From Question Answering to Task Completion: A Survey on Agent System and Harness Design | Paper Citation Record

Observation 58522ca2-8cbd-43b6-af60-cddcf722c9c6 · outbound

This paper cites Language models are few-shot learners,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Language models are few-shot learners,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84375e0d-1b05-49c3-b727-5ffe8ad49c17 · outbound

This paper cites Training language models to follow instructions with human feedback,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Training language models to follow instructions with human feedback,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f56010a-5489-44f8-ab7b-b27909e03997 · outbound

This paper cites Large Language Model Agent: A Survey on Methodology, Applications and Challenges.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Large Language Model Agent: A Survey on Methodology, Applications and Challenges

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-07-03T17:08:43.105689Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6d337973-b161-4fa9-a733-5fc38a523a1a · outbound

This paper cites The rise and potential of large language model based agents: A survey,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design The rise and potential of large language model based agents: A survey,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8a26d76-d63f-49a2-bfb2-db2d5f7046c1 · outbound

This paper cites Introducing devin, the first AI software engi- neer,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Introducing devin, the first AI software engi- neer,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bd1b179-c552-4a1f-8ee5-4a7a69d09668 · outbound

This paper cites How claude code works,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design How claude code works,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07ef3c0c-9b6e-4abd-9109-071ce6584eec · outbound

This paper cites Harness engineering: Leveraging codex in an agent- first world,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Harness engineering: Leveraging codex in an agent- first world,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7e47489-82db-4065-a3e0-4fea914af657 · outbound

This paper cites From Mind to Machine: The Rise of Manus AI as a Fully Autonomous Digital Agent.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design From Mind to Machine: The Rise of Manus AI as a Fully Autonomous Digital Agent

Reference 8

Resolution: metadata mismatch; arxiv_id, observed 2026-07-27T02:21:03.069205Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 13154711-0fc9-41c4-9ac0-fca12f83d261 · outbound

This paper cites AutoGPT,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design AutoGPT,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65e619f7-072e-466a-bbb7-36cd89138970 · outbound

This paper cites Openhands: An open platform for ai software developers as generalist agents,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Openhands: An open platform for ai software developers as generalist agents,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d663ab7-a072-460c-8a22-1c3dab9c01c9 · outbound

This paper cites OpenClaw: Personal AI assistant,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design OpenClaw: Personal AI assistant,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26d516e5-be41-4065-97e1-4d19ff11f0c4 · outbound

This paper cites Measuring Massive Multitask Language Understanding.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Measuring Massive Multitask Language Understanding

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-07-03T17:08:43.002801Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 834324a1-057a-4481-b9cf-7a13146b37f9 · outbound

This paper cites Gpqa: A graduate-level google-proof q&a benchmark,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Gpqa: A graduate-level google-proof q&a benchmark,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21822162-ffc5-408f-bfb0-a4ea067cb35f · outbound

This paper cites Evaluating Large Language Models Trained on Code.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Evaluating Large Language Models Trained on Code

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-07-03T17:08:43.088024Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8c647b28-4f5b-4596-a25e-e8d06aae98b6 · outbound

This paper cites Humanity's Last Exam.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Humanity's Last Exam

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-07-03T16:58:43.696000Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d643b8ee-076a-4272-9ffd-ab8bf7868e2e · outbound

This paper cites Swe-bench: Can language models resolve real-world github issues?.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Swe-bench: Can language models resolve real-world github issues?

Reference 16

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19b4ab92-5b53-4124-a1e4-4a0b495f0e84 · outbound

This paper cites Webarena: A realistic web environ- ment for building autonomous agents,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Webarena: A realistic web environ- ment for building autonomous agents,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7ab6247-f756-40ee-a44f-8efb31a25971 · outbound

This paper cites Osworld: Benchmarking mul- timodal agents for open-ended tasks in real computer environ- ments,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Osworld: Benchmarking mul- timodal agents for open-ended tasks in real computer environ- ments,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8168787c-8dcd-4f39-a89d-748b125cc7eb · outbound

This paper cites Theagent- company: benchmarking llm agents on consequential real world tasks,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Theagent- company: benchmarking llm agents on consequential real world tasks,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d814d75-9fb4-44f6-a7b4-8ebd02381387 · outbound

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

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-07-03T16:58:43.713064Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 521d6e99-f4b7-43ba-8367-78101d048baf · outbound

This paper cites Swe-agent: Agent-computer interfaces enable automated software engineering,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Swe-agent: Agent-computer interfaces enable automated software engineering,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f7bde6d-8e79-460f-9f7f-daf03a9ae462 · outbound

This paper cites My AI adoption journey,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design My AI adoption journey,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77a701d5-1f38-4a72-8d6a-2407e755e628 · outbound

This paper cites Natural-Language Agent Harnesses.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Natural-Language Agent Harnesses

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-07-03T16:58:43.621297Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0b11ae1e-86b3-45e4-8be4-38283a1ebcbf · outbound

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

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Meta-Harness: End-to-End Optimization of Model Harnesses

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-07-03T16:58:43.738570Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2bd0337b-55d7-49d4-bf87-1713529a3f2d · outbound

This paper cites Opensquilla: Token-efficient ai agent with same budget, higher intelligence density,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Opensquilla: Token-efficient ai agent with same budget, higher intelligence density,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9768f811-0a2a-4bf3-acc9-57baec4f2e1c · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Chain-of-thought prompting elicits reasoning in large language models,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1ef6680-9cd1-42a9-861a-c8ada338e125 · outbound

This paper cites Self-Consistency Improves Chain of Thought Reasoning in Language Models.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Self-Consistency Improves Chain of Thought Reasoning in Language Models

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-07-03T16:58:43.751042Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 32df21dc-46fa-4c0a-b9e8-a275b1cb56be · outbound

This paper cites Tree of thoughts: Deliberate problem solving with large language models,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Tree of thoughts: Deliberate problem solving with large language models,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a87922a-6235-43d4-b4eb-681aa58bdcc0 · outbound

This paper cites Effective context engineering for AI agents,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Effective context engineering for AI agents,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a66276ae-5cb7-4df7-8376-27278800f95e · outbound

This paper cites Retrieval- augmented generation for knowledge-intensive nlp tasks,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Retrieval- augmented generation for knowledge-intensive nlp tasks,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b971c240-1bd1-4be4-94db-ef401d132c94 · outbound

This paper cites Memgpt: towards llms as operating systems.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Memgpt: towards llms as operating systems

Reference 31

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1feae89a-2ef6-4092-9576-a6bc02330997 · outbound

This paper cites Tool- former: Language models can teach themselves to use tools,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Tool- former: Language models can teach themselves to use tools,

Reference 32

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 161f824f-295e-4aeb-964d-2285f960c3ed · outbound

This paper cites Gorilla: Large language model connected with massive apis,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Gorilla: Large language model connected with massive apis,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b2fe69c-c9ce-4e1f-a710-226782561abc · outbound

This paper cites Voyager: An Open-Ended Embodied Agent with Large Language Models.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Voyager: An Open-Ended Embodied Agent with Large Language Models

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-07-03T16:58:43.667693Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 62d12a83-18ab-4397-9b48-5edda27848d9 · outbound

This paper cites Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-07-03T17:08:42.991675Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c2b073f3-6b79-46b8-a6fb-ba11c55bd5d0 · outbound

This paper cites ReAct: Synergizing Reasoning and Acting in Language Models.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design ReAct: Synergizing Reasoning and Acting in Language Models

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-07-03T16:58:43.706847Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2b5d062b-464f-4662-93d3-65de195676a6 · outbound

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

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks

Reference 37

Resolution: verified exact; local_arxiv, observed 2026-07-03T16:58:43.628288Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c9fa01c1-68fd-4d4d-bc36-3df0351a7c1a · outbound

This paper cites Symphony: Synergistic multi-agent planning with heterogeneous language model assembly,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Symphony: Synergistic multi-agent planning with heterogeneous language model assembly,

Reference 38

Resolution: verified exact; arxiv_id, observed 2026-07-03T16:58:43.634674Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a49b79f7-9de0-44ac-839f-e4964bff13d6 · outbound

This paper cites Openai agents sdk,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Openai agents sdk,

Reference 39

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 954da0f9-8ef0-4a53-8d57-0e481a8bfacf · outbound

This paper cites Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses

Reference 40

Resolution: verified exact; local_arxiv, observed 2026-07-03T17:08:43.000167Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6b6f64c2-519b-438b-a0dd-300b98840a08 · outbound

This paper cites Webrl: Training llm web agents via self- evolving online curriculum reinforcement learning,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Webrl: Training llm web agents via self- evolving online curriculum reinforcement learning,

Reference 41

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5eccc082-9038-474f-867b-4b1859a9e440 · outbound

This paper cites Computerrl: Scaling end-to-end online reinforcement learning for computer use agents.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Computerrl: Scaling end-to-end online reinforcement learning for computer use agents

Reference 42

Resolution: verified exact; arxiv_id, observed 2026-07-03T16:58:43.761088Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation bbc10a30-eb7b-4656-8f72-24d6933ba2e5 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 43

Resolution: verified exact; local_arxiv, observed 2026-07-03T17:08:43.133784Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9140a3cb-c0db-4691-9c49-8bbc9b641215 · outbound

This paper cites EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle

Reference 44

Resolution: verified exact; local_arxiv, observed 2026-07-03T16:58:43.731204Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 656ff691-5abf-4439-b74e-83916829252d · outbound

This paper cites Agentevolver: Towards efficient self-evolving agent system.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Agentevolver: Towards efficient self-evolving agent system

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-07-03T16:58:43.803376Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 267608f2-640a-4f2f-8151-81e258f4d3a2 · outbound

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

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents

Reference 46

Resolution: verified exact; local_arxiv, observed 2026-07-03T16:58:43.781281Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e89abc72-ac39-4b02-b00e-c3f11b83290a · outbound

This paper cites A survey on large language model based autonomous agents,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design A survey on large language model based autonomous agents,

Reference 47

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f94880c6-3f83-4f45-9173-3a33cda34c65 · outbound

This paper cites Large Language Model based Multi-Agents: A Survey of Progress and Challenges.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Large Language Model based Multi-Agents: A Survey of Progress and Challenges

Reference 48

Resolution: verified exact; local_arxiv, observed 2026-07-03T16:58:43.678082Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4a9c5609-b8df-4a86-8735-a48437171287 · outbound

This paper cites A survey on llm-based multi-agent systems: workflow, infrastructure, and challenges,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design A survey on llm-based multi-agent systems: workflow, infrastructure, and challenges,

Reference 49

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 617ff05e-458b-43d2-9771-6c5d98faa7e2 · outbound

This paper cites Multi-Agent Collaboration Mechanisms: A Survey of LLMs.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Multi-Agent Collaboration Mechanisms: A Survey of LLMs

Reference 50

Resolution: verified exact; local_arxiv, observed 2026-07-03T16:58:43.775282Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c73ff787-acee-40a5-a6c5-db91920974d0 · outbound

This paper cites Survey on Evaluation of LLM-based Agents.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Survey on Evaluation of LLM-based Agents

Reference 51

Resolution: verified exact; local_arxiv, observed 2026-07-03T16:58:43.696328Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f1cbdb79-344f-42bb-ada9-4c10634f1dfa · outbound

This paper cites Gui agents: A survey,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Gui agents: A survey,

Reference 52

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0255382f-ad9f-4775-920e-01382c99af3f · outbound

This paper cites A survey on vision–language–action models for embodied ai,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design A survey on vision–language–action models for embodied ai,

Reference 53

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eacbeaa1-da2a-48f6-9c17-72f0b7abe9ee · outbound

This paper cites A survey on trustworthy llm agents: Threats and countermeasures,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design A survey on trustworthy llm agents: Threats and countermeasures,

Reference 54

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e6b76a6-0222-4123-a575-23ea398d4538 · outbound

This paper cites Agent harness for large language model agents: A survey,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Agent harness for large language model agents: A survey,

Reference 55

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1620c548-dc2b-4c75-b075-6a6a3ff5b89d · outbound

This paper cites Agent harness engineering: A survey,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Agent harness engineering: A survey,

Reference 56

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e80f71d-1931-439a-aa86-1564d9108f4e · outbound

This paper cites Code as Agent Harness.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Code as Agent Harness

Reference 57

Resolution: verified exact; local_arxiv, observed 2026-07-03T16:58:43.795053Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d868f062-685e-4f3e-9fb7-d96566eae302 · outbound

This paper cites Intelligent agents: Theory and practice,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Intelligent agents: Theory and practice,

Reference 58

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e4db965-2259-4c50-aedd-057ea2bc9829 · outbound

This paper cites Generative agents: Interactive simulacra of human behavior,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Generative agents: Interactive simulacra of human behavior,

Reference 59

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd226497-8354-4536-89f0-e626392271b3 · outbound

This paper cites Autogen: Enabling next-gen llm applications via multi-agent conversations,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Autogen: Enabling next-gen llm applications via multi-agent conversations,

Reference 60

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad1450e7-7528-48d7-a368-a23b2f87fb9e · outbound

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

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Metagpt: Meta program- ming for a multi-agent collaborative framework,

Reference 61

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67030b78-f4f4-45e7-b26c-1198c43532c5 · outbound

This paper cites Large Language Model Guided Tree-of-Thought.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Large Language Model Guided Tree-of-Thought

Reference 62

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T16:58:43.778580Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c1fa79df-c795-43fb-a389-00cb84ca9e8e · outbound

This paper cites Reflexion: Language agents with verbal reinforcement learn- ing,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Reflexion: Language agents with verbal reinforcement learn- ing,

Reference 63

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da3996db-0864-46d5-9637-a2060a4ae770 · outbound

This paper cites Effective harnesses for long-running agents,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Effective harnesses for long-running agents,

Reference 64

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1973f008-0aa1-4e98-ba92-cae7da844925 · outbound

This paper cites Model context protocol,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Model context protocol,

Reference 65

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c8f12d8-5955-4fff-a7c1-4b18b844749c · outbound

This paper cites Agent2agent (a2a,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Agent2agent (a2a,

Reference 66

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c02c64d9-4009-46e6-8afd-5c84e1249e2b · outbound

This paper cites Scaling Laws for Neural Language Models.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Scaling Laws for Neural Language Models

Reference 67

Resolution: verified exact; local_arxiv, observed 2026-07-03T16:58:43.815033Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation dce5347d-ed9b-4f6c-b930-e6c4a41481b0 · outbound

This paper cites Training Compute-Optimal Large Language Models.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Training Compute-Optimal Large Language Models

Reference 68

Resolution: verified exact; local_arxiv, observed 2026-07-03T16:58:43.830684Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d0f0ebe8-85a9-4a7e-95a2-209005b0d666 · outbound

This paper cites Palm: Scaling language modeling with pathways,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Palm: Scaling language modeling with pathways,

Reference 69

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d068976-249f-46a6-9d82-e7b08b33b53d · outbound

This paper cites CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis

Reference 70

Resolution: verified exact; local_arxiv, observed 2026-07-03T16:58:43.821874Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c291034b-5bbf-41b9-98bd-93e53b508a7f · outbound

This paper cites Competition- level code generation with alphacode,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Competition- level code generation with alphacode,

Reference 71

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7bce9e6b-38eb-4c3d-bfca-7320cd8a2a1e · outbound

This paper cites Solving quantitative reasoning problems with language models,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Solving quantitative reasoning problems with language models,

Reference 72

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbbb5c0a-109d-40dd-b2a6-25a4c0e4f22d · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 73

Resolution: verified exact; local_arxiv, observed 2026-07-03T17:08:43.005095Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f8ae1ce5-1a50-4841-bdd1-676e6dc99775 · outbound

This paper cites Flamingo: a visual language model for few-shot learning,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Flamingo: a visual language model for few-shot learning,

Reference 74

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 973f9e5a-d86a-4d96-9929-a772141f0c8d · outbound

This paper cites On scaling up a multilingual vision and language model,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design On scaling up a multilingual vision and language model,

Reference 75

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 492317bc-ec71-4ddd-967d-7dcd9928752c · outbound

This paper cites The Llama 3 Herd of Models.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design The Llama 3 Herd of Models

Reference 76

Resolution: verified exact; local_arxiv, observed 2026-07-03T16:58:43.707231Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e85f5e49-d91c-4d2e-9bde-4b9cf058639d · outbound

This paper cites Is your code generated by chatgpt really correct? rigorous evaluation of large language models for code generation,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Is your code generated by chatgpt really correct? rigorous evaluation of large language models for code generation,

Reference 77

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 422b7c19-2d82-4e9d-ac15-fc683857f187 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Training Verifiers to Solve Math Word Problems

Reference 78

Resolution: verified exact; local_arxiv, observed 2026-07-03T17:08:43.127363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c774dae3-fe47-4753-87d5-de8746833a9d · outbound

This paper cites Measuring Mathematical Problem Solving With the MATH Dataset.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Measuring Mathematical Problem Solving With the MATH Dataset

Reference 79

Resolution: verified exact; local_arxiv, observed 2026-07-03T16:58:43.651190Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0708e5e6-04e4-45f9-bcbf-ac4253b0cf08 · outbound

This paper cites Mmlu-pro: A more robust and challenging multi-task language understanding benchmark,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Mmlu-pro: A more robust and challenging multi-task language understanding benchmark,

Reference 80

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6922a4f7-237f-4cdd-9f10-0cc171491814 · outbound

This paper cites Qwen3 Technical Report.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Qwen3 Technical Report

Reference 81

Resolution: verified exact; local_arxiv, observed 2026-07-03T17:08:43.110700Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f66724d2-7d98-4caa-aa93-3762c17c51c4 · outbound

This paper cites Mmlu-pro leaderboard,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Mmlu-pro leaderboard,

Reference 82

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 086b54b9-1847-40c9-8c16-fa5728db1ada · outbound

This paper cites Gpqa diamond,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Gpqa diamond,

Reference 83

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8040ee2-01c4-48d0-bf21-0555f37aced1 · outbound

This paper cites Swe-agi: Benchmarking specification-driven software construction with moonbit in the era of autonomous agents,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Swe-agi: Benchmarking specification-driven software construction with moonbit in the era of autonomous agents,

Reference 84

Resolution: verified exact; arxiv_id, observed 2026-07-03T16:58:43.797876Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 485faf96-3d5b-4266-97c9-fba29254ea2c · outbound

This paper cites Agent alpha: Tree search unifying generation, exploration and evaluation for computer-use agents.arXiv preprint arXiv:2602.02995.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Agent alpha: Tree search unifying generation, exploration and evaluation for computer-use agents.arXiv preprint arXiv:2602.02995

Reference 85

Resolution: verified exact; arxiv_id, observed 2026-07-03T16:58:43.647753Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7509f3b5-37b6-4ca6-a6fe-5565dbdb3c74 · outbound

This paper cites Featurebench: Benchmarking agentic coding for complex feature development.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Featurebench: Benchmarking agentic coding for complex feature development

Reference 86

Resolution: verified exact; arxiv_id, observed 2026-07-03T16:58:43.775222Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6b4ebee3-bdb7-4bc6-ab9b-9971ece962eb · outbound

This paper cites Turkingbench: A challenge benchmark for web agents,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Turkingbench: A challenge benchmark for web agents,

Reference 87

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3aaa97ae-6aad-4122-b007-25f78e8c8e9a · outbound

This paper cites BEARCUBS: A benchmark for computer-using web agents.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design BEARCUBS: A benchmark for computer-using web agents

Reference 88

Resolution: verified exact; arxiv_id, observed 2026-07-03T17:08:43.103294Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ac74188f-114d-418d-97c0-6dd30932082b · outbound

This paper cites Towards Adaptive ML Benchmarks: Web-Agent-Driven Construction, Domain Expansion, and Metric Optimization.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Towards Adaptive ML Benchmarks: Web-Agent-Driven Construction, Domain Expansion, and Metric Optimization

Reference 89

Resolution: verified exact; arxiv_id, observed 2026-07-03T17:08:43.130648Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 40db96f3-0a1a-401d-a8c0-6d6043db88c4 · outbound

This paper cites From static benchmarks to dynamic protocol: Agent-centric text anomaly detection for evaluating llm reasoning,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design From static benchmarks to dynamic protocol: Agent-centric text anomaly detection for evaluating llm reasoning,

Reference 90

Resolution: verified exact; arxiv_id, observed 2026-07-03T16:58:43.699744Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e5bf09db-3a17-41bc-8e65-5820ee021d31 · outbound

This paper cites Cloud-OpsBench: A Reproducible Benchmark for Agentic Root Cause Analysis in Cloud Systems.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Cloud-OpsBench: A Reproducible Benchmark for Agentic Root Cause Analysis in Cloud Systems

Reference 91

Resolution: verified exact; arxiv_id, observed 2026-07-03T17:08:43.105600Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 81527069-bfad-4aa6-ac4c-909ebab6d78e · outbound

This paper cites Bigcodebench: Benchmarking code generation with diverse function calls and complex instructions,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Bigcodebench: Benchmarking code generation with diverse function calls and complex instructions,

Reference 92

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84d3d853-fdda-40c0-824f-6e3ef8ddaca6 · outbound

This paper cites LiveClawBench: Benchmarking LLM Agents on Complex, Real-World Assistant Tasks.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design LiveClawBench: Benchmarking LLM Agents on Complex, Real-World Assistant Tasks

Reference 93

Resolution: verified exact; local_arxiv, observed 2026-07-03T16:58:43.763767Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 5dfc95db-f400-4807-a57c-b309d5bdc2bf · outbound

This paper cites Multichallenge: A realistic multi-turn conversation evaluation benchmark challenging to frontier llms,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Multichallenge: A realistic multi-turn conversation evaluation benchmark challenging to frontier llms,

Reference 94

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07c2dd7c-4756-4de7-8b88-a6f35787d7dd · outbound

This paper cites Measuring AI Ability to Complete Long Software Tasks.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Measuring AI Ability to Complete Long Software Tasks

Reference 95

Resolution: metadata mismatch; arxiv_id, observed 2026-07-14T01:19:52.953392Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b77ef95e-190c-4ea5-a174-65dfb78e7baa · outbound

This paper cites Large language models are zero-shot reasoners,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Large language models are zero-shot reasoners,

Reference 96

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4975686-e876-471d-b4aa-8b5db4e1be24 · outbound

This paper cites Self-refine: Iterative refinement with self-feedback,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Self-refine: Iterative refinement with self-feedback,

Reference 97

Resolution: unresolved; no resolver link, observed 2026-06-27T04:40:30.985824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 318cc1cc-0f55-434a-9d44-4a811e21d98e · outbound

This paper cites A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications

Reference 98

Resolution: verified exact; local_arxiv, observed 2026-07-03T16:58:43.728078Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e0831e76-4b1f-42f6-8f1c-ae352711b84a · outbound

This paper cites Beyond local code optimization: Multi-agent reasoning for software system optimization,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Beyond local code optimization: Multi-agent reasoning for software system optimization,

Reference 99

Resolution: verified exact; arxiv_id, observed 2026-07-03T17:08:43.095933Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation dc56c47b-e22a-420e-966c-709baa889a58 · outbound

This paper cites Quality-driven agentic reasoning for llm-assisted software design: Questions-of-thoughts (qot) as a time-series self-qa chain,.

From Question Answering to Task Completion: A Survey on Agent System and Harness Design Quality-driven agentic reasoning for llm-assisted software design: Questions-of-thoughts (qot) as a time-series self-qa chain,

Reference 100

Resolution: verified exact; arxiv_id, observed 2026-07-03T16:58:43.735722Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers