Claim Plane: Reliability Gains and the Limits of Selective Concurrency for Parallel Coding Agents: A 30-Pair, Three-Seed Confirmatory Study of Deterministic Pre-Write Admission

• URL: http://arxiv.org/abs/2608.00947v1
• Date: Sun, 02 Aug 2026 02:56:49 GMT
• Title: Claim Plane: Reliability Gains and the Limits of Selective Concurrency for Parallel Coding Agents: A 30-Pair, Three-Seed Confirmatory Study of Deterministic Pre-Write Admission
• Abstract summary: Claim Plane addresses this failure mode as deterministic pre-write admission over versioned change intents.<n>Static Claim Plane raised pair pass from 23.3% under unconstrained parallel execution to 50.0%.<n> Dynamic admission was more selective, serializing 66.7% of conflict cases and 13.3% of clean cases, but 46 of 90 executions failed closed on undeclared scope.
• Score: 1.4721615285883427
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Parallel coding agents can produce locally valid changes that fail when combined. Claim Plane addresses this failure mode as deterministic pre-write admission over versioned change intents. This paper reports a confirmatory study on 30 frozen CooperBench feature pairs, balanced between 15 conflict and 15 clean labels, with three coder seeds, four coordination arms, and 360 completed executions. DeepSeek V4 Pro generated 60 feature-level planner declarations once; the declarations were frozen across all arms and coder seeds, while DeepSeek V4 Flash performed the coding work. Static Claim Plane raised pair pass from 23.3% under unconstrained parallel execution to 50.0%, a paired task-cluster difference of +26.7 percentage points (95% bootstrap CI 9.6 to 60.0), and raised integration success from 65.6% to 96.7%. On conflict-labeled pairs, pair pass rose from 6.7% to 60.0%. However, static admission serialized 96.7% of executions, including 93.3% of clean cases, and therefore recovered reliability largely by collapsing toward serial execution. Dynamic admission was more selective, serializing 66.7% of conflict cases and 13.3% of clean cases, but 46 of 90 executions failed closed on undeclared scope, reducing pair pass to 22.2%. Forty-five of those 46 blocks targeted files already present in the frozen declarations, indicating region undercoverage and insufficient amendment handling rather than wholly unknown files. The results support pre-write admission as a reliability mechanism, but they do not establish useful wall-clock parallel speedup: provider calls were physically sequential, and the conservative policy largely serialized the workload. The complete study artifacts, hashes, and clustered bootstrap analysis are publicly released for reproduction.

Related papers

• Engineering Reliable Commit Gates for Agentic AI: Cost-Aware Verification Portfolios under Common-Mode Data Failures [4.287745257410248]
  We present a runtime-assurance benchmark for cost-aware commit gates.<n>Its 48 task templates yield 2,880 scenarios across six fault regimes.<n>Results motivate explicit evidence lineage, cost-aware selection, and commit-time enforcement.
  arXiv  Detail & Related papers  (2026-09-10T01:42:40Z)
• The Recall Trap: A Recall-Maximizing Retriever Configuration Reduces Issue Resolution in Fixed-Budget Code Context [45.88028371034407]
  We report a controlled case study in code repair, not a new phenomenon.<n>We toggle one flag (one-chunk-perfile deduplication) on an otherwise identical stack.<n>We map where it holds: it reverses on a lexical BM25 (3.2pp, significant cross-paradigm interaction)<n>We show that at a tight fixed budget, do not hard-deduplicate by file, and A/B packing policies against the task, not the metric flag was tuned.
  arXiv  Detail & Related papers  (2026-08-14T19:22:50Z)
• Control Under Compression: Reliability Frontiers for Tool-Using Agents [0.0]
  We introduce CompressAgent, an environment-verified benchmark for ACC compression.<n>At 75% retained context, generic rewriting and section-based compression achieve 92.7% and 92.4% success.<n>At retained-context budgets from 25% to 10%, executable protocols become fragile.
  arXiv  Detail & Related papers  (2026-08-02T07:43:44Z)
• Turning Interaction History into Execution State: A Runtime Layer for Long-Horizon Coding Agents [48.967927222079965]
  Ledger is a runtime layer that distills an agent's completed interactions into an explicit execution state.<n> Ledger keeps this state in an online execution ledger and applies it at two boundaries of every step.<n>Across all 500 SWE-bench Verified instances, Ledger raises Pass@1 from 56.2% to 64.2% with GPT-5 mini and from 75.8% to 81.0% with MiniMax M2.5.
  arXiv  Detail & Related papers  (2026-08-01T18:25:00Z)
• EduPluginBench: Executable Assurance for AI-Generated Educational Plugins [0.0]
  We introduce negative provenance, an executable benchmark and staged admission method for generated plugins in software ecosystems.<n>A frozen transfer study of 600 unmodified generations from two current coding models found that 300/600 parsed, but none passed P0 or achieved P0-P4 conformance.<n>An earlier 540-generation diagnostic found that post-hoc bounded repair yielded 112 P0 passes, all nonconforming, with recall increasing from 13.4% to 100%.
  arXiv  Detail & Related papers  (2026-08-01T16:22:35Z)
• DarwinX: Evolving Agent Harnesses Through Natural Selection [48.64258219266629]
  DarwinX treats self-evolution as selection over a population of harnesses with the model frozen.<n>General agent competence, not benchmark-specific patches, so it survives changes of task, verifier, and base model.
  arXiv  Detail & Related papers  (2026-07-31T05:34:02Z)
• Rehearse: Stepping Back from the Confidence Cliff in Self-Improving Autoresearch [44.05969616406614]
  Autoresearch improves machine-learning code by proposing changes, running full training jobs, and keeping changes that improve the metric.<n>We study how the reliability of this pre-execution judgment changes over the course of an autoresearch trajectory.
  arXiv  Detail & Related papers  (2026-07-30T05:08:15Z)
• Looping Is Not Reliability: State-Bound Evidence and Typed Revision Contracts for Agentic Code Repair [36.56438114281786]
  We study the gap between finding a correct patch and retaining, verifying, and submitting it.<n>We derive an evidence-bound typed loop contract and instantiate its mechanically enforceable subset in a reference implementation.
  arXiv  Detail & Related papers  (2026-07-27T16:05:23Z)
• Efficient Visual Pointing for Embodied AI:Agent-Driven Data Synthesis, Cross-Block Attention, and Iterative Correction [55.11480729304395]
  We describe our PointArena 2026 solution, which achieves 77.2% overall accuracy and ranks second on the benchmark.<n>The ap proach targets three failure modes. First, agent-driven syn thesis builds large semantic and anchor-relative candidate pools.<n>Second, a determinis tic steerable-data pipeline creates a verified 10,000-sample main set, plus reserve samples, using masks, templates, and path verification.
  arXiv  Detail & Related papers  (2026-06-29T06:39:03Z)
• Converted, Not Equivalent: Benchmarking Codebase Conversion via Observational Equivalence [56.25095230687242]
  Coding agents often over-trust their own local validation routines and declare success on artifacts that satisfy surface checks.<n>This problem is especially acute in conversion, where prior evaluation is outcome-driven.<n>Across blind conversion attempts, the best system reaches 26.7--28.9% overall pass rate despite Spec pass rates up to 91.1%.<n>This suggests that failures stem more from contract-misaligned self-validation than from limited budget or backbone strength.
  arXiv  Detail & Related papers  (2026-05-27T19:57:15Z)
• CRANE: Constrained Reasoning Injection for Code Agents via Nullspace Editing [5.661334639541121]
  We present CRANE, a training-free parameter-editing method that treats the Thinking-Instruct delta as a pool of candidate reasoning edits for the Instruct backbone.<n>By merging paired Instruct and Thinking checkpoints, CRANE delivers strong gains over either individual model.
  arXiv  Detail & Related papers  (2026-05-13T20:09:35Z)
• MOSAIC-Bench: Measuring Compositional Vulnerability Induction in Coding Agents [2.1942030377331245]
  Coding agents often pass per-prompt safety review yet ship exploitable code when their tasks are decomposed into routine engineering tickets.<n>We introduce MOSAIC-Bench, a benchmark of 199 three-stage attack chains paired with deterministic exploit oracles on deployed software substrates.<n>We show that nine production coding agents compose innocuous tickets at 53-86% end-to-end ASR with only two refusals across all staged runs.
  arXiv  Detail & Related papers  (2026-05-05T16:38:23Z)
• 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)
• Scalable Multi-Task Low-Rank Model Adaptation [43.22544779625565]
  Scaling multi-task low-rank adaptation (LoRA) to a large number of tasks induces catastrophic performance degradation.<n>We find that existing solutions, like regularization and dynamic routing, fail at scale because they are constrained by a fundamental trade-off.<n>We propose mtLoRA, a scalable solution with three novel designs.
  arXiv  Detail & Related papers  (2026-03-02T06:57:11Z)

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.