VeriHarness is introduced, a code-controlled agent loop in which models generate candidates while external validators control acceptance, budgets, and traces, and it is used to compare raw diagnostics with feedback that identifies the failure location, observed value, and admissible alternatives.
Abstract
LLM agents often retry after external validation rejects a candidate, but the interface between validation and the next model call remains underspecified. We introduce VeriHarness, a code-controlled agent loop in which models generate candidates while external validators control acceptance, budgets, and traces. We use it to compare raw diagnostics with feedback that identifies the failure location, observed value, and admissible alternatives. Across 50 paired TextWorld games under a four-call cap, feedback containing all three fields raises terminal success from 14/50 to 36/50 for Qwen2.5-Coder-14B (+44 percentage points) and from 8/50 to 29/50 for Llama-3.1-8B (+42 points). Ablations locate most of the gain in the admissible alternatives: feedback containing only the location and observed value remains near the raw diagnostic baseline. Presenting the complete repair information in prose instead of a keyed JSON record yields nearly the same success, providing no evidence that JSON syntax itself improves repair. The ordering persists across the tested call budgets and one sampled-decoding setting.
This work forks live SWE-bench agent trajectories at controlled points, rebuild the environment, continue each fork with a different model, and compare against same-model control forks that isolate sampling and replay noise, finding configuration-dependent temperature-0"determinism" is configuration-dependent.
Generate--test--revise loops are common in coding agents, but repetition alone provides no reliability guarantee. We study the gap between finding a correct patch and retaining, verifying, and submitting it. A sealed five-seed study over 30 HumanEval repairs produces 900 three-revision trajectories. Under forced revision, current correctness with current traces falls from 0.820 after one revision to 0.673 after two, although ever-correct rises to 0.847. Two common-state studies use 2,430 branches from identical frozen programs to remove post-treatment risk-set bias. In a prespecified 14B replication, stale traces harm 34/135 correct starts versus 4/135 with current traces, a 22.2-point increase (task-cluster 95\% CI $[8.9,37.0]$, exact Holm $p=0.0337$). A prospective 540-rollout policy eliminates observed correct-start harm but reduces wrong-start repair and fails its joint criterion. Repository experiments over 24 bugs and four coder stacks expose floor effects and component heterogeneity without Holm-significant effects. We therefore separate admission, preservation, grounded certification, competence, and liveness. We derive an evidence-bound typed loop contract and instantiate its mechanically enforceable subset in a reference implementation that binds verifier evidence to exact code states, preserves verified checkpoints, and emits auditable admission receipts. The implementation is an executable specification and conformance artifact, not evidence of improved repair competence or calibrated verifier dependence.
Agent harnesses record a failed tool call and its error message in the transcript and ask the model to continue, on the assumption that the error is corrective information, and it is found the gain is negative for every instruction-tuned model tested.
FailForge is proposed, an agentic framework that converts failed rollouts into training signal, and recovers over 26% of previously failed instances at marginal additional cost, and training Qwen3.5-4B on the augmented corpus improves the SWE-bench Verified resolve rate by 6.6 points over a strong RFT baseline.
Dongyi Lv, E. Fushun, Aichen Cai et al.· 1 citation
LLM agents that repair failures often discard successful corrections, forcing later episodes to rediscover similar solutions. We study whether finalized repair outcomes can improve subsequent Text-to-SQL episodes without parameter updates. We introduce MERIT, a training-free agent that maintains an online dual-polarity memory of oracle-verified corrections and observed unsuccessful directions. Under oracle-assisted benchmark feedback, only memories from earlier finalized episodes are eligible for retrieval. A deterministic classifier assigns a coarse failure type, which conditions a hybrid lexical-dense retriever before the frozen model generates each revision. Using Qwen2.5-7B-Instruct with identical initial predictions and repair budgets, \method{} improves execution accuracy over stateless iterative repair from \(66.34\%\) to \(69.79\%\) on Spider and from \(47.35\%\) to \(48.44\%\) on BIRD. Paired analyses provide clear evidence for the Spider gain but weaker evidence on BIRD. MERIT is not reliably separated from untyped dynamic retrieval on either benchmark, while Reflexion-style memory reaches \(51.24\%\) on BIRD at substantially higher inference cost. Ablations show that negative memory contributes modestly, the value of type conditioning and lexical-dense ranking is dataset dependent, and schema-local experience provides the most consistent benefit. These results clarify when causal cross-query memory improves repair and when broader memory representations remain preferable. Our implementation is available here:
K. Vo, Tam Minh Chu, A. T. D. Dinh et al.· 0 citations
Results show that EMAS can turn experience from new samples into reusable updates to MAS topology and prompts, and is best or tied in six of eight model--benchmark settings.
Chao Fei, Qingyi Si, Kaihua Liang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
