SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2604.06296 · 2026

Client-Side Optimization for LLM-Based Agent

Tianyi Peng, Wenyue Hua, Qian Xie, Kostis Kaffes, Sripad Karne, Armaan Agrawal, Nikos Pagonas

arXiv · PDF · Open in the Atlas

Code that ran

None of the 4 samples (functions and classes) lifted from this paper's linked repositories has a recorded run on a synthesized input (4 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2604.06296.json · badge: /api/ran/2604.06296.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
AgentOptimizer/agentopt canonical (classifier label)
classifier basis: census
0 ran · 4 no recorded run
FunctionStatusWhere it lives
compute_price Not yet run
unverified (harvested, no recorded run)
AgentOptimizer/agentopt/src/agentopt/model_price.py
code served (permissive licence) · get_code("1a08d4c71aaa928b")
How it ran

no invocation recorded.

get_faster_neighbor Not yet run
unverified (harvested, no recorded run)
AgentOptimizer/agentopt/src/agentopt/model_topology.py
code served (permissive licence) · get_code("68106c4826c66802")
How it ran

no invocation recorded.

get_higher_quality_neighbor Not yet run
unverified (harvested, no recorded run)
AgentOptimizer/agentopt/src/agentopt/model_topology.py
code served (permissive licence) · get_code("d5e3b642da927628")
How it ran

no invocation recorded.

get_model_price Not yet run
unverified (harvested, no recorded run)
AgentOptimizer/agentopt/src/agentopt/model_price.py
code served (permissive licence) · get_code("d8859c6c42188062")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 4 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

AI agents are increasingly deployed in real-world applications, including systems such as Manus, OpenClaw, and coding agents. Existing research has primarily focused on server-side efficiency, proposing methods such as caching, speculative execution, traffic scheduling, and load balancing to reduce the cost of serving agentic workloads. However, as users increasingly construct agents by composing local tools, remote APIs, and diverse models, an equally important optimization problem arises on the client side. Client-side optimization asks how developers should allocate the resources available to them, including model choice, local tools, and API budget across pipeline stages, subject to application-specific quality, cost, and latency constraints. Because these objectives depend on the task and deployment setting, they cannot be determined by server-side systems alone. We introduce AGENTOPT, the first framework-agnostic Python package for client-side agent optimization. We first study model selection, a high-impact optimization lever in multi-step agent pipelines. Given a pipeline and a small evaluation set, the goal is to find the most cost-effective assignment of models to pipeline roles. This problem is consequential in practice: at matched accuracy, the cost gap between the best and worst model combinations can reach 13-32× in our experiments. To efficiently explore the exponentially growing combination space, AGENTOPT implements ten search algorithms, including UCB-E, UCB-E with Low-Rank Factorization, Arm Elimination, Epsilon-LUCB, Threshold Successive Elimination, and Bayesian Optimization. Across four benchmarks, UCB-E recovers near-optimal accuracy while reducing evaluation budget by 62-76% relative to brute-force search.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2604.06296")
get_code_for_paper("2604.06296")
have("2604.06296")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2604.06296.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2604.06296.svg)](https://syntology.ai/paper/2604.06296)

Connect an agent — have() is free.