arXiv AI
Jun 9
Repair Before Veto, When Repair Is Hidden: Quantum-Accessible Features for Repair-Augmented Constraint Learning
arXiv:2606. 08020v1 Announce Type: cross Abstract: Hard-constraint decision systems usually veto infeasible candidates.
Repair Before Veto: Repair-Augmented Constraint Learning for Contextual Decisions
arXiv:2606. 02326v1 Announce Type: new Abstract: Hard constraints are usually treated as terminal vetoes: once a candidate violates a requirement, the learned rule rejects it and any repair is handled outside the decision semantics.
Related stories
arXiv AI
2d ago
ContractRL: Shielded Group-Relative Policy Optimization for Auditable Tool-Call Repair
ContractRL introduces a contract-constrained sequential repair protocol for structured tool calls, modeling verifier-guided JSON repair as a bounded decision process. The policy observes candidate data, verifier feedback, JSON pointers, repair history, and budget, using a contract-derived action mask to filter invalid operations before a deterministic validator applies changes. Compared to Patch‑SFT and full regeneration, ContractRL achieves higher semantic success (0.9362 vs. 0.9076 and 0.9148) while generating fewer tokens (34.4 vs. 44.9 and 137.2), and policy optimization further improves success rates.
arXiv AI
Jul 2
Mnemosyne: Agentic Transaction Processing for Validating and Repairing AI-generated Workflows
arXiv:2607. 00269v1 Announce Type: new Abstract: LLMs, solvers, and agent teams increasingly generate workflow actions, repairs, and plans, but a generated action may be syntactically valid yet stale, infeasible, conflicting, or destructive of the evidence that triggered a repair.
arXiv Machine Learning
Aug 6
Relational Response Fields: A General Theory of Black-Box LLM Response Consistency and Recovery
arXiv:2608. 04552v1 Announce Type: cross Abstract: Black-box language-model reliability is commonly pursued by sampling, prompting, voting, verifying, or iteratively revising individual answers.
arXiv AI
Sep 25
Auditability Is Not One Property: Rule Overlap, Behavioural Agreement, and Composition in Reinforcement Learning
The paper introduces a protocol for auditing and composing reinforcement‑learning policies using discrete behavioral rules, defining auditability through six testable predicates such as trace integrity and rule coverage. Experiments show that overlapping rule sets do not guarantee behavioral agreement, and that rule‑based fusion often fails to outperform value‑based composition, highlighting limitations in current description layers. The authors provide an evidence‑bounded audit framework and outline future directions for more robust skill composition.
arXiv AI
Jul 22
One Rewrite to Fix Them All? Type-Aware Repair Allocation for Text-to-Image Prompt Optimization
arXiv:2607. 18724v1 Announce Type: new Abstract: Text-to-image (T2I) generators often fail to follow their prompts faithfully, producing wrong counts, swapped attributes, ambiguous relations, and illegible text.
Hugging Face Trending Papers
Jun 19
Training the Orchestrator: A Supervised Approach to End-to-End PDDL Planning with LLM Agents
Translating natural-language planning intent into verified plans is a longstanding challenge: people communicate goals in language, while classical planners require formal PDDL specifications. Recent agentic frameworks bridge this gap by orchestrating a pool of specialized repair agents inside a verifier-checked refinement loop, but the orchestrator at the centre is itself a prompted frontier LLM, paying a frontier-LLM API call at every refinement step.
arXiv Computer Vision
Sep 1
RePair: Turning Retrieval Failures into Counterfactual Hard Pairs
arXiv:2608.29604v1 Announce Type: cross Abstract: Vision-language retrieval with CLIP-style dual encoders achieves strong cross-modal performance, yet practical accuracy often hinges on localized sem...
arXiv AI
Aug 14
LLMs Know the Constraint But Do Not Use It: Activation Bottlenecks in Pragmatic Constraint Reasoning
arXiv:2608. 12321v1 Announce Type: cross Abstract: When a salient surface cue competes with an implicit feasibility constraint, LLMs often fail -- but aggregate accuracy conflates genuine constraint inference with conservative defaulting.
arXiv Computation and Language
3d ago
Is This Evidence Decision-Critical? Learning to Verify Rule-Governed Decisions
arXiv:2609.39608v1 Announce Type: new Abstract: Rule-based reasoning, as in eligibility checks and contract reviews, requires language models to assess evidence against individual conditions and comb...
arXiv AI
Jun 3
CARVE: Certified Affordable Repair of Vetoed Maneuvers via Envelopes for Interactive Driving
arXiv:2606. 02641v1 Announce Type: cross Abstract: Interactive driving exposes a failure mode that is easy to miss in rule-aware autonomous-driving stacks: a hard-rule margin can be negative for an ego candidate even though a small lawful accommodation by a non-priority agent would restore feasibility.
arXiv AI
Jun 9
ANNEAL: Adapting LLM Agents via Governed Symbolic Patch Learning
arXiv:2605. 16309v2 Announce Type: replace 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.