From Version Conflicts to Decision Conflicts: Selective Revalidation for Long-Running AI Agents
- URL: http://arxiv.org/abs/2609.08015v1
- Date: Mon, 07 Sep 2026 21:56:48 GMT
- Title: From Version Conflicts to Decision Conflicts: Selective Revalidation for Long-Running AI Agents
- Abstract summary: Long-running AI agents may read state, reason, wait for tools or human approval, and perform an external action much later.<n>ATR records the explicit, executable conditions that justify a pending action and rechecks only the conditions affected by a change before releasing the external operation.
- Score: 5.854855197115679
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Long-running AI agents may read state, reason, wait for tools or human approval, and perform an external action much later. The state that justified the action can change in the meantime. For example, after an agent proposes an 80 GBP refund under a limit of 100, a customer-name change affects only presentation metadata, a new limit of 90 still permits the refund, a limit of 50 invalidates it, and a refund issued by another worker must prevent a duplicate. Standard optimistic concurrency control and version checks can detect that previously read state has changed, but by themselves do not determine whether that change invalidates the pending action's justification. We call any detected version change a version conflict; when that change invalidates the action's justification, it is also a decision conflict. ATR records the explicit, executable conditions that justify a pending action and rechecks only the conditions affected by a change before releasing the external operation. It can retain the action, refresh non-decisive metadata, require replanning, or block execution; a target-side transaction or compare-and-set binds checked state to commit. Across 210,000 controlled executions over 15 mutation cases, ATR matched every developer-specified outcome with no false allows or blocks. In ten durable SQLite checkpoint/resume cells, it evaluated 0.6 conditions per change versus 6.0 for FullScan. At 4,093 recorded reads, ATR took 9.3 microseconds versus 2595.9 microseconds for FullScan. These deterministic results establish controlled feasibility, not production generality or automatic extraction of the required conditions.
Related papers
- ReDraft, Don't Just Distill: Reference-Driven Revision for Continual VLLM Post-Training [66.72708893922605]
Post-training of large multimodal models should add new capabilities while preserving those from pre-training.<n>SFT gives explicit target supervision that learns a task from near-zero accuracy, but its off-policy targets move the model far enough to cause forgetting.<n>We introduce ReDraft, which obtains both from the model's own failures.
arXiv Detail & Related papers (2026-09-15T04:59:03Z) - Guardrailed Meta-Agent Loops: Stress-Testing Policy Pinning, Budget Bounds, and Crash Recovery [7.414694666903067]
GuardrailLoop is a simulation-based testbed that makes three operational contracts jointly testable.<n>A hash-pinned policy fixes goals, scope, evaluation identity, budget, and release conditions.<n>It separates useful adaptation, state recovery, and repeated execution.
arXiv Detail & Related papers (2026-09-10T21:22:08Z) - RobustSGPO: Search-Space Control for Agent Harness Evolution [56.722805974785125]
We introduce RobustSGPO, which specifies the requested edit, constructs and checks the patch, and continues search from either the incumbent or retained snapshots.<n>We evaluate permission scheduling, cumulative controls, and task-family transfer in the AgentX brainstorming workflow using 120 tasks, 95 runs, and 7,350 candidate attempts.
arXiv Detail & Related papers (2026-09-09T03:00:03Z) - Task-Conditioned Least-Privilege Learning for Executable Terminal and MCP Agents [45.88028371034407]
Tool-using large language-model agents can complete a task while exercising authority that the user did not grant or the task does not need.<n>We propose a framework where each action is audited before execution and again from observed effects along six dimensions of risk.<n>We find that after training using this framework on Qwen3.5-4B over 1,500 tasks, the selected seed reaches 98.48% safe success across 2,896 evaluation episodes.
arXiv Detail & Related papers (2026-08-18T22:07:23Z) - When Memory Updates but Behavior Does Not: Repairing Implicit Stale Dependencies in Personalized Agent Responses [1.5770673503612611]
Memory-augmented agents can know that a user's stored state is outdated and still plan around the old value.<n>We identify one structural contributor: draft-anchored verification checks what a response says, and in an open-ended response the stale dependency is usually unsaid.
arXiv Detail & Related papers (2026-08-03T02:49:08Z) - 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) - LemonHarness Technical Report [40.68992799867636]
LemonHarness is an integrated execution framework for long-horizon agents.<n>It constrains state-changing operations within a clearly defined workspace.<n>It brings model invocation, tool execution, and rule knowledge within a single controlled boundary.
arXiv Detail & Related papers (2026-06-23T08:44:00Z) - Overeager Coding Agents: Measuring Out-of-Scope Actions on Benign Tasks [40.270213696031625]
OverEager-Gen is a benchmark dedicated to overeager behavior on benign tasks.<n>On Claude Code, stripping the consent declaration alone raises the overeager rate from 0.0% to 17.1%.<n>OverEager-Gen therefore certifies each scenario's discriminative power before admission.
arXiv Detail & Related papers (2026-05-18T16:00:41Z) - Verify-Gated Completion as Admission Control in a Governed Multi-Agent Runtime: A Bounded Architecture Case Study [0.6875312133832079]
We study verify-gated completion as an admission-control pattern for governed multi-agent runtimes.<n>We show that under observed conditions, a read-only verify gate plus packetized admission records made completion decisions inspectable and fail-closed.
arXiv Detail & Related papers (2026-05-18T07:52:13Z) - Agent Control Protocol: Admission Control for Agent Actions [0.4929694290403903]
Agent Control Protocol (ACP) is a formal specification for admission control governance of autonomous agents in B2B institutional environments.<n>ACP defines cryptographic identity, capability-based authorization, deterministic risk evaluation, chained delegation, and cryptographically-chained auditing.<n>ACP operates on top of RBAC and Zero Trust, addressing what neither model solves.
arXiv Detail & Related papers (2026-03-19T12:28:28Z) - interwhen: A Generalizable Framework for Verifiable Reasoning with Test-time Monitors [47.363850513075356]
We present a test-time verification framework, interwhen, that ensures that the output of a reasoning model is valid wrt. a given set of verifiers.<n> Verified reasoning is an important goal in high-stakes scenarios such as deploying agents in the physical world.
arXiv Detail & Related papers (2026-02-05T08:35:01Z) - SABER: Small Actions, Big Errors -- Safeguarding Mutating Steps in LLM Agents [52.20768003832476]
We analyze execution traces on $$-Bench (Airline/Retail) and SWE-Bench Verified.<n>We formalize emphdecisive deviations, earliest action, level divergences that flip success to failure.<n>We introduce cm, a model-agnostic, gradient-free, test-time safeguard.
arXiv Detail & Related papers (2025-11-26T01:28:22Z)
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.