Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

T-Search: An Open Agentic Retriever and Playground for Hard Multi-Step Search

Olga Tsymboi, Ramil Latypov, Aleksandr Medvedev, Danil Taranets +4 more

Published

Oct 5, 2026

Citations

0

Trust level

Low

Usefulness score

25/100 (Low)

Extraction confidence

45% (Low)

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 General 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

The available metadata is too thin to trust this as a primary source.

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

We present T-Search, an open-weight agentic retriever for hard multi-step search. Given a question and a search tool over a fixed corpus, it runs a bounded multi-round search and returns a ranked list of evidence chunks with short justifications, leaving answer generation to a downstream model, so backend and generator can be swapped without retraining. T-Search is built on Qwen3.6-35B-A3B and trained on adversarially filtered synthetic search tasks with round-sliced supervised fine-tuning followed by GSPO on a recall reward. Averaged over seven English and Russian benchmarks with gold evidence annotations, it reaches 56.0 Recall@10 with one rollout, 14.4 points above its base, and 61.3 with three fused rollouts, outperforming larger open models. We release the model, harness, live demo, and three benchmarks, including TRuST, the first native-Russian hard-search benchmark.

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.

"We present T-Search, an open-weight agentic retriever for hard multi-step search."

Evaluation Modes

partial

Automatic Metrics

Includes extracted eval setup.

"We present T-Search, an open-weight agentic retriever for hard multi-step search."

Quality Controls

missing

Not reported

No explicit QC controls found.

"We present T-Search, an open-weight agentic retriever for hard multi-step search."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"We present T-Search, an open-weight agentic retriever for hard multi-step search."

Reported Metrics

partial

Recall, Recall@10

Useful for evaluation criteria comparison.

"T-Search is built on Qwen3.6-35B-A3B and trained on adversarially filtered synthetic search tasks with round-sliced supervised fine-tuning followed by GSPO on a recall reward."

Benchmarks and datasets

No benchmark or dataset names were extracted from the available abstract.

Reported metrics

recallrecall@10
Human feedback details
Uses human feedback
No
Feedback types
None
Rater population
Not reported
Unit of annotation
Ranking (inferred)
Expertise required
General
Evaluation details
Evaluation modes
Automatic Metrics
Agentic eval
Long Horizon
Quality controls
Not reported
Evidence quality
Low
Use this page as
Background context only

Research brief

Metadata summary

We present T-Search, an open-weight agentic retriever for hard multi-step search.

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

Key takeaways

  • We present T-Search, an open-weight agentic retriever for hard multi-step search.
  • Given a question and a search tool over a fixed corpus, it runs a bounded multi-round search and returns a ranked list of evidence chunks with short justifications, leaving answer generation to a downstream model, so backend and generator can be swapped without retraining.
  • T-Search is built on Qwen3.6-35B-A3B and trained on adversarially filtered synthetic search tasks with round-sliced supervised fine-tuning followed by GSPO on a recall reward.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Validate inferred eval signals (Long-horizon tasks) against the full paper.
  • 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

  • We present T-Search, an open-weight agentic retriever for hard multi-step search.
  • Averaged over seven English and Russian benchmarks with gold evidence annotations, it reaches 56.0 Recall@10 with one rollout, 14.4 points above its base, and 61.3 with three fused rollouts, outperforming larger open models.
  • We release the model, harness, live demo, and three benchmarks, including TRuST, the first native-Russian hard-search benchmark.

Why it matters for eval

  • We present T-Search, an open-weight agentic retriever for hard multi-step search.
  • Averaged over seven English and Russian benchmarks with gold evidence annotations, it reaches 56.0 Recall@10 with one rollout, 14.4 points above its base, and 61.3 with three fused rollouts, outperforming larger open models.

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

    No benchmark/dataset anchor extracted from abstract.

  • Metric reporting is present

    Detected: recall, recall@10