arXiv Machine Learning
Verifier-Grounded Agentic RL for Provably Correct Code
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
4d ago
Checking the Checkers: A Synthesis of Verifier Noise and Robustness in RLVR
The paper surveys 58 studies on verifier errors in reinforcement learning with verifiable rewards (RLVR), examining how such errors affect training and which mitigations are effective. It finds that the type of error—rather than its frequency—has a larger impact on learning dynamics, with random errors mainly slowing progress and false positives potentially causing learning plateaus or collapse. The authors compile findings into comparison tables, reconcile conflicting reports, and propose a reporting protocol to standardize future research.
arXiv Machine Learning
4d ago
Policy-Verified Self-Training: Learning Agent Compliance from Verifiable Policy Rewards
arXiv:2610.19372v1 Announce Type: new Abstract: Runtime policy verifiers can prevent agents from executing disallowed actions, but their decisions are typically used only for enforcement and discarde...
arXiv AI
Oct 2
Verify Claims, Not Scores: Evidence-Based Verification of Modular Agents
The paper proposes a claim‑specific verification audit for modular agents that replaces aggregate task scores with evidence‑based evaluations. Each agent conclusion is recorded with supporting evidence and classified as supported, unsupported, unresolved, or not evaluated, along with the boundary of validity. The audit employs three tools—oracle policies, perfect component replacements, and verifier‑score tests—to trace value changes, locate lost value, and assess verifier effectiveness, demonstrated on a portfolio‑allocation agent in a synthetic market.
arXiv AI
Jun 30
SEVA: Self-Evolving Verification Agent with Process Reward for Fact Attribution
arXiv:2606. 29713v1 Announce Type: cross Abstract: Hallucination is the reliability bottleneck for LLM-based agents, and fact attribution verifiers are the last line of defense -- yet today's verifiers emit only opaque binary labels, leaving agents unable to self-correct and operators unable to audit.
arXiv Machine Learning
Sep 2
Where the Verifier Fails: A Category-Level Audit of Reward Signals in RLVR
arXiv:2609.01354v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) and standard benchmark evaluation both rely on an automatic verifier that turns a free text ans...
arXiv AI
Jul 21
Self-Modifying Lean Proof Agents with Verifier-Grounded Benchmark Coevolution
arXiv:2607. 17352v1 Announce Type: new Abstract: Designing effective Lean proof agents is a central challenge in formal mathematical reasoning.