Paper Citation Record · LEDGER

Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0

As of 7 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 0 inbound Pith citation observations for arXiv:2607.14004.

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

pith.paper-citation-record.v1
2607.14004 v1

Coverage vector

measured 33 of 33 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T03:07:01.736890Z

measured 33 of 33 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+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

33 of 33 outbound references displayed

verified exact0
verified fuzzy0
unresolved33
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation b39a6960-0658-4aa4-b918-381b484ee6a3 · outbound

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

Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0 GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T03:06:57.655149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4316c8be-730e-42d9-99d1-e67e13b3d517 · outbound

This paper cites Claude code.https://www.anthropic.com/claude-code, 2025.

Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0 Claude code.https://www.anthropic.com/claude-code, 2025

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T03:06:57.805283Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b70666a3-86c8-4a7a-b7e0-36c6733e35b0 · outbound

This paper cites Dreaming.https://platform.claude.com/docs/en/managed-agents/dreams,.

Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0 Dreaming.https://platform.claude.com/docs/en/managed-agents/dreams,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T03:06:57.996291Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a2fd03c-f95b-409d-b32d-2344276bcee5 · outbound

This paper cites HALO: An RLM-based automatic agent optimization loop.https://github.com/ context-labs/halo, 2026.

Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0 HALO: An RLM-based automatic agent optimization loop.https://github.com/ context-labs/halo, 2026

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T03:06:58.397629Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62c571e3-1f7d-4b2c-a117-a9b290aed180 · outbound

This paper cites Harbor: A framework for evaluating and optimizing agents and models in container environments, 2026.

Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0 Harbor: A framework for evaluating and optimizing agents and models in container environments, 2026

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T03:06:58.521041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf14ea6f-95c9-4a2c-b27e-12352003cc63 · outbound

This paper cites Karpathy.

Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0 Karpathy

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T03:06:58.655378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 463ab879-ae17-49bd-b296-a3721cd1d6d8 · outbound

This paper cites DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines.

Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0 DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T03:06:58.809844Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81497779-d164-4e2c-92a4-2679e1741035 · outbound

This paper cites Overcoming catastrophic forgetting in neural networks.

Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0 Overcoming catastrophic forgetting in neural networks

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T03:06:59.001551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbb44bc6-537e-4bdb-9048-1ed77038712a · outbound

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

Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0 Meta-Harness: End-to-End Optimization of Model Harnesses

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T03:06:59.116346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d19b858-6539-418b-893f-01a7fa5e628c · outbound

This paper cites Letta (formerly MemGPT): Stateful agents with long-term memory.https://github.com/ letta-ai/letta, 2023.

Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0 Letta (formerly MemGPT): Stateful agents with long-term memory.https://github.com/ letta-ai/letta, 2023

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T03:06:59.192854Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 222ab042-8d71-4ec4-8010-167b7c402aad · outbound

This paper cites Combee: Scaling Prompt Learning for Self-Improving Language Model Agents.

Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0 Combee: Scaling Prompt Learning for Self-Improving Language Model Agents

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T03:06:59.275957Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 306dd607-a383-4f35-86f2-29008544f4ef · outbound

This paper cites Motus.https://github.com/lithos-ai/motus, 2026.

Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0 Motus.https://github.com/lithos-ai/motus, 2026

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T03:06:59.359190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d9831da-640e-45ef-b372-bef73337ce29 · outbound

This paper cites Categorizing Variants of Goodhart's Law.

Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0 Categorizing Variants of Goodhart's Law

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T03:06:59.462591Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8454bd5-5a8d-446f-92ba-d1786c4a6d98 · outbound

This paper cites mem0: Memory layer for AI agents.https://github.com/mem0ai/mem0, 2024.

Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0 mem0: Memory layer for AI agents.https://github.com/mem0ai/mem0, 2024

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T03:06:59.575218Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab1de30e-1af7-40a2-acf2-3d944f9268b3 · outbound

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

Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0 Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T03:06:59.716514Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c959f2d0-c04f-4f95-b137-68a3e5925186 · outbound

This paper cites Hermes.https://github.com/nousresearch/hermes-agent, 2026.

Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0 Hermes.https://github.com/nousresearch/hermes-agent, 2026

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T03:06:59.832023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca8c73d7-ad73-4b7c-be5d-4c3644a95168 · outbound

This paper cites Codex.https://openai.com/index/introducing-codex/, 2025.

Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0 Codex.https://openai.com/index/introducing-codex/, 2025

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T03:06:59.983768Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d5d6830-e951-4b4f-b5bb-8e1d115ef81e · outbound

This paper cites Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs.

Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0 Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T03:07:00.083970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60b2eb1f-2bea-4948-beb2-df2a2f36e895 · outbound

This paper cites Generalizing Verifiable Instruction Following.

Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0 Generalizing Verifiable Instruction Following

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T03:07:00.201320Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43f1767b-9f51-4eba-b23b-301d893ba9f3 · outbound

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

Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0 DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T03:07:00.333315Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2efb186-9e8d-43bc-a706-ac7b81613cf2 · outbound

This paper cites Reflexion: Language Agents with Verbal Reinforcement Learning.

Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0 Reflexion: Language Agents with Verbal Reinforcement Learning

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T03:07:00.458580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 402e3873-8f1c-463f-b92d-20cf2219e28b · outbound

This paper cites Tannyhill.

Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0 Tannyhill

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T03:07:00.559956Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f4aef0e-c401-445d-9ee0-02d27f2115a0 · outbound

This paper cites Maestro: Joint Graph & Config Optimization for Reliable AI Agents.

Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0 Maestro: Joint Graph & Config Optimization for Reliable AI Agents

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T03:07:00.673765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32f92bda-f1d3-4d97-8336-cff93dfc2554 · outbound

This paper cites an unresolved cited work.

Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0 Unresolved cited work

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-02T03:07:00.789351Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60763ea9-a45b-4757-98ca-44cc5804728f · outbound

This paper cites Zhang, B.

Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0 Zhang, B

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-02T03:07:00.923650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60d31c03-edbb-44ab-b3c9-a35344bb92c8 · outbound

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

Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0 Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-02T03:07:01.058753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2230fba-9fd8-43ce-a456-401183cdfa1a · outbound

This paper cites TerminusKira.

Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0 TerminusKira

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-02T03:07:01.220940Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14de4084-fcd0-45a0-84d6-1be8ae85efe4 · outbound

This paper cites an unresolved cited work.

Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0 Unresolved cited work

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-02T03:07:01.358806Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c922a1db-a993-4790-9df0-cd5017e20494 · outbound

This paper cites an unresolved cited work.

Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0 Unresolved cited work

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-02T03:07:01.486922Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation daf65cd2-c119-49bb-9fe5-93a0f1a1c676 · outbound

This paper cites an unresolved cited work.

Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0 Unresolved cited work

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-02T03:07:01.589192Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 307f4af3-8261-4cd5-a2e7-e1240028d8d5 · outbound

This paper cites an unresolved cited work.

Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0 Unresolved cited work

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-02T03:07:01.689132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a63b6cf7-394b-429b-918d-5cca9547db86 · outbound

This paper cites an unresolved cited work.

Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0 Unresolved cited work

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-02T03:07:01.736890Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8f69650-fa5c-4578-bb92-d70e4ec09eb4 · outbound

This paper cites an unresolved cited work.

Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0 Unresolved cited work

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-02T03:06:58.198693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.