PACE: Anytime-Valid Acceptance Tests for Self-Evolving Agents

• URL: http://arxiv.org/abs/2606.08106v1
• Date: Sat, 06 Jun 2026 11:12:11 GMT
• Title: PACE: Anytime-Valid Acceptance Tests for Self-Evolving Agents
• Abstract summary: Self-evolving agents improve by repeatedly proposing changes to their own prompts, skills, ormodifications.<n>On Qwen2.5 agents (0.5B-3B) self-evolving at the prompt level on GSM8K, SVAMP, and ARC-Challenge, greedy acceptance commits 30-42% false and 10-33% harmful edits.<n> PACE commits the real one and essentially nothing else, matching greedy's held-out accuracy at sharply lower variance and about 18% lower evaluation cost.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Self-evolving agents improve by repeatedly proposing changes to their own prompts, skills, or workflows and keeping those that score higher on a small held-out set. Almost all effort has gone into the proposer that generates candidates; we argue the weak point is the acceptor, the rule that decides whether to commit a change. Applied hundreds of times against the same noisy dev estimate, the ubiquitous "keep it if the score went up" rule is uncontrolled adaptive multiple testing: the agent effectively p-hacks itself, accumulating false commits that make it churn and drift rather than improve. We recast committing as a sequential hypothesis test and propose PACE (Paired Anytime-valid Commit Evaluation), a training-free, anytime-valid commit gate. Each candidate is compared to the incumbent on identical instances and committed only when a testing-by-betting e-process accumulates decisive evidence, stopping early to save evaluations and controlling each candidate's false-commit probability at a user-set level even under optional stopping (a per-decision guarantee). On Qwen2.5 agents (0.5B-3B) self-evolving at the prompt level on GSM8K, SVAMP, and ARC-Challenge, greedy acceptance commits 30-42% false and 10-33% harmful edits when a genuine improvement is hidden among noisy proposals, while PACE commits the real one and essentially nothing else, matching greedy's held-out accuracy at sharply lower variance and about 18% lower evaluation cost. With no real gain available, greedy commits 13-21 spurious self-modifications per run (72-100% false) and degrades the most fragile agent by 4.9 points, while PACE holds at baseline. Reliability of self-evolution depends on the acceptor, not only on the proposer.

Related papers

• Certifying Model Upgrades with Slice-Wise Non-Regression and Incumbent Fallback [2.8716825293247665]
  We study checkpoint selection subject to non-regression tolerances relative to a retained incumbent.<n>We give a reproducible release procedure that separates candidate search from independent, paired evaluation.<n>A joint release decision does not require a slice-count Bonferroni penalty, although certification power can still decrease with the number of slices.
  arXiv  Detail & Related papers  (2026-09-12T05:00:50Z)
• 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)
• Beyond Pass@k: Measuring Reliability and Security of Agentic Code Generation [2.1734195143282693]
  We propose reliability@k, the same estimator applied correctly, with n = independent rollouts and c = fully-passing rollouts per (task, agent) pair.<n>Motivated by evidence that functional correctness does not imply security safety, we additionally propose security-adjusted reliability@k.
  arXiv  Detail & Related papers  (2026-08-11T16:01:15Z)
• The Order Is the Guarantee: Verifier-Budgeted Code Deletion with Static-First Learned Proposals [12.095189927690988]
  We study the inverse problem-how an Al system should remove code when execution-verification capacity is finite.<n>We formulate redundant-code reduction as proposal scheduling.<n>We show that scheduling governs search while the test suite alone governs what "preserving behavior" means.
  arXiv  Detail & Related papers  (2026-08-05T09:16:29Z)
• 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)
• Self-Authored Verification Is Unreliable in Heuristic Self-Improving Agents [5.91817208489443]
  We study the verifier-acceptance-deployment gap.<n>This gap refers to the discrepancy between an agent's self-authored verification signal and a sealed deployment evaluation.<n>We introduce a Sealed Exogenous Acceptance Loop (SEAL)
  arXiv  Detail & Related papers  (2026-07-27T11:45:14Z)
• TTHE: Test-Time Harness Evolution [50.26245555541721]
  Existing approaches optimize such harnesses before deployment, searching training or development data for a fixed agent workflow that is then frozen at test time.<n>We ask whether the harness can instead be optimized during evaluation itself, using only the unlabeled execution traces the agent produces on the test inputs.<n>During evaluation, TTHE maintains a population of candidate harnesses and refines them through an agentic proposer that reasons over their execution traces.<n>A judge then commits an improved harness from execution-derived proxy signals, and the selected program persists to govern subsequent inputs.
  arXiv  Detail & Related papers  (2026-07-09T05:53:39Z)
• Proper Scoring Rules for Agentic Uncertainty Quantification [0.038379177968040606]
  Trajectory Proper Score (TPS) is a predictor-agnostic family of strictly proper trajectory-level scoring rules.<n>Trajectory ECE is resolution-blind, while scalarized Trajectory Brier elicits only the collapsed scalar, not the full trace.
  arXiv  Detail & Related papers  (2026-05-23T22:22:00Z)
• Empirical Bayes Conformal Prediction for Vision and Language Models [20.40115871314124]
  Conformal prediction (CP) gives distribution-free coverage for modern vision and language models.<n>Standard CP uses one realization, while average-then-calibrate variants smooth multiple realizations into a point estimate.<n>We describe an empirical Bayes conformal prediction framework that uses $r$-values to convert score variability into an uncertainty informed nonconformity score.
  arXiv  Detail & Related papers  (2026-05-22T03:17:14Z)
• Pause and Reflect: Conformal Aggregation for Chain-of-Thought Reasoning [8.024041325202612]
  Chain-of-thought (CoT) reasoning with self-consistency improves performance by aggregating multiple sampled reasoning paths.<n>We introduce a conformal procedure for CoT reasoning that directly addresses aggregation uncertainty.<n>Our approach replaces majority voting with weighted score aggregation over reasoning paths and calibrates an abstention rule using conformal risk control.
  arXiv  Detail & Related papers  (2026-05-13T20:33:59Z)
• Correct Answers from Sound Reasoning: Verifiable Process Supervision for Language Models [94.68358825189738]
  We propose a post-training framework for verifiable domains that jointly optimize prediction accuracy and reasoning quality.<n>We evaluate VPS on chess, a controlled testbed where reasoning steps can be deterministically verified against engine signals.<n>VPS preserves accuracy while significantly improving reasoning quality, reducing win-rate error by up to 30% and restoring consistency to near saturation.
  arXiv  Detail & Related papers  (2026-04-03T15:19:46Z)
• Are Benchmark Tests Strong Enough? Mutation-Guided Diagnosis and Augmentation of Regression Suites [49.16055123488827]
  Insufficiently strong test suites can admit plausible yet semantically incorrect patches, inflating reported success rates.<n>We introduce STING, a framework for targeted test augmentation that uses semantically altered program variants as diagnostic stressors.<n>STING produces 1,014 validated tests spanning 211 instances and increases patch-region line and branch coverage by 10.8% and 9.5%.
  arXiv  Detail & Related papers  (2026-04-02T01:13:40Z)
• Preventing the Collapse of Peer Review Requires Verification-First AI [49.995126139461085]
  We propose truth-coupling, i.e. how tightly venue scores track latent scientific truth.<n>We formalize two forces that drive a phase transition toward proxy-sovereign evaluation.
  arXiv  Detail & Related papers  (2026-01-23T17:17:32Z)
• 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)
• CGES: Confidence-Guided Early Stopping for Efficient and Accurate Self-Consistency [3.2807118426157493]
  Large language models (LLMs) are often queried multiple times at test time, with predictions aggregated by majority vote.<n>We introduce Confidence-Guided Early Stopping (CGES), a Bayesian framework that forms posteriors over candidate answers.<n>CGES adaptively halts sampling once the posterior mass of a candidate exceeds a threshold.
  arXiv  Detail & Related papers  (2025-11-04T14:25:54Z)
• Latent Veracity Inference for Identifying Errors in Stepwise Reasoning [78.29317733206643]
  We introduce Veracity Search (VS), a discrete search algorithm over veracity assignments.<n>It performs otherwise intractable inference in the posterior distribution over latent veracity values.<n>It generalizes VS, enabling accurate zero-shot veracity inference in novel contexts.
  arXiv  Detail & Related papers  (2025-05-17T04:16:36Z)
• Certified Error Control of Candidate Set Pruning for Two-Stage Relevance Ranking [57.42241521034744]
  We propose the concept of certified error control of candidate set pruning for relevance ranking. Our method successfully prunes the first-stage retrieved candidate sets to improve the second-stage reranking speed.
  arXiv  Detail & Related papers  (2022-05-19T16:00:13Z)

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.