DART: Semantic Recoverability for Structured Tool Agents

• URL: http://arxiv.org/abs/2605.23311v1
• Date: Fri, 22 May 2026 07:30:43 GMT
• Title: DART: Semantic Recoverability for Structured Tool Agents
• Abstract summary: We introduce DART, a modular runtime that localizes a failed instance and certifies semantically recoverable boundaries.<n>We show that DART correctly recovers all evaluated commitment-sensitive cases where baseline local recovery fails.<n>These results show that controller legality does not imply semantic validity, and that sound local recovery requires an explicit admissibility check.
• Score: 17.458285666498337
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: When a structured tool agent fails mid-execution, the runtime faces a dilemma: replaying the entire task is safe but wasteful, while restoring from a local checkpoint is efficient but can leave committed downstream work tied to an upstream history that no longer exists. This tension is acute in commitment-sensitive settings, where rollback targets a single failed instance yet downstream consumers have already acted on its output. Existing recovery approaches provide mechanical rollback but no criterion for whether a local restore remains semantically valid after downstream commitment. We formalize this gap as semantic recoverability and address it in DART, a modular runtime that localizes the failed instance, certifies semantically recoverable boundaries of that instance, aligns checkpoints to those boundaries, and selects an admissible restore point that preserves committed downstream work under dependency and effect constraints-or blocks otherwise. Across three LLM-driven domains and external validation on a LangGraph-based substrate, DART correctly recovers all evaluated commitment-sensitive cases where baseline local recovery fails, and a five-domain safety audit finds no unsafe admitted rollbacks. These results show that controller legality does not imply semantic validity, and that sound local recovery requires an explicit admissibility check.

Related papers

• Recoverability as a System Primitive for Long-Horizon AI Agents [5.008310199603767]
  We introduce recoverability as a system primitive that makes reuse an explicit decision.<n>Four deterministic and 20 paired file challenges demonstrate that accurate restoration and successful completion can conceal disallowed starting points.
  arXiv  Detail & Related papers  (2026-09-12T02:54:33Z)
• Safe to Resume? Breaking Execution Continuity of Agent Execution via Rollback [18.855582025155268]
  Checkpoint and rollback (C/R) are becoming essential for recovery, yet their security implications remain largely unexplored.<n>We present the first systematic security study of checkpoint and rollback in existing agent systems.
  arXiv  Detail & Related papers  (2026-08-29T17:40:13Z)
• Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction [22.654396704495934]
  Development-set failures can recover part of the missing diagnostic substrate by deciding which recovery interventions are admissible.<n>We propose DARC, a diagnosis-guided recovery harness that profiles task-family failure modes, prunes mismatched interventions from a shared recovery library, and freezes a verifier-selected success-cost policy for deployment.
  arXiv  Detail & Related papers  (2026-08-12T08:14:45Z)
• Independent Patch Verification for Coding Agents with a Bidirectional Reconstruct-and-Verify Framework [49.16055123488827]
  coding agents powered by large language models can now generate code patches directly from bug reports.<n>No mechanism independently verifies whether it truly resolves the reported problem.<n>We propose RETRACE, a training-free post-generation verification framework.
  arXiv  Detail & Related papers  (2026-08-09T22:59:13Z)
• ScrambleToolBench: Agents Search Exhaustively Even When Their Own Map Points to the Next Step [74.83535434786145]
  We introduce ScrambleToolBench, an interactive terminal benchmark designed to isolate behavioral reasoning.<n>The benchmark requires agents to uncover hidden tool behaviors entirely through trial-and-error interaction.<n>Our evaluation of state-of-the-art language models reveals that successful initial discovery does not translate into robust adaptation.
  arXiv  Detail & Related papers  (2026-08-03T15:07:46Z)
• Can LLMs Really Recover Microservice Failures? A Recovery-Aware Evaluation of Diagnosis-to-Action Reasoning [48.22526014304726]
  This paper presents R2Act, a recovery-action evaluation framework for post-diagnosis incident response.<n>R2Act defines an incident schema, quality gate, action-space representation, recovery-validity metrics, offline evaluator, and live-replay protocol.<n>We instantiate the framework as a benchmark dataset of 302 quality-audited incidents from system.
  arXiv  Detail & Related papers  (2026-07-06T03:05:17Z)
• RepoMirage: Probing Repository Context Reasoning in Code Agents with Perturbations [51.43574078961796]
  We introduce RepoMirage, a two-stage evaluation suite built on SWE-Bench Verified.<n>RepoMirage-Perturb applies three types of semantics-preserving repository-level perturbations, revealing a clear performance drop when correct solving requires broader context access.<n>We propose RepoAnchor, a structure-first prototype workflow that separates repository exploration from downstream problem solving.
  arXiv  Detail & Related papers  (2026-05-25T06:26:43Z)
• Partial Evidence Bench: Benchmarking Authorization-Limited Evidence in Agentic Systems [0.0]
  This paper introduces Partial Evidence Bench, a deterministic benchmark for measuring that failure mode.<n>The benchmark ships three scenario families -- due diligence, compliance audit, and security incident response.<n>It evaluates systems along four surfaces: answer correctness, completeness awareness, gap-report quality, and unsafe completeness behavior.
  arXiv  Detail & Related papers  (2026-05-06T19:01:29Z)
• ANNEAL: Adapting LLM Agents via Governed Symbolic Patch Learning [12.44509691077682]
  We introduce ANNEAL, a neuro-symbolic agent that converts recurring failures into governed symbolic edits of a process knowledge graph.<n>Its core mechanism, Failure-Driven Knowledge Acquisition (FDKA), localizes the responsible operator, synthesizes a typed patch through constrained LLM generation, and validates the proposal.<n>Across four domains and 27 multi-seed runs, ANNEAL is the only evaluated system that commits persistent structural repairs.
  arXiv  Detail & Related papers  (2026-05-04T05:24:03Z)
• Ghost in the Context: Measuring Policy-Carriage Failures in Decision-Time Assembly [0.0]
  LLM agents do not act on raw interaction history; they act on a bounded decision state assembled by truncation, summarization, reordering, and rewriting.<n>We study this failure mode over local Llama 3.1 8B, Qwen 2.5 7B, and Mistral 7B using judged exact constraint respect and direct audits of assembled-state visibility.
  arXiv  Detail & Related papers  (2026-05-02T18:07:42Z)
• ANCHOR: A Physically Grounded Closed-Loop Framework for Robust Home-Service Mobile Manipulation [10.278758849939917]
  We present ANCHOR, a closed-loop framework that aligns symbolic reasoning with verifiable physical state during execution.<n>ANCHOR improves task success from 53.3% to 71.7% and achieves a 71.4% recovery rate under perturbations.
  arXiv  Detail & Related papers  (2026-04-28T07:37:39Z)
• IMPACT-CYCLE: A Contract-Based Multi-Agent System for Claim-Level Supervisory Correction of Long-Video Semantic Memory [73.22944697933603]
  Existing pipelines produce opaque, end-to-end outputs that expose no intermediate state for inspection.<n>We present IMPACT-Cycle, a supervisory multi-agent system that reformulates long-video understanding as a multimodal iterative claim-level maintenance.
  arXiv  Detail & Related papers  (2026-04-22T03:03:33Z)
• Rewind-IL: Online Failure Detection and State Respawning for Imitation Learning [7.445072780282545]
  We present Rewind-IL, a training-free online safeguard framework for generative action-chunked imitation policies.<n> Rewind-IL combines a zero-shot failure detector based on Temporal Inter-chunk Discrepancy Estimate (TIDE), with split conformal prediction, with a state-respawning mechanism.<n>Online, Rewind-IL monitors self-consistency in overlapping action chunks, tracks similarity to the checkpoint library, and, upon failure, rewinds execution to the latest verified safe state.
  arXiv  Detail & Related papers  (2026-04-17T20:41:14Z)
• Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors [48.881343993730844]
  Safety-aligned large language models (LLMs) are increasingly deployed in real-world pipelines.<n> adversaries can distribute backdoored checkpoints that behave normally under standard evaluation but jailbreak when a hidden trigger is present.<n>Recent post-hoc weight-editing methods offer an efficient approach to injecting such backdoors.
  arXiv  Detail & Related papers  (2026-04-14T06:48:33Z)
• Why Does the LLM Stop Computing: An Empirical Study of User-Reported Failures in Open-Source LLMs [50.075587392477935]
  We conduct the first large-scale empirical study of 705 real-world failures from the open-source DeepSeek, Llama, and Qwen ecosystems.<n>Our analysis reveals a paradigm shift: white-box orchestration relocates the reliability bottleneck from model algorithmic defects to the systemic fragility of the deployment stack.
  arXiv  Detail & Related papers  (2026-01-20T06:42:56Z)
• Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization [58.390885294401066]
  Retrieval-augmented generation (RAG) has become a widely adopted paradigm for enabling knowledge-grounded large language models (LLMs)<n>RAG pipelines often fail to ensure that model reasoning remains consistent with the evidence retrieved, leading to factual inconsistencies or unsupported conclusions.<n>We propose AlignRAG, a novel iterative framework grounded in Critique-Driven Alignment (CDA)<n>We introduce AlignRAG-auto, an autonomous variant that dynamically terminates refinement, removing the need to pre-specify the number of critique iterations.
  arXiv  Detail & Related papers  (2025-04-21T04:56:47Z)
• Exploring Robustness of Unsupervised Domain Adaptation in Semantic Segmentation [74.05906222376608]
  We propose adversarial self-supervision UDA (or ASSUDA) that maximizes the agreement between clean images and their adversarial examples by a contrastive loss in the output space. This paper is rooted in two observations: (i) the robustness of UDA methods in semantic segmentation remains unexplored, which pose a security concern in this field; and (ii) although commonly used self-supervision (e.g., rotation and jigsaw) benefits image tasks such as classification and recognition, they fail to provide the critical supervision signals that could learn discriminative representation for segmentation tasks.
  arXiv  Detail & Related papers  (2021-05-23T01:50:44Z)

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.