are practically unusable due to extremely high end-to-end latency (e.g., tens of minutes) for tasks that typically take humans just a few minutes to complete. To understand the cause behind this and to guide future developments of computer agents, we conduct the first study on the temporal performance of computer-use agents on OSWorld, the flagship benchmark in computer-use AI. We find that large model calls for planning and reflection account for the majority of the overall latency, and as an agent uses more steps to complete a task, each successive step can take 3x longer than steps at the beginning of a task. We then construct OSWorld-Human, a manually annotated version of the original OSWorld dataset that contains a human-determined trajectory for each task. We evaluate 16 agents on their efficiency using OSWorld-Human and found that even the highest-scoring agents on OSWorld take 1.4-2.7x more steps than necessary.

Although large language models (LLMs) are becoming increasingly capable of solving challenging real-world tasks, accurately quantifying their uncertainty remains a critical open problem, which limits their applicability in high-stakes domains. This challenge is further compounded by the closed-source, black-box nature of many state-of-the-art LLMs. Moreover, LLM-based systems can be highly sensitive to the prompts that bind them together, which often require significant manual tuning (i.e., prompt engineering). In this work, we address these challenges by viewing LLM-based systems through a Bayesian lens. We interpret prompts as textual parameters in a statistical model, allowing us to use a small training dataset to perform Bayesian inference over these prompts. This novel perspective enables principled uncertainty quantification over both the model's textual parameters and its downstream predictions, while also incorporating prior beliefs about these parameters expressed in free-form text. To perform Bayesian inference, a difficult problem even for well-studied data modalities, we introduce Metropolis-Hastings through LLM Proposals (MHLP), a novel Markov chain Monte Carlo (MCMC) algorithm that combines prompt optimization techniques with standard MCMC methods. MHLP is a turnkey modification to existing LLM pipelines, including those that rely exclusively on closed-source models. Empirically, we demonstrate that our method yields improvements in both predictive accuracy and uncertainty quantification (UQ) on a range of LLM benchmarks and UQ tasks. More broadly, our work demonstrates a viable path for incorporating methods from the rich Bayesian literature into the era of LLMs, paving the way for more reliable and calibrated LLM-based systems.