BAGEN: Are LLM Agents Budget-Aware?

• URL: http://arxiv.org/abs/2606.00198v1
• Date: Fri, 29 May 2026 17:02:17 GMT
• Title: BAGEN: Are LLM Agents Budget-Aware?
• Abstract summary: Budget-Aware Agents (BAGEN) should treat budget as an active control signal, rather than a passive cost metric.<n>We first systematically define budget estimation as internal budgets (from agent computation) and external budgets (from agent actions)<n>We then formalize budget-awareness as progressive interval estimation.
• Score: 35.04587529168086
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While agents are increasingly spending more resources, today agent cost is mostly measured only after execution. A Budget-Aware Agent (BAGEN) should treat budget as an active control signal, rather than a passive cost metric. We first systematically define budget estimation as internal budgets (from agent computation) and external budgets (from agent actions). We then formalize budget-awareness as progressive interval estimation: at each step of a plan, an agent should predict an upper and lower bound on remaining budget, and alert when completion is unlikely. Scoring with a rollout-replay protocol, we find consistent failure patterns on four environments and five frontier agents: (1) strong agents do not necessarily have strong budget-awareness, with correlation r=0.35. (2) frontier models are consistently over-optimistic, continue spending on tasks that are unlikely to succeed, instead of alerting the user early. (3) budget-aware signal is actionable and trainable. Early stop saves 28-64% tokens on failed trajectories, and SFT+RL strengthens early stop and alert behavior. (4) precise interval calibration remains challenging, with interval coverage capping at 47% after SFT+RL. Project page: https://ragen-ai.github.io/bagen/

Related papers

• AdaTurn: Budget-Aware Test-Time Scaling for Active Visual Perception Agents [43.827500763103586]
  AdaTurn is a budget-aware framework for visual agent training.<n>FA-DAPO converts an over-budget event into a trainable final-decision step.<n>AdaTurn substantially improves low-budget accuracy, for example raising VisualProbe-Medium from 36.7% to 47.6% at four turns.
  arXiv  Detail & Related papers  (2026-07-16T04:07:22Z)
• Green SARC: Predictive Cost and Carbon Governance for Agentic AI Systems [0.0]
  Green SARC applies the SARC governance-by-architecture framework to FinOps and GreenOps.<n>We report four policy-independent results.
  arXiv  Detail & Related papers  (2026-06-14T18:26:43Z)
• Seeing Before Colliding: Anticipatory Safe RL with Frozen Vision-Language Models [0.0]
  We present VLM-Safe-RL, a framework that integrates a frozen vision-language model into the CMDP Lagrangian update as an anticipatory cost term.<n>This is the first work to use frozen VLM signals as an anticipatory cost term inside the CMDP Lagrangian update.
  arXiv  Detail & Related papers  (2026-06-09T04:46:37Z)
• ZEBRA: Zero-shot Budgeted Resource Allocation for LLM Orchestration [8.226365534099399]
  We propose ZEBRA, a framework that reduces multi-phase budget allocation to a continuous nonlinear knapsack problem.<n>On a $150$-task APPS coding benchmark, both ZEBRA variants outperform LLM-direct on every aggregate metric.<n>We show that lightweight algorithmic guidance at inference time can improve the economic behavior of autonomous multi-agent systems.
  arXiv  Detail & Related papers  (2026-05-19T20:50:05Z)
• $\texttt{YC-Bench}$: Benchmarking AI Agents for Long-Term Planning and Consistent Execution [38.30265058791818]
  We introduce $texttYC-Bench$, a benchmark that evaluates capabilities by tasking an agent with running a simulated startup over a one-year horizon spanning hundreds of turns.<n>We evaluate 12 models, both proprietary and open source, across 3 seeds each.<n>Only three models consistently surpass the starting capital of $200K, with Claude Opus 4.6 achieving the highest average final funds at $1.27 M, followed by GLM-5 at $1.21 M at 11$times$ lower inference cost.
  arXiv  Detail & Related papers  (2026-04-01T17:52:19Z)
• Learning Query-Aware Budget-Tier Routing for Runtime Agent Memory [56.0946692457838]
  BudgetMem is a runtime agent memory framework for explicit, query-aware performance-cost control.<n>A lightweight router performs budget-tier routing across modules to balance task performance and memory construction cost.<n>Across LoCoMo, LongMemEval, and HotpotQA, BudgetMem surpasses strong baselines when performance is prioritized.
  arXiv  Detail & Related papers  (2026-02-05T18:57:09Z)
• Budget-Aware Tool-Use Enables Effective Agent Scaling [82.6942342482552]
  Scaling test-time computation improves performance across different tasks on large language models (LLMs)<n>We study how to scale such agents effectively under explicit tool-call budgets, focusing on web search agents.<n>We introduce the Budget Tracker, a lightweight plug-in that provides the agent with continuous budget awareness.
  arXiv  Detail & Related papers  (2025-11-21T07:18:55Z)
• Safe In-Context Reinforcement Learning [19.11554873825587]
  In-context reinforcement learning (ICRL) is an emerging RL paradigm where the agent, after some pretraining procedure, is able to adapt to out-of-distribution test tasks without any parameter updates.<n>We propose the first method that promotes the safety of ICRL's adaptation process in the framework of constrained Markov Decision Processes.
  arXiv  Detail & Related papers  (2025-09-29T23:07:32Z)
• Steering LLM Thinking with Budget Guidance [48.65894557568655]
  Budget guidance is a method for steering the reasoning process of LLMs toward a target budget without requiring any fine-tuning.<n>Our approach introduces a lightweight predictor that models a Gamma distribution over the remaining thinking length.<n>This signal is then used to guide generation in a soft, token-level manner, ensuring that the overall reasoning trace adheres to the specified thinking budget.
  arXiv  Detail & Related papers  (2025-06-16T17:57:05Z)
• Runaway is Ashamed, But Helpful: On the Early-Exit Behavior of Large Language Model-based Agents in Embodied Environments [54.67512489842682]
  Large language models (LLMs) have demonstrated strong planning and decision-making capabilities in complex embodied environments.<n>We take a first step toward exploring the early-exit behavior for LLM-based agents.
  arXiv  Detail & Related papers  (2025-05-23T08:23:36Z)
• Enhancing Adaptive Mixed-Criticality Scheduling with Deep Reinforcement Learning [0.0]
  We enhance Adaptive Mixed-Criticality (AMC) with a deep reinforcement learning (DRL) approach based on a Deep-Q Network. The DRL agent is trained off-line, and at run-time adjusts the low-criticality budgets of tasks to avoid budget overruns, while ensuring that no job misses its deadline if it does not overrun its budget. The results show that the agent is able to reduce budget overruns by at least up to 50%, even when the budget of each task is chosen based on sampling the distribution of its execution time.
  arXiv  Detail & Related papers  (2024-11-01T13:29:33Z)
• Stochastic Shortest Path with Adversarially Changing Costs [57.90236104782219]
  shortest path (SSP) is a well-known problem in planning and control. We present the adversarial SSP model that also accounts for adversarial changes in the costs over time. We are the first to consider this natural setting of adversarial SSP and obtain sub-linear regret for it.
  arXiv  Detail & Related papers  (2020-06-20T12:10:35Z)

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.