Paper Citation Record · LEDGER

EvoHarness-RL: Learning Self-Evolving Runtime Harness for Long-Horizon LLM Agents

As of 16 August 2026, this Paper Citation Record lists 18 of 18 outbound references and 0 inbound Pith citation observations for arXiv:2608.05446.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2608.05446 v1

Coverage vector

measured 18 of 18 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-08T13:01:09.196433Z

measured 18 of 18 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

18 of 18 outbound references displayed

verified exact1
verified fuzzy2
unresolved14
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4a6d7bf9-fd87-4c3e-9e8c-212aec11a419 · outbound

This paper cites HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry.

EvoHarness-RL: Learning Self-Evolving Runtime Harness for Long-Horizon LLM Agents HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-08T13:01:09.109705Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 431a4610-419f-4600-8b9e-a9e9f7df540a · outbound

This paper cites Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses.

EvoHarness-RL: Learning Self-Evolving Runtime Harness for Long-Horizon LLM Agents Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-08-08T13:01:09.644786Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 6dabd5d8-a7ea-4cfc-91c2-9d716bd5c071 · outbound

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

EvoHarness-RL: Learning Self-Evolving Runtime Harness for Long-Horizon LLM Agents Meta-Harness: End-to-End Optimization of Model Harnesses

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-08T13:01:09.126857Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b9c0152-606f-4459-9f0d-3134eba162e5 · outbound

This paper cites A survey of rag-reasoning systems in large language models.

EvoHarness-RL: Learning Self-Evolving Runtime Harness for Long-Horizon LLM Agents A survey of rag-reasoning systems in large language models

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T13:01:09.692569Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 930d7106-d271-4825-9b4c-b59350b8f75f · outbound

This paper cites Code as Agent Harness.

EvoHarness-RL: Learning Self-Evolving Runtime Harness for Long-Horizon LLM Agents Code as Agent Harness

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-08T13:01:09.141829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4c1738e-b185-48b1-92a5-63ea5ae09602 · outbound

This paper cites ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory.

EvoHarness-RL: Learning Self-Evolving Runtime Harness for Long-Horizon LLM Agents ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-08T13:01:09.146993Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96b5fa5c-df1e-4541-85d0-c80679e6c718 · outbound

This paper cites SkillOS: Learning Skill Curation for Self-Evolving Agents.

EvoHarness-RL: Learning Self-Evolving Runtime Harness for Long-Horizon LLM Agents SkillOS: Learning Skill Curation for Self-Evolving Agents

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-08T13:01:09.152575Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bc8883f-c226-4ef3-aa0a-f6e0024a0797 · outbound

This paper cites Agent-BRACE: Decoupling Beliefs from Actions in Long-Horizon Tasks via Verbalized State Uncertainty.

EvoHarness-RL: Learning Self-Evolving Runtime Harness for Long-Horizon LLM Agents Agent-BRACE: Decoupling Beliefs from Actions in Long-Horizon Tasks via Verbalized State Uncertainty

Reference 11

Resolution: metadata mismatch; local_arxiv, observed 2026-08-08T13:01:09.442492Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 706ec058-ff90-4cfe-8301-b448593cea3d · outbound

This paper cites A subgoal-driven framework for improving long-horizon llm agents.arXiv preprint arXiv:2603.19685,.

EvoHarness-RL: Learning Self-Evolving Runtime Harness for Long-Horizon LLM Agents A subgoal-driven framework for improving long-horizon llm agents.arXiv preprint arXiv:2603.19685,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-08T13:01:09.172381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bb76d25-62da-45e2-bac6-db998fb2d110 · outbound

This paper cites Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory.

EvoHarness-RL: Learning Self-Evolving Runtime Harness for Long-Horizon LLM Agents Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-08T13:01:09.177139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b515a26c-3d1f-49a8-a7f4-967ecedeb764 · outbound

This paper cites SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning.

EvoHarness-RL: Learning Self-Evolving Runtime Harness for Long-Horizon LLM Agents SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-08T13:01:09.181843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1b6d065-9a0c-4fb5-9ca0-e6deb3257770 · outbound

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

EvoHarness-RL: Learning Self-Evolving Runtime Harness for Long-Horizon LLM Agents ReAct: Synergizing Reasoning and Acting in Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-08T13:01:09.186739Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75de33ff-6f87-4c6a-ad93-354f26c3dafb · outbound

This paper cites Webarena: A realistic web environment for building autonomous agents.

EvoHarness-RL: Learning Self-Evolving Runtime Harness for Long-Horizon LLM Agents Webarena: A realistic web environment for building autonomous agents

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-08T13:01:09.196433Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4c83c10-5760-403a-aff6-676ea40c811e · outbound

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

EvoHarness-RL: Learning Self-Evolving Runtime Harness for Long-Horizon LLM Agents Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-08T13:01:09.191498Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f52a568-7256-4550-b383-2a385709d1e4 · outbound

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

EvoHarness-RL: Learning Self-Evolving Runtime Harness for Long-Horizon LLM Agents DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-08T13:01:09.157540Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ba7f1c8-168c-4038-acc6-f8e7b536858c · outbound

This paper cites LiveResearchBench: A Live Benchmark for User-Centric Deep Research in the Wild.

EvoHarness-RL: Learning Self-Evolving Runtime Harness for Long-Horizon LLM Agents LiveResearchBench: A Live Benchmark for User-Centric Deep Research in the Wild

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-08T13:01:09.167691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6161676f-4a1d-408d-b284-811ecdf3ac95 · outbound

This paper cites Autoharness: improving llm agents by automatically synthesizing a code harness.arXiv preprint arXiv:2603.03329,.

EvoHarness-RL: Learning Self-Evolving Runtime Harness for Long-Horizon LLM Agents Autoharness: improving llm agents by automatically synthesizing a code harness.arXiv preprint arXiv:2603.03329,

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-08T13:01:09.137056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 387b5da8-8f9a-42ce-9a86-625b7cb2b170 · outbound

This paper cites Memp: Exploring agent procedural memory.

EvoHarness-RL: Learning Self-Evolving Runtime Harness for Long-Horizon LLM Agents Memp: Exploring agent procedural memory

Reference 2026

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T13:01:09.713399Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Pith citing papers

No inbound Pith citation observations are available.