Pith. sign in

Paper Citation Record · LEDGER

Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents

As of 23 July 2026, this Paper Citation Record lists 16 of 16 outbound references and 4 inbound Pith citation observations for arXiv:2605.30621.

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

pith.paper-citation-record.v1
2605.30621 v1

Coverage vector

measured 16 of 16 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-29T06:43:21.809704Z

measured 20 of 20 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-07-22T06:31:00.163083+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-14T15:24:58.589243Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-02T23:17:29.011746Z

Reference resolution

16 of 16 outbound references displayed

  • verified exact2
  • verified fuzzy0
  • unresolved13
  • parse uncertain0
  • malformed identifier1
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c1467348-5bf7-4d27-907a-5d3bf6735f92 · outbound

This paper cites gpt-oss-120b & gpt-oss-20b Model Card.

Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents gpt-oss-120b & gpt-oss-20b Model Card

Reference 1

Resolution
verified exact
local_arxiv, observed 2026-06-29T14:23:31.093536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

source=pdf_text observed=2026-06-29T06:43:21.809704Z digest=sha256:0a692cfc941c37f58d6f8c9b985ea888f9b3b8ac34e915247acd7bdcf37a3233

Observation 7a90849e-abaa-45ad-a399-2e06c62509f1 · outbound

This paper cites Measuring Massive Multitask Language Understanding.

Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents Measuring Massive Multitask Language Understanding

Reference 2

Resolution
verified exact
local_arxiv, observed 2026-06-29T14:23:31.096061Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

source=pdf_text observed=2026-06-29T06:43:21.809704Z digest=sha256:e788950ab8bfc4ff4eb97c7b1d9fa381aa744dd32f08b4ab6cf9491b4ba0d96c

Observation 7ec4e8e8-6738-4186-b070-355c8189bcdc · outbound

This paper cites an unresolved cited work.

Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents Unresolved cited work

Reference 3

Resolution
unresolved
no resolver link, observed 2026-06-29T06:43:21.809704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T06:43:21.809704Z digest=sha256:d721c57bd41706ef80b2e520d1c63f1aff7af5fb0bf487e3f0bc4e4cdcff03b1

Observation 3a4e8a2c-c2fd-4fe6-b9a8-82987331a52f · outbound

This paper cites Collectively, these methods show that writing execution experience back into persistent harness components can improve downstream task perfor- mance.

Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents Collectively, these methods show that writing execution experience back into persistent harness components can improve downstream task perfor- mance

Reference 4

Resolution
malformed identifier
no resolver link, observed 2026-06-29T06:43:21.809704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T06:43:21.809704Z digest=sha256:fe4904b1f949a49fb9db67686909e7484cd85a80ccd1fdbc701c0e8524067953

Observation d836bcf1-f139-43b6-9fb9-a44b09dac85f · outbound

This paper cites Identify the root cause.

Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents Identify the root cause

Reference 5

Resolution
unresolved
no resolver link, observed 2026-06-29T06:43:21.809704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T06:43:21.809704Z digest=sha256:23a9018e2a294ff8c448d9c73b4000c9c55f22d1eb5a4de8b2f34f15a27e6a42

Observation ed888a2d-4966-49a4-8d35-f33a6d7c0378 · outbound

This paper cites an unresolved cited work.

Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents Unresolved cited work

Reference 6

Resolution
unresolved
no resolver link, observed 2026-06-29T06:43:21.809704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T06:43:21.809704Z digest=sha256:758874fc5799267ad7b180f8c623d93ab018f679db4bc3d6eac76f020dc3bb6d

Observation bf22fdb5-12e5-4226-9cd7-eaa6193c0626 · outbound

This paper cites an unresolved cited work.

Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents Unresolved cited work

Reference 7

Resolution
unresolved
no resolver link, observed 2026-06-29T06:43:21.809704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T06:43:21.809704Z digest=sha256:63df0796a98c0bb9005d4b08282356c757fcc243a9cd08d69523d5d05ba0c19e

Observation 434988a4-48cf-4c0e-bfb7-2ff99cffd0b8 · outbound

This paper cites Avoid unnecessary changes.

Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents Avoid unnecessary changes

Reference 8

Resolution
unresolved
no resolver link, observed 2026-06-29T06:43:21.809704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T06:43:21.809704Z digest=sha256:b03318d2a2f4510de4087e45fb75a1f41ef2ffd226be4a3ce1b142ee5bec3676

Observation d4154b94-e5bd-4a61-8578-1f7e36ee8aea · outbound

This paper cites Guidelines • Prefer small, focused patches over large rewrites.

Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents Guidelines • Prefer small, focused patches over large rewrites

Reference 9

Resolution
unresolved
no resolver link, observed 2026-06-29T06:43:21.809704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T06:43:21.809704Z digest=sha256:4c1ee0abe539f9ea6a56aa1105d98649825256a9dbfd58ed1ec5f090c0219565

Observation cf5d9b83-85a8-4e94-a319-a20fbd17d1d4 · outbound

This paper cites an unresolved cited work.

Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents Unresolved cited work

Reference 10

Resolution
unresolved
no resolver link, observed 2026-06-29T06:43:21.809704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T06:43:21.809704Z digest=sha256:cbaceae3f1d2163fb2d76a772a6b4126710dda81c9ef6907417ec000f71a9fb8

Observation dda05883-02ce-4e56-a778-db4db087a4d6 · outbound

This paper cites an unresolved cited work.

Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents Unresolved cited work

Reference 11

Resolution
unresolved
no resolver link, observed 2026-06-29T06:43:21.809704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T06:43:21.809704Z digest=sha256:43c64e472d14b5e312fbcbd52e3382992305526fca5398ef1f2cdcfb10488ae3

Observation 558bc399-fd06-4d30-985d-1a7b4d311022 · outbound

This paper cites an unresolved cited work.

Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents Unresolved cited work

Reference 12

Resolution
unresolved
no resolver link, observed 2026-06-29T06:43:21.809704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T06:43:21.809704Z digest=sha256:91078b54a3cb8e1156a020cbfbdc71c1f8e7eb0bafcb1d295ca39d6c998d41ba

Observation 51e8f805-fb35-4943-93ce-f6887d86c53e · outbound

This paper cites an unresolved cited work.

Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents Unresolved cited work

Reference 13

Resolution
unresolved
no resolver link, observed 2026-06-29T06:43:21.809704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T06:43:21.809704Z digest=sha256:f8d5c82038e1fe726271ecd155a8a83353d62cfc64d82891fe87b42f4ee8c2a4

Observation 742edefc-7951-43bf-9ee5-ceaf256e7d56 · outbound

This paper cites Guidelines • NEVER ask the user for clarification.

Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents Guidelines • NEVER ask the user for clarification

Reference 14

Resolution
unresolved
no resolver link, observed 2026-06-29T06:43:21.809704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T06:43:21.809704Z digest=sha256:674db987f504e75c5d482771c2b839732573baff1132aa1ffa40200ec522de4a

Observation 53b912e6-da10-4487-8602-d637beb67e00 · outbound

This paper cites Do NOT extract advice, rationale, examples, or motivational text as instructions.

Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents Do NOT extract advice, rationale, examples, or motivational text as instructions

Reference 15

Resolution
unresolved
no resolver link, observed 2026-06-29T06:43:21.809704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T06:43:21.809704Z digest=sha256:e94f0b8b34a3bc48cc0405d1a37df1e38ab277a4a39ed7886a7d65d5ea594e31

Observation af7e07d8-e4be-48a1-97c6-fd1a882d1e0f · outbound

This paper cites required.

Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents required

Reference 16

Resolution
unresolved
no resolver link, observed 2026-06-29T06:43:21.809704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T06:43:21.809704Z digest=sha256:ea0eead664d83a253af23784cd146182d479b18ddde291543e137c134acddba0

Pith citing papers

Observation 531d4321-1204-48e2-9b14-f8defae62d3e · inbound

Think-Before-Speak: From Internal Evaluation to Public Expression in Multi-Agent Social Simulation cites this paper.

Think-Before-Speak: From Internal Evaluation to Public Expression in Multi-Agent Social Simulation Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents

Reference 22

Resolution
verified exact
local_arxiv, observed 2026-07-02T23:17:29.012969Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

source=pdf_text observed=2026-07-02T23:10:03.733636Z digest=sha256:a41f093f52325b5d2cc240bdaa16b2aac1fdc18f6ee8440024013a2571bf81b0

Observation 40f4d06d-fa90-40d7-861a-d64ed6ffe6c6 · inbound

Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading cites this paper.

Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents

Reference 20

Resolution
unresolved
no resolver link, observed 2026-07-13T05:28:45.311405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-13T05:28:45.311405Z digest=sha256:f51dcde87852e1f167dc39a34079eb37e7eaada432c04c0714f7dab94fe4e7a7

Observation 0c9ae61e-4b22-4b12-af30-28b97b755bc4 · inbound

Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading cites this paper.

Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents

Reference 20

Resolution
unresolved
no resolver link, observed 2026-07-14T15:24:58.589243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-14T15:24:58.589243Z digest=sha256:0a6ef274ac8cdf380af8a2c4b32201d5691094e92632dc446eb3cb72c2eca490

Observation 1eeaea7d-b7f7-454a-b656-e3ac906d4b62 · inbound

ToFu: A White-Box, Token-Efficient Agent Harness for Researchers cites this paper.

ToFu: A White-Box, Token-Efficient Agent Harness for Researchers Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents

Reference 48

Resolution
unresolved
no resolver link, observed 2026-07-14T05:42:00.932045Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-14T05:42:00.932045Z digest=sha256:92117e16443cd91bab54941f0677490aab850c5f2b23d7ec3c490e4df24ec836