Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

Programmatic Search Agents: Extending Agentic Search Beyond Query Reformulation

Jiaming Qian, Huiyan Yang, Mandi Liu, Jie Liu +6 more

Published

Oct 5, 2026

Citations

0

Trust level

Moderate

Usefulness score

25/100 (Low)

Extraction confidence

55% (Moderate)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Oct 5, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Tags

Automatic Metrics Coding 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 for comparison and orientation, not as your only source.

Best use

Background context only

Use if you need

A benchmark-and-metrics comparison anchor.

What to verify

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

Main weakness

No major weakness surfaced.

Human feedback signal
Not explicit
Not explicit in abstract metadata
Evaluation signal
Detected
Eval setup described
Usefulness for eval research
25/100
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

Search agents adapt their queries, yet fixed search interfaces leave candidate processing and evidence presentation outside the agent's direct control. Our trajectory analysis shows that supporting passages can be retrieved yet never delivered to the agent; a same-page oracle intervention shows that changing the returned evidence can reduce subsequent search. We introduce Programmatic Search Agent (PSA), which makes a local executable computation over candidates the unit of a search action. PSA unifies a persistent candidate workspace, flexible primitive composition, and selective evidence presentation. It incrementally generates program cells that reuse candidates, execute dependent operations, and select what the agent inspects next. The runtime resolves specified data dependencies within each cell, while the agent adapts its search strategy across cells as new evidence arrives. We compare PSA with the Query-based Agent and Tool-based Agent on InfoSeek-Eval and BrowseComp-Plus using five policy backbones without task-specific training. All three interfaces share the search substrate, and the Tool-based Agent also shares PSA's primitives and persistent workspace. Relative to the Query-based Agent, PSA improves macro-averaged task success by 4.00 and 7.56 percentage points on the two benchmarks, respectively; within-backbone reductions in final-step tokens average 28.3% and 33.9%. These results support extending agent control beyond query reformulation to the processing and presentation of retrieved evidence. Code will be released subject to approval.

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.

"Search agents adapt their queries, yet fixed search interfaces leave candidate processing and evidence presentation outside the agent's direct control."

Evaluation Modes

strong

Automatic Metrics

Includes extracted eval setup.

"Search agents adapt their queries, yet fixed search interfaces leave candidate processing and evidence presentation outside the agent's direct control."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Search agents adapt their queries, yet fixed search interfaces leave candidate processing and evidence presentation outside the agent's direct control."

Benchmarks / Datasets

strong

BrowseComp, Infoseek Eval

Useful for quick benchmark comparison.

"We compare PSA with the Query-based Agent and Tool-based Agent on InfoSeek-Eval and BrowseComp-Plus using five policy backbones without task-specific training."

Reported Metrics

strong

Task success

Useful for evaluation criteria comparison.

"Relative to the Query-based Agent, PSA improves macro-averaged task success by 4.00 and 7.56 percentage points on the two benchmarks, respectively; within-backbone reductions in final-step tokens average 28.3% and 33.9%."

Benchmarks and datasets

BrowseCompInfoseek-Eval

Reported metrics

task success
Human feedback details
Uses human feedback
No
Feedback types
None
Rater population
Not reported
Unit of annotation
Trajectory
Expertise required
Coding
Evaluation details
Evaluation modes
Automatic Metrics
Agentic eval
Long Horizon
Quality controls
Not reported
Evidence quality
Moderate
Use this page as
Background context only

Research brief

Metadata summary

Search agents adapt their queries, yet fixed search interfaces leave candidate processing and evidence presentation outside the agent's direct control.

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

Key takeaways

  • Search agents adapt their queries, yet fixed search interfaces leave candidate processing and evidence presentation outside the agent's direct control.
  • Our trajectory analysis shows that supporting passages can be retrieved yet never delivered to the agent; a same-page oracle intervention shows that changing the returned evidence can reduce subsequent search.
  • We introduce Programmatic Search Agent (PSA), which makes a local executable computation over candidates the unit of a search action.

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

  • Search agents adapt their queries, yet fixed search interfaces leave candidate processing and evidence presentation outside the agent's direct control.
  • We introduce Programmatic Search Agent (PSA), which makes a local executable computation over candidates the unit of a search action.
  • Relative to the Query-based Agent, PSA improves macro-averaged task success by 4.00 and 7.56 percentage points on the two benchmarks, respectively; within-backbone reductions in final-step tokens average 28.3% and 33.9%.

Why it matters for eval

  • We introduce Programmatic Search Agent (PSA), which makes a local executable computation over candidates the unit of a search action.
  • Relative to the Query-based Agent, PSA improves macro-averaged task success by 4.00 and 7.56 percentage points on the two benchmarks, respectively; within-backbone reductions in final-step tokens average 28.3% and 33.9%.

Researcher checklist

  • Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Evaluation mode is explicit

    Detected: Automatic Metrics

  • Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Benchmark or dataset anchors are present

    Detected: BrowseComp, Infoseek-Eval

  • Metric reporting is present

    Detected: task success