Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

Write Once, Check Many: Reusable Ledgers for Post-Hoc Policy Compliance Auditing of Agent Trajectories

Ashwin Nagarajan, Gursimran Panesar, Alicia Yang, Mona T. Diab +2 more

Published

Oct 17, 2026

Citations

0

Trust level

Low

Usefulness score

0/100 (Low)

Extraction confidence

30% (Low)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Oct 17, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Tags

Long Horizon

Should you rely on this paper?

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Use this as background context only. Do not make protocol decisions from this page alone.

Best use

Background context only

Use if you need

A secondary eval reference to pair with stronger protocol papers.

What to verify

Validate the evaluation procedure and quality controls in the full paper before operational use.

Main weakness

This paper looks adjacent to evaluation work, but not like a strong protocol reference.

Human feedback signal
Not explicit
Not explicit in abstract metadata
Evaluation signal
Detected
Eval setup described
Usefulness for eval research
0/100
Adjacent candidate

Treat as adjacent context, not a core eval-method reference.

If you are doing eval pipeline work, start here

Human Eval Papers LLM-as-Judge Papers Pairwise Preference Papers Tool-Use Evaluation Search

Abstract

Auditing LLM agents against policies is critical to ensure safety but requires rereading long trajectories once per policy. Can we instead record each trajectory once and reuse that record for policies not known in advance? We propose write once, check many, a framework in which a writer model converts each agent trajectory into a policy-independent ledger of the agent's actions and outcomes. A reader then checks each new policy against the ledger alone, without access to the original trajectory. On 900 trajectories from SHADE-Arena, $τ$-bench, and $τ^2$-bench, we show that a 12B reader of narrative ledgers can either match or in fact achieve higher AUC than the same 12B model reading full trajectories. On SHADE-Arena policies that combine several facts, our approach outperforms a 31B model reading the trajectory (.777 vs. .713 AUC). When checking eight SHADE-Arena policies separately, ledgers use about $5\times$ fewer tokens, including the cost of writing them. A deeper analysis shows that rule-based extraction performs better on some single-action policies, and ledgers can miss evidence in long tool outputs and message contents. Our results suggest that reusable, policy-independent records can make retrospective agent auditing more efficient and effective, and highlight important considerations in ledger design.

What we could verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

missing

None explicit

No explicit feedback protocol extracted.

"Auditing LLM agents against policies is critical to ensure safety but requires rereading long trajectories once per policy."

Evaluation Modes

missing

None explicit

Validate eval design from full paper text.

"Auditing LLM agents against policies is critical to ensure safety but requires rereading long trajectories once per policy."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Auditing LLM agents against policies is critical to ensure safety but requires rereading long trajectories once per policy."

Benchmarks / Datasets

partial

LMSYS Chatbot Arena, Shade Arena

Useful for quick benchmark comparison.

"On 900 trajectories from SHADE-Arena, $τ$-bench, and $τ^2$-bench, we show that a 12B reader of narrative ledgers can either match or in fact achieve higher AUC than the same 12B model reading full trajectories."

Reported Metrics

missing

Not extracted

No metric anchors detected.

"Auditing LLM agents against policies is critical to ensure safety but requires rereading long trajectories once per policy."

Benchmarks and datasets

LMSYS Chatbot ArenaShade-Arena

Reported metrics

No metric terms were extracted from the available abstract.

Human feedback details
Uses human feedback
No
Feedback types
None
Rater population
Not reported
Unit of annotation
Trajectory (inferred)
Expertise required
General
Evaluation details
Evaluation modes
None
Agentic eval
Long Horizon
Quality controls
Not reported
Evidence quality
Low
Use this page as
Background context only

Research brief

Metadata summary

Auditing LLM agents against policies is critical to ensure safety but requires rereading long trajectories once per policy.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key takeaways

  • Auditing LLM agents against policies is critical to ensure safety but requires rereading long trajectories once per policy.
  • Can we instead record each trajectory once and reuse that record for policies not known in advance?
  • We propose write once, check many, a framework in which a writer model converts each agent trajectory into a policy-independent ledger of the agent's actions and outcomes.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Check the full text for explicit evaluation design choices (raters, protocol, and metrics).
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended queries

Contribution summary

  • Auditing LLM agents against policies is critical to ensure safety but requires rereading long trajectories once per policy.
  • We propose write once, check many, a framework in which a writer model converts each agent trajectory into a policy-independent ledger of the agent's actions and outcomes.
  • On 900 trajectories from SHADE-Arena, τ-bench, and τ^2-bench, we show that a 12B reader of narrative ledgers can either match or in fact achieve higher AUC than the same 12B model reading full trajectories.

Why it matters for eval

  • Auditing LLM agents against policies is critical to ensure safety but requires rereading long trajectories once per policy.
  • We propose write once, check many, a framework in which a writer model converts each agent trajectory into a policy-independent ledger of the agent's actions and outcomes.

Researcher checklist

  • Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Evaluation mode is explicit

    No clear evaluation mode extracted.

  • Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Benchmark or dataset anchors are present

    Detected: LMSYS Chatbot Arena, Shade-Arena

  • Metric reporting is present

    No metric terms extracted.