Paper Citation Record · LEDGER

When Does Memory Help Multi-Trajectory Inference for Tool-Use LLM Agents?

As of 18 August 2026, this Paper Citation Record lists 12 of 12 outbound references and 0 inbound Pith citation observations for arXiv:2605.28224.

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

pith.paper-citation-record.v1
2605.28224 v1

Coverage vector

measured 12 of 12 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-29T12:21:02.155471Z

measured 12 of 12 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+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

12 of 12 outbound references displayed

verified exact1
verified fuzzy0
unresolved10
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ce5d4d22-76f4-41e9-bb08-624d12b663e4 · outbound

This paper cites MemCollab: Cross-Model Memory Collaboration via Contrastive Trajectory Distillation.

When Does Memory Help Multi-Trajectory Inference for Tool-Use LLM Agents? MemCollab: Cross-Model Memory Collaboration via Contrastive Trajectory Distillation

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-06-29T12:23:24.248323Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 981b85ba-6e4f-4e4d-bd89-26bbdcb313d8 · outbound

This paper cites In The Twelfth International Conference on Learning Representations.

When Does Memory Help Multi-Trajectory Inference for Tool-Use LLM Agents? In The Twelfth International Conference on Learning Representations

Reference 2

Resolution: unresolved; no resolver link, observed 2026-06-29T12:21:02.155471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af5e0848-3542-4e1b-9f40-265a20ec8d0b · outbound

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

When Does Memory Help Multi-Trajectory Inference for Tool-Use LLM Agents? Reflexion: Language Agents with Verbal Reinforcement Learning

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-06-29T12:23:24.249899Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation df0a05e9-c00a-4875-affd-2bf9c2952017 · outbound

This paper cites an unresolved cited work.

When Does Memory Help Multi-Trajectory Inference for Tool-Use LLM Agents? Unresolved cited work

Reference 4

Resolution: unresolved; no resolver link, observed 2026-06-29T12:21:02.155471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 903ca64d-d4df-40a2-aed3-3b0510bfa6e5 · outbound

This paper cites an unresolved cited work.

When Does Memory Help Multi-Trajectory Inference for Tool-Use LLM Agents? Unresolved cited work

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-29T12:21:02.155471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8052d518-3145-4c44-9ff0-663ae5909f5b · outbound

This paper cites Re- flection and fact extraction are persistent (g= 1; accumulated across iterations).

When Does Memory Help Multi-Trajectory Inference for Tool-Use LLM Agents? Re- flection and fact extraction are persistent (g= 1; accumulated across iterations)

Reference 6

Resolution: unresolved; no resolver link, observed 2026-06-29T12:21:02.155471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7aa6a085-3922-4c2d-8629-cd73f80bcf00 · outbound

This paper cites an unresolved cited work.

When Does Memory Help Multi-Trajectory Inference for Tool-Use LLM Agents? Unresolved cited work

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-29T12:21:02.155471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8df7177-7e7d-4bb9-b5f7-b0f60811dfcf · outbound

This paper cites These are the examples where tree search and memory have the opportunity to rescue.

When Does Memory Help Multi-Trajectory Inference for Tool-Use LLM Agents? These are the examples where tree search and memory have the opportunity to rescue

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-29T12:21:02.155471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 516f99a3-4ea4-42eb-b350-a844aa956023 · outbound

This paper cites One sampled index (idx=1) overlaps with the initial pilot run and is ex- cluded from the subset command, yielding 9 controls.

When Does Memory Help Multi-Trajectory Inference for Tool-Use LLM Agents? One sampled index (idx=1) overlaps with the initial pilot run and is ex- cluded from the subset command, yielding 9 controls

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-29T12:21:02.155471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ad37300-050c-43bd-890a-3496eb89ff0a · outbound

This paper cites Name the platform for year more than 2006 and developer of 3g studios.

When Does Memory Help Multi-Trajectory Inference for Tool-Use LLM Agents? Name the platform for year more than 2006 and developer of 3g studios

Reference 10

Resolution: unresolved; no resolver link, observed 2026-06-29T12:21:02.155471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84942536-cc41-4a6d-8db3-93c96955de0a · outbound

This paper cites 1. List all tables.

When Does Memory Help Multi-Trajectory Inference for Tool-Use LLM Agents? 1. List all tables

Reference 11

Resolution: unresolved; no resolver link, observed 2026-06-29T12:21:02.155471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4895c409-e38e-42b8-ac85-b5bef51dd358 · outbound

This paper cites The same pattern holds on WikiTQ (70% → 23% skip rate; 49.0%→46.9% pass@5).

When Does Memory Help Multi-Trajectory Inference for Tool-Use LLM Agents? The same pattern holds on WikiTQ (70% → 23% skip rate; 49.0%→46.9% pass@5)

Reference 12

Resolution: unresolved; no resolver link, observed 2026-06-29T12:21:02.155471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.