VERPO: Verified Evidence Regularized Policy Optimization

• URL: http://arxiv.org/abs/2609.06100v1
• Date: Sat, 05 Sep 2026 13:52:18 GMT
• Title: VERPO: Verified Evidence Regularized Policy Optimization
• Abstract summary: Verifiable outcome rewards guide language-model post-training, but sequence-level advantages do not identify which token-level decisions should be preserved or revised.<n>We introduce VERPO, a Verified Evidence Regularized Policy Optimization framework.<n>It separates evidence-free reference restoration from signed token-level evidence corrections.
• Score: 14.40177244052392
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Verifiable outcome rewards guide language-model post-training, but sequence-level advantages do not identify which token-level decisions should be preserved or revised. Evidence-conditioned Teachers provide denser supervision by replaying sampled trajectories with privileged feedback. Yet indiscriminate imitation risks transferring formatting or reasoning-style shifts that do not support task success. We introduce VERPO, a Verified Evidence Regularized Policy Optimization framework that treats evidence as a proposal for policy correction while retaining the outcome objective. It separates evidence-free reference restoration from signed token-level evidence corrections. Fisher Evidence Contrast attenuates corrections along an estimated evidence-presence direction. A stopped token-wise ZPD controller scales acceptance according to local reward alignment and Fisher movement cost, while the reference channel remains independent of acceptance. Across five scientific-reasoning and tool-use tasks, the best variant on each backbone exceeds the strongest compared baseline in average score. The averages rise from 0.6826 to 0.6857 on Qwen3-4B, from 0.6895 to 0.7058 on Qwen3-8B, and from 0.4751 to 0.5657 on Llama-3.2-1B.

Related papers

• Candidate Comparability Before Promotion: Conditional Validation in Adaptive Network Intrusion Detection [0.0]
  Promotion is security-relevant because it changes the model responsible for subsequent attack detection.<n>We test dependence on CICIDS 2017, UNSW-NB15 and ToN-IoT with self-contained challenger pipelines.<n>Raising nominal candidate evidence from 512 to 2,000 samples per class improved promotion under pool-constructed progressive drift by +0.53, +1.67 and +0.38.
  arXiv  Detail & Related papers  (2026-09-03T18:55:09Z)
• FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience [18.64380706071327]
  FlowBalance is a verifier-grounded self-improvement method that learns a normalized distribution over complete responses.<n>For each on-policy trajectory, a frozen training-time view of the same policy uses privileged context to produce token-level log-probability gains.<n>Our analysis establishes within-group contrast preservation, a minimum-change reverse-KL characterization, monotonic verifier control of target reward, and an exact correction against false-positive self-guidance on rejected responses.
  arXiv  Detail & Related papers  (2026-09-03T00:47:11Z)
• PLC-DPO: Posterior Label Correction in Noisy and Ambiguous Preference Optimization [40.91256615677526]
  We propose Posterior Label Correction DPO to robustly optimize preferences.<n>Key idea is to use the policy-reference margin as online evidence to take appropriate correction actions.<n>PLC-DPO obtains the best mean win rate against DPO (60.5 vs. 55.5 for the next-best method)
  arXiv  Detail & Related papers  (2026-08-31T11:11:33Z)
• Cross-Fitted Residual Utility for Primary-Preserving Cognitive Decision Correction in Automatic Modulation Classification [1.547549252134621]
  We study a post-inference problem through cross-fitted residual utility and a primary-preserving cognitive decision policy.<n>A structured KAN-Fourier classifier supplies the default probability, while neural and non-neural candidates provide observable evidence.<n>On RMLA, RMLB, and HISAR, the complete system improves overall accuracy from 63.632% to 66.332%, 65.161% to 66.168%, and 77.769% to 79.867%.
  arXiv  Detail & Related papers  (2026-08-03T11:07:37Z)
• SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute [62.3458279176813]
  Self-Verifying Refinement is an oracle-free multi-turn reinforcement learning framework.<n>It learns to use self-verification as a compute-control policy.<n>It achieves a macro-average accuracy of 0.563 with only 2.99 inference turns on average.
  arXiv  Detail & Related papers  (2026-07-30T16:20:58Z)
• ContainmentBench: Trace-Based Evaluation of Post-Injection Containment in Tool-Using LLM Agents [4.018837636907658]
  We introduce a sandboxed, trace-based benchmark that measures benchmark-defined endpoint policy compliance.<n>We find that aggregate logged-spread rankings change with evidence-stage composition and denominator choice.<n>These results show that a terminal policy label is not a sufficient statistic for operational post-exposure containment.
  arXiv  Detail & Related papers  (2026-07-27T04:51:20Z)
• H$^2$SD: Hybrid Hindsight Self-Distillation [61.71131241473028]
  Reinforcement learning with verifiable rewards (RLVR) provides reliable outcome supervision for language model reasoning.<n>Existing self-distillation methods add a privileged teacher but typically assign it a fixed role.<n>We introduce Hybrid Hindsight Self-Distillation ($mathrmH2mathrmSD$), which jointly adapts teacher context and update strategy to trajectory correctness.
  arXiv  Detail & Related papers  (2026-07-21T10:47:27Z)
• VeriGate: Verifier-Gated Step-Level Supervision for GRPO [51.26100506256885]
  Group Relative Policy Optimization is an effective recipe for training reasoning models with verifier-based outcome rewards.<n>We present VeriGate, a verifier-gated extension of GRPO that addresses these limitations with three design choices.<n>We show that VeriGate improves average accuracy by about 20% and 12% for 1.5B and 7B models respectively.
  arXiv  Detail & Related papers  (2026-05-28T18:20:32Z)
• One-Way Policy Optimization for Self-Evolving LLMs [63.8638342097375]
  Reinforcement Learning with Verifiable Rewards (RLVR) has become a promising paradigm for scaling reasoning capabilities of Large Language Models (LLMs)<n>We propose One-Way Policy Optimization (OWPO), a method based on the principle of decoupling optimization direction from update magnitude.<n> Experimental results demonstrate that OWPO outperforms strong baselines, including DAPO, OPD, and MOPD.
  arXiv  Detail & Related papers  (2026-05-21T08:25:27Z)
• CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal [84.71254539482369]
  Group-relative reinforcement learning with verifiable rewards (RLVR) often wastes the most informative data it already has the failures.<n>We present CARE, a failure-centric post-training framework for multimodal reasoning that turns errors into supervision.<n> CARE improves accuracy and training smoothness while explicitly increasing the share of learning signal that comes from failures.
  arXiv  Detail & Related papers  (2025-12-22T16:34:21Z)
• Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers [90.50039419576807]
  Reinforcement Learning with Verifiable Rewards (RLVR) trains policies against automated verifiers to avoid costly human labeling.<n>To reduce vulnerability to verifier hacking, many RLVR systems collapse rewards to binary $0,1$ during training.<n>This choice carries a cost: it introduces textitfalse negatives (rejecting correct answers, FNs) and textitfalse positives (accepting incorrect ones, FPs)
  arXiv  Detail & Related papers  (2025-10-01T13:56:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.