Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation | Paper Citation Record

Observation 08628950-e618-4828-b7b6-a9361d969bd6 · outbound

This paper cites How Cox automotive launched AI agents at scale using Amazon Bedrock AgentCore,.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation How Cox automotive launched AI agents at scale using Amazon Bedrock AgentCore,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7313a38-b5b1-419f-9d2d-cb252845d5b0 · outbound

This paper cites Engine provides personalized service to 1 million travelers with Agentforce,.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation Engine provides personalized service to 1 million travelers with Agentforce,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e141860-a2c8-4add-b03a-bd4036dfe2c0 · outbound

This paper cites Anthropic clinches $380 billion valuation after $30 billion funding round,.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation Anthropic clinches $380 billion valuation after $30 billion funding round,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f30d1020-3a47-4a42-8182-f439e9284352 · outbound

This paper cites Uber CTO shows how claude code can blow up AI budgets,.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation Uber CTO shows how claude code can blow up AI budgets,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6287643e-5d97-42a4-abf8-a7436d5f5d67 · outbound

This paper cites Qwen3 Technical Report.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation Qwen3 Technical Report

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29945232-b49f-4422-909c-59b6f7e7d876 · outbound

This paper cites Kimi K2.5: Visual Agentic Intelligence.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation Kimi K2.5: Visual Agentic Intelligence

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9584d029-a3d4-4370-aa2f-bbd12b9714a6 · outbound

This paper cites Deepseek-v4: Towards highly efficient million-token context intelligence,.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation Deepseek-v4: Towards highly efficient million-token context intelligence,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 344d7d71-960a-4d53-8418-324d74daa6f7 · outbound

This paper cites Small Language Models are the Future of Agentic AI.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation Small Language Models are the Future of Agentic AI

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 110004c5-5d24-4b56-be3d-10bf422d284d · outbound

This paper cites Introducing the openhands index,.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation Introducing the openhands index,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd10fb79-56a4-4596-a780-2bf2c0154fcc · outbound

This paper cites Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85f988ea-c3da-406f-8730-f1276d0a98cc · outbound

This paper cites Meta-Harness: End-to-End Optimization of Model Harnesses.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation Meta-Harness: End-to-End Optimization of Model Harnesses

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54752dd6-7d5a-4371-a870-996899c339b6 · outbound

This paper cites Introducing gpt-5.2,.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation Introducing gpt-5.2,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38358f87-bd5e-4620-b7b9-c5a39d0f0df4 · outbound

This paper cites Introducing claude opus 4.7,.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation Introducing claude opus 4.7,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e49d5686-b96d-4204-bf06-c831ccef017c · outbound

This paper cites Qwen3.5: Accelerating productivity with native multimodal agents,.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation Qwen3.5: Accelerating productivity with native multimodal agents,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 905b3c8f-6cee-4017-a19e-4f106a8b5d8c · outbound

This paper cites The Berkeley function calling leaderboard (bfcl): From tool use to agentic evaluation of large language models,.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation The Berkeley function calling leaderboard (bfcl): From tool use to agentic evaluation of large language models,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d0fb670-1714-40e2-8a07-3d1d364973dd · outbound

This paper cites MCP-Atlas: A Large-Scale Benchmark for Tool-Use Competency with Real MCP Servers.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation MCP-Atlas: A Large-Scale Benchmark for Tool-Use Competency with Real MCP Servers

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5118b12b-c9de-4e7f-bd04-e6f9da94f1e9 · outbound

This paper cites Instruction-Following Evaluation for Large Language Models.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation Instruction-Following Evaluation for Large Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67a860de-897d-47f0-a3ae-59b2450cc034 · outbound

This paper cites Measuring short-form factuality in large language models.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation Measuring short-form factuality in large language models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b311b60-31a0-4742-80dc-e649977b6f90 · outbound

This paper cites LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d855009-e5b9-4660-a617-23de16d92e3e · outbound

This paper cites GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b5ac157-2302-4681-9e08-37e37153ad26 · outbound

This paper cites Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f06d599-1688-4067-bd43-458fe1e23791 · outbound

This paper cites WebArena: A Realistic Web Environment for Building Autonomous Agents.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation WebArena: A Realistic Web Environment for Building Autonomous Agents

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40606c50-281c-45f2-a436-d9a515811eb3 · outbound

This paper cites BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 600058e4-999d-4d49-b066-4feec96df7e1 · outbound

This paper cites What Prompts Don't Say: Understanding and Managing Underspecification in LLM Prompts.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation What Prompts Don't Say: Understanding and Managing Underspecification in LLM Prompts

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1ff71b2-c420-47d1-97f2-a38eec420edd · outbound

This paper cites Why Do Multi-Agent LLM Systems Fail?.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation Why Do Multi-Agent LLM Systems Fail?

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45118d18-b748-410e-8e06-f7be94a4ba44 · outbound

This paper cites Where llm agents fail and how they can learn from failures,.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation Where llm agents fail and how they can learn from failures,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73410475-13a3-4c6c-a6ad-58799d03dc23 · outbound

This paper cites Claude code overview,.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation Claude code overview,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8936a570-01a5-4223-8bb0-7aab66e288c4 · outbound

This paper cites an unresolved cited work.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation Unresolved cited work

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88099abc-d97f-4237-8b59-d2e517ee876b · outbound

This paper cites Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f23242b-b7af-4e6b-a69d-269a77ad7f50 · outbound

This paper cites Evaluating AGENTS.md: Are Repository-Level Context Files Helpful for Coding Agents?.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation Evaluating AGENTS.md: Are Repository-Level Context Files Helpful for Coding Agents?

Reference 30

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c0fd06e-f258-49e3-b418-8c3e8a346a5e · outbound

This paper cites Skill authoring best practices,.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation Skill authoring best practices,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 572879fe-e258-42f9-a310-3e29ccf2f76b · outbound

This paper cites Recursive Language Models.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation Recursive Language Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6234d205-da6a-4367-8997-be47d2188bb7 · outbound

This paper cites ACON: Optimizing Context Compression for Long-horizon LLM Agents.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation ACON: Optimizing Context Compression for Long-horizon LLM Agents

Reference 33

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7543fa65-101d-4ac9-b040-55d53c46fad9 · outbound

This paper cites Improving the efficiency of llm agent systems through trajectory reduction,.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation Improving the efficiency of llm agent systems through trajectory reduction,

Reference 34

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 072181b0-e721-43d3-ad53-47ef2eafaeb6 · outbound

This paper cites Boad: Discovering hierarchical software engineering agents via bandit optimization,.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation Boad: Discovering hierarchical software engineering agents via bandit optimization,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03ce8265-32f6-4845-8d41-62ee3dbe0f31 · outbound

This paper cites Introducing the model context protocol,.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation Introducing the model context protocol,

Reference 36

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec8dfd56-ccce-4552-87a5-a661a145a9ee · outbound

This paper cites Inducing Programmatic Skills for Agentic Tasks.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation Inducing Programmatic Skills for Agentic Tasks

Reference 37

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c624eac5-d5bf-4392-b8fb-17fb164f76c1 · outbound

This paper cites AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web Agents.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web Agents

Reference 38

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2c4b187-dd2a-4871-8214-ef8d6516955a · outbound

This paper cites Don't Adapt Small Language Models for Tools; Adapt Tool Schemas to the Models.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation Don't Adapt Small Language Models for Tools; Adapt Tool Schemas to the Models

Reference 39

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 554c7327-56d3-423b-ab13-7e2661471575 · outbound

This paper cites Intercept and control agent behavior with hooks,.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation Intercept and control agent behavior with hooks,

Reference 40

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31a7bf79-833a-4f8c-8663-a4d37484e2a6 · outbound

This paper cites Don't Make Models Guess Security and Safety: Symbolic Guardrails for Domain-Specific AI Agents.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation Don't Make Models Guess Security and Safety: Symbolic Guardrails for Domain-Specific AI Agents

Reference 41

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ecd0ede5-3900-4be5-b7de-4387dde9092c · outbound

This paper cites Towards a Science of Scaling Agent Systems.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation Towards a Science of Scaling Agent Systems

Reference 42

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb0a349e-94d1-46be-ad0c-6f262cc8e10d · outbound

This paper cites Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks

Reference 43

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06ebce89-2ee1-44ff-ad4b-53984ab5fc2c · outbound

This paper cites Metagpt: Meta programming for a multi-agent collaborative framework,.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation Metagpt: Meta programming for a multi-agent collaborative framework,

Reference 44

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4f624ec-4ad1-4307-a77a-3e15b14c6714 · outbound

This paper cites Harness design for long-running application development,.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation Harness design for long-running application development,

Reference 45

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4d11798-61f2-4a77-8519-4d84d3b24735 · outbound

This paper cites The bitter lesson,.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation The bitter lesson,

Reference 46

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65e3afad-f3a8-4f3f-ade7-4ddd1224a4ae · outbound

This paper cites Live-swe-agent: Can software engineering agents self-evolve on the fly?.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation Live-swe-agent: Can software engineering agents self-evolve on the fly?

Reference 47

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bcb082b-24b5-4978-b811-dc31b4460b77 · outbound

This paper cites GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning

Reference 49

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c2e909e-fadf-47b1-a7b7-84a9f0b16cc5 · outbound

This paper cites TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks

Reference 50

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c37f867a-c7c5-4a85-b398-33727bfd46f5 · outbound

This paper cites Loca-bench: Benchmarking language agents under controllable and extreme context growth,.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation Loca-bench: Benchmarking language agents under controllable and extreme context growth,

Reference 51

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df41b1aa-0ac2-48d4-9ca5-8afa6e89fc61 · outbound

This paper cites WebGen-Bench: Evaluating LLMs on Generating Interactive and Functional Websites from Scratch.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation WebGen-Bench: Evaluating LLMs on Generating Interactive and Functional Websites from Scratch

Reference 52

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c53dfeb-cd32-439a-ad2f-0b8bd088aaea · outbound

This paper cites RefactorBench: Evaluating Stateful Reasoning in Language Agents Through Code.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation RefactorBench: Evaluating Stateful Reasoning in Language Agents Through Code

Reference 53

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0dd97940-431f-4d66-944a-16e0ae532201 · outbound

This paper cites The OpenHands Software Agent SDK: A Composable and Extensible Foundation for Production Agents.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation The OpenHands Software Agent SDK: A Composable and Extensible Foundation for Production Agents

Reference 54

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d6afbfe-090c-4cbd-a27f-2b17073480bf · outbound

This paper cites Artificial analysis,.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation Artificial analysis,

Reference 55

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9875865-e8ce-4e8f-a11a-3d497c3c8a48 · outbound

This paper cites Building effective agents,.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation Building effective agents,

Reference 56

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ead7539-0c09-4b66-bc26-2c42d417271e · outbound

This paper cites Effgen: Enabling small language models as capable autonomous agents,.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation Effgen: Enabling small language models as capable autonomous agents,

Reference 57

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fdb2581e-3abb-49a1-83f0-cbe631d8ebf9 · outbound

This paper cites Automated Design of Agentic Systems.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation Automated Design of Agentic Systems

Reference 58

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac06f5a4-dfa9-476f-8a1e-4acb36a8ee62 · outbound

This paper cites AgentSquare: Automatic LLM Agent Search in Modular Design Space.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation AgentSquare: Automatic LLM Agent Search in Modular Design Space

Reference 59

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5afe4d7-5ac6-4f6c-bb22-720bd23339d0 · outbound

This paper cites Multi-agent Architecture Search via Agentic Supernet.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation Multi-agent Architecture Search via Agentic Supernet

Reference 60

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 816be76f-12bd-404c-8db2-bdaf23b8c404 · outbound

This paper cites Multi-agent design: Optimizing agents with better prompts and topologies,.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation Multi-agent design: Optimizing agents with better prompts and topologies,

Reference 61

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 095ff0e2-1e71-49eb-b91a-07391b69e65f · outbound

This paper cites Adapting the Interface, Not the Model: Runtime Harness Adaptation for Deterministic LLM Agents.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation Adapting the Interface, Not the Model: Runtime Harness Adaptation for Deterministic LLM Agents

Reference 62

Resolution: unresolved; no resolver link, observed 2026-07-13T05:40:26.231504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers