EVE-Agent: Evidence-Verifiable Self-Evolving Agents
EVE-Agent introduces evidence verifiability to self-evolving search agents by modifying the proposer–solver framework with an evidence verifier that rewards spans based on marginal accuracy gain. This ensures each training example includes a source-grounded span that explains why it should be trusted, leading to improved evidence-grounded correctness without human annotations.
Article intelligence
Key points
- Self-evolving agents require verifiable evidence in training examples to avoid rewarding unsupported but fluent instances.
- EVE-Agent extends the proposer–solver framework with an evidence verifier that rewards spans based on their contribution to answer accuracy.
- The system generates auditable training data without oracle answers, human labels, or external annotations.
- Experiments show significant improvement in evidence-grounded correctness over previous self-evolving agents.
Why it matters
This matters because self-evolving agents require verifiable evidence in training examples to avoid rewarding unsupported but fluent instances.
Technical impact
May affect model selection, inference cost, product capability, and evaluation benchmarks.
[2605.22905] EVE-Agent: Evidence-Verifiable Self-Evolving Agents
[Submitted on 21 May 2026]
Title:EVE-Agent: Evidence-Verifiable Self-Evolving Agents
View a PDF of the paper titled EVE-Agent: Evidence-Verifiable Self-Evolving Agents, by Yamato Arai and 1 other authors
View PDF HTML (experimental)
Abstract:Self-evolving agents should not train on examples they cannot justify. Data-free self-evolving search agents offer a scalable route to systems that generate their own questions, answer them, and improve from their own feedback without human annotations. Yet, without verifiable evidence, this loop can reward fluent but unsupported examples, turning the self-generated curriculum into an opaque and potentially unreliable training signal. We argue that evidence verifiability is a prerequisite for trustworthy self-evolution in search agents: each generated instance should include not only an answer but also a source-grounded span whose contribution to that answer can be measured. We introduce EVE-Agent, an Evidence-Verifiable Self-Evolving Agent that operationalizes this principle through a modification to the proposer--solver framework. The proposer generates a question, an answer, and a verbatim evidence span. An evidence verifier then rewards the span according to the marginal accuracy gain when the evidence is provided. This produces a training signal that favors evidence that genuinely helps answer the question, without requiring oracle answers, human labels, or external annotations. EVE-Agent leaves the backbone model, retriever, search tool, and optimization framework unchanged. Experiments show that EVE-Agent substantially improves evidence-grounded correctness over prior self-evolving search agents. The resulting curriculum is not merely self-generated but auditable by construction: each training example carries an inspectable source span that explains why it should be trusted.
Comments: 23 pages, 2 figures
Subjects:
Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
Cite as: arXiv:2605.22905 [cs.AI]
(or arXiv:2605.22905v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2605.22905
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Yuma Ichikawa [view email] [v1] Thu, 21 May 2026 17:47:01 UTC (1,888 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled EVE-Agent: Evidence-Verifiable Self-Evolving Agents, by Yamato Arai and 1 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.AI
new | recent | 2026-05
Change to browse by:
cs cs.CL
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)