The Handoff Tax: Continuing Non-Native Trajectories in LLM Agents
Summary
This paper studies the cost-quality trade-off when handing off tasks between low-cost and high-cost LLM models, introducing the 'handoff tax' concept where full trajectory transfer during escalation yields suboptimal quality recovery at a cost premium.
View Cached Full Text
Cached at: 08/27/26, 07:17 AM
Paper page - The Handoff Tax: Continuing Non-Native Trajectories in LLM Agents
Source: https://huggingface.co/papers/2608.24358
Abstract
Codingagentsperformlong-runningtasksspanningdozensofmodelcalls,tooluses,andcodeedits.Astheserunsunfold,usersfaceapracticalcost-qualitytrade-off:escalatingtoastrongermodelwhenacheaperonestruggles,ordownshiftingoncethehardreasoningiscomplete.Eachswitchrequiresthereceivertocontinueanon-nativetrajectoryproducedbyanothermodel.Westudyhowthishandoffaffectsqualityandcost,andhowvaryingthetrajectoryinformationinheritedbythereceiverchangestheoutcome.Usingpairsoflow-cost,low-capability(LC)andhigh-cost,high-capability(HC)modelsfromtheClaudeandGPTfamilies,wevaryhandoffdirection,timing,andinterface,comparingfull-trajectorytransfer,compaction,andtrajectoryremovalwhilepreservingtherepositorystate.Acrossbothmodelfamilies,full-trajectoryescalationrecoverslessthanhalfoftheLC-to-HCqualitygapwhileincurringasubstantialcostpremium.Wetermthiscost-qualitypenaltythehandofftax.Bycontrast,downshiftoffersafavorablecost-qualitypoint.Interestingly,thepreferredinterfacealsoreverseswithdirection:reducingLC-modeltrajectoryinformationimprovesescalationquality,whereasremovingtheHC-modeltrajectoryreducesdownshiftquality.
View arXiv pageView PDFAdd to collection
Get this paper in your agent:
hf papers read 2608\.24358
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2608.24358 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2608.24358 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2608.24358 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
The Collaboration Tax: How Much LLM Multi-Agent Systems Pay to Coordinate
This paper formulates the collaboration tax in LLM multi-agent systems, measuring it across tasks and models to reveal predictable mechanisms and practical interventions.
@rohanpaul_ai: New Stanford paper argues that, under equal reasoning budgets, one LLM usually solves multi-hop problems better than ma…
A new Stanford paper shows that under equal reasoning token budgets, single LLMs typically outperform multi-agent systems on multi-hop reasoning tasks, with gains from multi-agent setups often stemming from additional compute rather than architectural superiority. The paper uses the Data Processing Inequality to explain why information loss in handoffs harms multi-agent performance, and identifies context quality as the key factor where multi-agent systems can provide benefits.
@_avichawla: A tricky LLM interview question: Your agent runs everything on a frontier LLM, so you add a routing layer that sends se…
Explains why model routing in agent tasks may not save costs due to cache warmup, and describes a production solution with model affinity and the open-source proxy Plano to achieve actual savings.
Toward Reliable Design of LLM-Enabled Agentic Workflows: Optimizing Latency-Reliability-Cost Tradeoffs
This paper analyzes tradeoffs between latency, reliability, and cost in LLM-enabled agentic workflows, introducing performance models and deriving optimal resource allocation policies like water-filling token allocation.
Not All Tokens Are Equal: Inflation-Aware Routing for Agentic LLM Systems
This paper introduces InflationAgent, a routing system for agentic LLMs that measures token inflation, predicts task difficulty using CoT Branching Entropy, and optimizes model selection to maximize accuracy per cost, achieving higher accuracy with fewer tokens on benchmarks like GSM8K.