Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

SelfSearch: Reward-Free Search for Self-Improving Agents

Jungwoo Yang, In Jin Kong, Yohan Jo

Published

Sep 29, 2026

Citations

0

Trust level

Low

Usefulness score

5/100 (Low)

Extraction confidence

45% (Low)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Sep 29, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Tags

Automatic Metrics

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 benchmark-and-metrics comparison anchor.

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
5/100
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

Advances in the coding capabilities of LLM agents allow them to inspect and modify their own instructions, tools, and execution procedures. Existing approaches use this ability to search for improved agents through repeated downstream evaluation, which incurs substantial costs and ties the search to the evaluated tasks. We introduce \textbf{SelfSearch}, a reward-free search procedure in which agents modify themselves using records of previous self-improvement episodes. These records capture the reasoning, tool actions, and outcomes of earlier modification attempts, providing concrete experience for improving both task solving and self-modification. Without downstream reward signals during search, SelfSearch improves population-mean success over the initial agent in all six model--benchmark settings, with individual agents gaining up to 11.2 percentage points on Terminal-Bench 2.1. On SWE-bench Multilingual, an agent improves success by \textbf{5.0} percentage points while reducing execution cost by \textbf{38.5}\% on tasks solved by both the initial and evolved agents. SelfSearch achieves competitive task success with evaluation-guided search baselines at lower search cost. With only \textbf{\$4.03} in search cost, it produces a harness that solves \textbf{82.0}\% of Terminal-Bench 2.1 tasks with DeepSeek V4 Flash under the settings of a public nine-harness comparison, matching the top-scoring harness, Codex. These results suggest that experience gained through self-modification can improve agents' downstream capabilities and efficiency.

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.

"Advances in the coding capabilities of LLM agents allow them to inspect and modify their own instructions, tools, and execution procedures."

Evaluation Modes

partial

Automatic Metrics

Includes extracted eval setup.

"Advances in the coding capabilities of LLM agents allow them to inspect and modify their own instructions, tools, and execution procedures."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Advances in the coding capabilities of LLM agents allow them to inspect and modify their own instructions, tools, and execution procedures."

Benchmarks / Datasets

partial

SWE Bench, Terminal Bench

Useful for quick benchmark comparison.

"Without downstream reward signals during search, SelfSearch improves population-mean success over the initial agent in all six model--benchmark settings, with individual agents gaining up to 11.2 percentage points on Terminal-Bench 2.1."

Reported Metrics

partial

Task success

Useful for evaluation criteria comparison.

"SelfSearch achieves competitive task success with evaluation-guided search baselines at lower search cost."

Benchmarks and datasets

SWE-benchTerminal-Bench

Reported metrics

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

Research brief

Metadata summary

Advances in the coding capabilities of LLM agents allow them to inspect and modify their own instructions, tools, and execution procedures.

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

Key takeaways

  • Advances in the coding capabilities of LLM agents allow them to inspect and modify their own instructions, tools, and execution procedures.
  • Existing approaches use this ability to search for improved agents through repeated downstream evaluation, which incurs substantial costs and ties the search to the evaluated tasks.
  • We introduce \textbf{SelfSearch}, a reward-free search procedure in which agents modify themselves using records of previous self-improvement episodes.

Researcher actions

  • Compare this paper against others mentioning SWE-bench.
  • 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

SWE-bench

Contribution summary

  • Advances in the coding capabilities of LLM agents allow them to inspect and modify their own instructions, tools, and execution procedures.
  • Existing approaches use this ability to search for improved agents through repeated downstream evaluation, which incurs substantial costs and ties the search to the evaluated tasks.
  • We introduce SelfSearch, a reward-free search procedure in which agents modify themselves using records of previous self-improvement episodes.

Why it matters for eval

  • Advances in the coding capabilities of LLM agents allow them to inspect and modify their own instructions, tools, and execution procedures.
  • We introduce SelfSearch, a reward-free search procedure in which agents modify themselves using records of previous self-improvement episodes.

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: SWE-bench, Terminal-Bench

  • Metric reporting is present

    Detected: task success