ANNEAL: Adapting LLM Agents via Governed Symbolic Patch Learning

• URL: http://arxiv.org/abs/2605.16309v1
• Date: Mon, 04 May 2026 05:24:03 GMT
• Title: ANNEAL: Adapting LLM Agents via Governed Symbolic Patch Learning
• Abstract summary: 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.
• Score: 12.44509691077682
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: LLM-based agents can recover from individual execution errors, yet they repeatedly fail on the same fault when the underlying process knowledge--operator schemas, preconditions, and constraints--remains unrepaired. Existing self-evolving approaches address this gap by updating prompts, memory, or model weights, but none directly repair the symbolic structures that encode how tasks are executed, and few provide the governance guarantees required for safe deployment. We introduce ANNEAL, a neuro-symbolic agent that converts recurring failures into governed symbolic edits of a process knowledge graph without modifying foundation model weights. Its core mechanism, Failure-Driven Knowledge Acquisition (FDKA), localizes the responsible operator, synthesizes a typed patch through constrained LLM generation, and validates the proposal via multi-dimensional scoring, symbolic guardrails, and canary testing before commit. Every accepted edit carries full provenance and deterministic rollback capability. Across four domains and 27 multi-seed runs, ANNEAL is the only evaluated system that commits persistent structural repairs--strong baselines such as ReAct and Reflexion achieve high episodic recovery yet retain 72-100% holdout failure rates on recurring faults, whereas ANNEAL reduces these to 0% in the tested recurring-failure settings. Ablation confirms that removing FDKA eliminates all structural repairs and drops success rate by up to 26.7 percentage points. These results suggest that governed symbolic repair offers a complementary paradigm to weight-level and prompt-level adaptation for persistent fault elimination.

Related papers

• DCFA: Dual-view Causal-inspired Attribution for Failure Reasoning in LLM-based Multi-agent Systems [61.11435469308521]
  We propose DCFA, a training-free framework for failure attribution in large language model systems.<n> DCFA integrates a global module that constructs structured causal-inspired dependency graphs from system traces.<n>Experiments show that DCFA improves step-level accuracy by up to 8.27% over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-09-04T05:29:31Z)
• Finding Where the Buck Stops: An Automated Failure Attribution-Based Reflection Framework for Multi-Agent Collaboration [14.41671360589919]
  DoCtOR (Diagnose-then-Correct PPO-enhanced Reflection) is a novel reflection framework that enhances multi-agent collaboration.<n>DoCtOR achieves 22%, 26%, and 27% improvements over initial success rates on HotPotQA, ChartQAPro, and Mind2Web datasets.
  arXiv  Detail & Related papers  (2026-08-28T12:26:03Z)
• 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)
• Mnemosyne: Agentic Transaction Processing for Validating and Repairing AI-generated Workflows [0.764671395172401]
  Agentic Transaction Processing treats generated actions as untrusted proposals until they pass deterministic admission under a declared, executable constraint set C.<n>We realize ATP in Mnemosyne, a runtime with an append-only transition log, effective-state projection, dependency-safe compensation, and active commitment records.<n>A reproducible artifact rejects the targeted violations across nine falsification tests while still admitting valid work, at under 6% overhead, and local repair edits an order of magnitude fewer operations than global recompute.
  arXiv  Detail & Related papers  (2026-06-30T23:33:16Z)
• From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flaws [12.757205456771295]
  This paper proposes HarnessFix, a trace-guided framework for diagnosing agent failures and repairing agent harnesses.<n> HarnessFix compiles raw execution traces and harness code into a Harness-aware Trace Intermediate Representation.<n>It attributes failures to responsible trajectory steps and harness layers, consolidates recurring diagnoses into actionable flaw records, and maps them to scoped repair operators.
  arXiv  Detail & Related papers  (2026-06-04T15:58:30Z)
• Self-Healing Agentic Orchestrators for Reliable Tool-Augmented Large Language Model Systems [0.10210859604701106]
  Self-healing agentic orchestrator treats reliability as a runtime bounded control problem.<n>Self-healing achieves 98.8% task success, compared with 94.5% for retry-only and 93.8% for full replanning.
  arXiv  Detail & Related papers  (2026-05-31T19:27:22Z)
• How Sparsity Allocation Shapes Label-Free Post-Pruning Recoverability [4.9112670395105305]
  Post-pruning repair methods can partially recover collapsed sparse models, but their effectiveness depends on the sparse model left by the upstream pruning allocation.<n>This paper studies how sparsity allocation shapes post-repair recoverability under a fixed activation-statistic repair backend.
  arXiv  Detail & Related papers  (2026-05-21T04:03:24Z)
• VerifyMAS: Hypothesis Verification for Failure Attribution in LLM Multi-Agent Systems [79.51005192758262]
  Large language model-driven multi-agent systems excel at complex tasks.<n>However, unreliable agents remain a key bottleneck to system-level reliability.<n>We propose a hypothesis verification framework for agent failure attribution.
  arXiv  Detail & Related papers  (2026-05-17T14:09:35Z)
• RePO-VLA: Recovery-Driven Policy Optimization for Vision-Language-Action Models [90.39703013636868]
  RePO-VLA is a recovery-driven policy optimization framework.<n>It assigns distinct roles to success, recovery, and failure trajectories.<n>It raises adversarial success from 20% to 75% on average and up to 80% in scaled real-world trials.
  arXiv  Detail & Related papers  (2026-05-10T08:24:05Z)
• 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)
• Dynamic analysis enhances issue resolution [53.50448142467294]
  DAIRA (Dynamic Analysis-enhanced Issue Resolution Agent) is an automated repair framework that embeds dynamic analysis into the agent's reasoning cycle.<n> Driven by a Test Tracing-Driven methodology, DAIRA utilizes lightweight monitors to extract critical runtime data.<n>When powered by Gemini 3 Flash Preview, DAIRA establishes a new state-of-the-art (SOTA) performance, achieving a 79.4% resolution rate on the SWE-bench Verified dataset.
  arXiv  Detail & Related papers  (2026-03-23T14:48:54Z)
• RECOVER: Robust Entity Correction via agentic Orchestration of hypothesis Variants for Evidence-based Recovery [8.750432529472802]
  We introduce RECOVER, an agentic correction framework that serves as a tool-using agent.<n>It leverages multiple hypotheses as evidence from ASR, retrieves relevant entities, and applies Large Language Model (LLM) correction under constraints.<n>It achieves 8-46% relative reductions in entity-phrase word error rate (E-WER) and increases recall by up to 22 percentage points.
  arXiv  Detail & Related papers  (2026-03-17T11:48:12Z)
• MAS-FIRE: Fault Injection and Reliability Evaluation for LLM-Based Multi-Agent Systems [38.44649280816596]
  We propose MAS-FIRE, a systematic framework for fault injection and reliability evaluation of Multi-Agent Systems.<n>We define a taxonomy of 15 fault types covering intra-agent cognitive errors and inter-agent coordination failures.<n>Applying MAS-FIRE to three representative MAS architectures, we uncover a rich set of fault-tolerant behaviors.
  arXiv  Detail & Related papers  (2026-02-23T13:47:43Z)
• Metacognitive Self-Correction for Multi-Agent System via Prototype-Guided Next-Execution Reconstruction [58.51530390018909]
  Large Language Model based multi-agent systems excel at collaborative problem solving but remain brittle to cascading errors.<n>We present MASC, a metacognitive framework that endows MAS with real-time, unsupervised, step-level error detection and self-correction.
  arXiv  Detail & Related papers  (2025-10-16T05:35:37Z)
• Semantics-Aligned, Curriculum-Driven, and Reasoning-Enhanced Vulnerability Repair Framework [15.17681731375364]
  SeCuRepair is a semantics-aligned, curriculum-driven, and reasoning-enhanced framework for vulnerability repair.<n>At its core, SeCuRepair adopts a reason-then-edit paradigm, requiring the model to articulate why and how a vulnerability should be fixed.<n>SeCuRepair also moves beyond traditional supervised fine-tuning and employs semantics-aware reinforcement learning.
  arXiv  Detail & Related papers  (2025-10-01T15:09:27Z)
• Recover: A Neuro-Symbolic Framework for Failure Detection and Recovery [2.0554045007430672]
  This paper introduces Recover, a neuro-symbolic framework for online failure identification and recovery. By integrating logical rules, and LLM-based planners, Recover exploits symbolic information to enhance the ability of LLMs to generate recovery plans.
  arXiv  Detail & Related papers  (2024-03-31T17:54:22Z)

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.