Cost-Utility Alignment in LLM Agent Trajectories:Profiling,Attribution,Diagnosis,Adaptation,and Evaluation

• URL: http://arxiv.org/abs/2608.26195v1
• Date: Tue, 25 Aug 2026 06:31:00 GMT
• Title: Cost-Utility Alignment in LLM Agent Trajectories:Profiling,Attribution,Diagnosis,Adaptation,and Evaluation
• Abstract summary: LLM agents execute tasks through multi-step trajectories that accumulate cost in tokens, latency, monetary fees, and environmental risk while producing utility only at the aggregate task level.<n>We develop a trajectory-centric cost-utility alignment framework that treats resource consumption and task contribution as dual ledgers over the same execution.
• Score: 7.673754519525176
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: LLM agents execute tasks through multi-step trajectories that accumulate cost in tokens, latency, monetary fees, and environmental risk while producing utility only at the aggregate task level. Prior surveys address inference optimization, agent capabilities, or evaluation in isolation, leaving practitioners without principled tools to determine whether a trajectory's resource expenditure is justified by its task contribution. We address this gap by developing a trajectory-centric cost-utility alignment framework that treats resource consumption and task contribution as dual ledgers over the same execution, organized around five analytical stages: cost profiling, utility attribution, misalignment diagnosis, targeted adaptation, and evaluation. Utility attribution is central to this structure: rather than relying on aggregate outcomes, it organizes contribution methods by evidential strength, from process proxies and information dependency to counterfactual replay, supplying the causal evidence that grounds diagnosis and guides adaptation. Using this framework, we analyze recent agent systems, attribution methods, and evaluation protocols covering efficiency, reliability, and economic value, as well as five forms of misalignment spanning cognitive and context use, external interaction, recovery-loop control, resource-capability allocation, and multi-agent coordination, together with their targeted adaptations. The result is a closed analytical loop connecting the cost side of agent execution to its utility side, providing a structured basis for resource-aware agent design and deployment.

Related papers

• A Hybrid Agentic AI Framework for Intelligent Supply Chain Analytics [3.3292687565862535]
  We propose an agentic system for supply chain analytics that bridges the gap between business decision-making and technical expertise.<n>The system supports both exploratory analysis and deterministic delegates, enabling planners to transition between ad hoc questions and structured processes.<n>Results show that our multi-agent design achieves a 90% accuracy, which is competitive with a single agent baseline.
  arXiv  Detail & Related papers  (2026-09-11T21:59:30Z)
• From Sequence to Structure: Relational Uncertainty Propagation for LLM Agents [75.69180947909148]
  We propose a trajectory-level UQ framework for large language model (LLM) agents.<n>RuPA represents an execution history as a directed trajectory graph in which reasoning states, tool interactions, and environment feedback are nodes connected by temporal and semantic dependency edges.<n>We evaluate RUPA on representative agent benchmarks, including $$-2, Terminal-Bench-2, and GAIA, using 6 open-source LLMs spanning multiple model families.
  arXiv  Detail & Related papers  (2026-08-17T01:40:14Z)
• EASy: Towards Efficient LLM-Based Agentic System [54.10819421625103]
  We propose EASy, a trainable agentic framework that jointly optimize task performance and computational efficiency through reinforcement learning.<n> EASy equips an LLM-based orchestrator with explicit knowledge of the capability and cost profiles of heterogeneous executors, enabling context-sensitive coordination beyond performance-only routing.<n>It further introduces a milestone-plan-act workflow that decomposes complex tasks into manageable milestones, constructs dependency-aware execution graphs, assigns suitable executors, and parallelizes independent steps while adapting subsequent decisions to intermediate outcomes.
  arXiv  Detail & Related papers  (2026-08-05T08:50:36Z)
• Agentomics: Economic Foundations for the Valuation, Attribution, and Pricing of AI Agents in Human-AI Workflows [20.036142577511455]
  This paper introduces emphAgentomics, a framework for valuing, attributing, and pricing human and artificial agents.<n>A security-operations case study illustrates how the framework accounts for productivity gains, deployment costs, reliability losses, and coalition-level complementarities in hybrid human-AI-AI.
  arXiv  Detail & Related papers  (2026-06-09T03:28:14Z)
• Agents that Matter: Optimizing Multi-Agent LLMs via Removal-Based Attribution [21.301961149692453]
  We formalize agent attribution as a cooperative game, parameterized by the coalition distribution, removal protocol, and target metric.<n>We show that Leave-One-Out (LOO) identifies bottleneck agents as effectively as bottleneck methods, but at a fraction of the computational cost.<n>We also apply our framework to audit a medical MAS, revealing that agent contributions to diagnostic accuracy and ethical behavior are often decoupled.
  arXiv  Detail & Related papers  (2026-05-26T19:39:27Z)
• When Independent Sampling Outperforms Agentic Reasoning [4.226475360842309]
  We study how to allocate inference-time compute for competitive programming under fixed budgets.<n>We compare agent-based reasoning with repeated independent sampling (k-shot) as a function of both cost and number of model calls.
  arXiv  Detail & Related papers  (2026-05-08T20:53:51Z)
• Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning [79.88942231770629]
  Reinforcement learning (RL) has become a central post-training tool for improving the reasoning abilities of large language models (LLMs)<n>We formalize rollout pipelines with unified notation and introduce Generate-Filter-Control-Replay (GFCR)<n>We synthesize methods spanning RL with verifiable rewards, process supervision, judge-based gating, guided and tree/segment rollouts, adaptive compute allocation, early-exit and partial rollouts, throughput optimization, and replay/recomposition for self-improvement.
  arXiv  Detail & Related papers  (2026-04-08T00:53:29Z)
• When Should a Robot Think? Resource-Aware Reasoning via Reinforcement Learning for Embodied Robotic Decision-Making [68.12864562049957]
  Embodied robotic systems increasingly rely on large language model (LLM)-based agents to support high-level reasoning.<n>This raises a fundamental question for embodied agents: when should the agent reason, and when should it act?<n>We propose RARRL (Resource-Aware Reasoning via Reinforcement Learning), a hierarchical framework for resource-aware orchestration of embodied agents.
  arXiv  Detail & Related papers  (2026-03-17T15:38:50Z)
• Benchmarking LLM Agents for Wealth-Management Workflows [0.0]
  This dissertation extends TheAgentCompany with a finance-focused environment.<n>It investigates whether a general purpose LLM agent can complete representative wealth-management tasks both accurately and economically.
  arXiv  Detail & Related papers  (2025-12-01T21:56:21Z)
• AgentEvolver: Towards Efficient Self-Evolving Agent System [51.54882384204726]
  We present AgentEvolver, a self-evolving agent system that drives autonomous agent learning.<n>AgentEvolver introduces three synergistic mechanisms: self-questioning, self-navigating, and self-attributing.<n>Preliminary experiments indicate that AgentEvolver achieves more efficient exploration, better sample utilization, and faster adaptation compared to traditional RL-based baselines.
  arXiv  Detail & Related papers  (2025-11-13T15:14:47Z)
• Source Attribution in Retrieval-Augmented Generation [3.579940498399598]
  This paper investigates the feasibility and effectiveness of adapting Shapley-based attribution to identify influential retrieved documents in RAG.<n>Our work aims to: (1) systematically apply established attribution principles to the RAG document-level setting; (2) quantify how well SHAP approximations can mirror exact attributions; and (3) evaluate their practical explainability in identifying critical documents.
  arXiv  Detail & Related papers  (2025-07-06T17:36:45Z)
• Cost-Sensitive Portfolio Selection via Deep Reinforcement Learning [100.73223416589596]
  We propose a cost-sensitive portfolio selection method with deep reinforcement learning. Specifically, a novel two-stream portfolio policy network is devised to extract both price series patterns and asset correlations. A new cost-sensitive reward function is developed to maximize the accumulated return and constrain both costs via reinforcement learning.
  arXiv  Detail & Related papers  (2020-03-06T06:28:17Z)

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.