IMPACT-CYCLE: A Contract-Based Multi-Agent System for Claim-Level Supervisory Correction of Long-Video Semantic Memory

• URL: http://arxiv.org/abs/2604.20136v1
• Date: Wed, 22 Apr 2026 03:03:33 GMT
• Title: IMPACT-CYCLE: A Contract-Based Multi-Agent System for Claim-Level Supervisory Correction of Long-Video Semantic Memory
• Abstract summary: 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.
• Score: 73.22944697933603
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Correcting errors in long-video understanding is disproportionately costly: existing multimodal pipelines produce opaque, end-to-end outputs that expose no intermediate state for inspection, forcing annotators to revisit raw video and reconstruct temporal logic from scratch. The core bottleneck is not generation quality alone, but the absence of a supervisory interface through which human effort can be proportional to the scope of each error. We present IMPACT-CYCLE, a supervisory multi-agent system that reformulates long-video understanding as iterative claim-level maintenance of a shared semantic memory -- a structured, versioned state encoding typed claims, a claim dependency graph, and a provenance log. Role-specialized agents operating under explicit authority contracts decompose verification into local object-relation correctness, cross-temporal consistency, and global semantic coherence, with corrections confined to structurally dependent claims. When automated evidence is insufficient, the system escalates to human arbitration as the supervisory authority with final override rights; dependency-closure re-verification then ensures correction cost remains proportional to error scope. Experiments on VidOR show substantially improved downstream reasoning (VQA: 0.71 to 0.79) and a 4.8x reduction in human arbitration cost, with workload significantly lower than manual annotation. Code will be released at https://github.com/MKong17/IMPACT_CYCLE.

Related papers

• The Immutable Past: Formalizing State Mutability and Conflict Resolution in Mutable RAG [0.0]
  This paper formalizes the mechanics of State Mutability to prove that standard dense retrieval suffers from Asymptotic Recall Decay.<n>To resolve this, we introduce GC-Mem, a strict inference-time consistency protocol.
  arXiv  Detail & Related papers  (2026-09-13T15:28:07Z)
• 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)
• Heaviside Continuity of Rolling Coefficients for Eliminating Epistemic Entropy in Large Language Models [0.0]
  Heaviside Continuity of Rolling Coefficients (HCRC) is a verification-first execution framework.<n>It reformulates inference as predicate-gated state transitions governed by a Heaviside Gate.<n>HCRC combines model confidence with independent verification signals from a parallel worker architecture, allowing execution to advance only when correctness predicates are satisfied.
  arXiv  Detail & Related papers  (2026-07-06T00:29:34Z)
• TAPO: Tool-Aware Policy Optimization via Credit Transfer for Multimodal Search Agents [54.08846865906602]
  We characterize credit misassignment as a systematic failure mode of GRPO in tool-augmented multimodal search agents.<n>We propose Tool-Aware Policy Optimization (TAPO), which exploits the parameter-determinism property of information-acquisition tools.
  arXiv  Detail & Related papers  (2026-06-04T07:15:43Z)
• Citation-Closure Retrieval and Per-Rule Attribution for Real-World Regulatory Compliance Question Answering [54.97384993676565]
  We formalize Regulatory Compliance QA with RegOps-Bench, a novel benchmark featuring an Operational Knowledge Graph derived from complex national R&D regulations.<n>RefWalk traverses cross-document citations, fuses multi-view candidates via max-based aggregation, and enforces per-rule attribution to explicitly map claims to sources.
  arXiv  Detail & Related papers  (2026-05-28T10:38:38Z)
• Affordance Agent Harness: Verification-Gated Skill Orchestration [45.231685718099264]
  Affordance grounding requires identifying where and how an agent should interact in open-world scenes.<n>We propose Affordance Agent Harness, a closed-loop runtime that unifies skills with an evidence store and cost control.
  arXiv  Detail & Related papers  (2026-05-01T13:45:16Z)
• Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment [59.536125286960186]
  Multi-agent frameworks assigning specialized roles are increasingly adopted to enable self-reflection and mutual auditing.<n>We find it simultaneously induces a human-like cognitive bias known as Actor-Observer Asymmetry.<n>ReTAS guides agents to synthesize conflicting viewpoints into an objective consensus.
  arXiv  Detail & Related papers  (2026-04-21T15:05:58Z)
• The Consensus Trap: Rescuing Multi-Agent LLMs from Adversarial Majorities via Token-Level Collaboration [32.17285446393425]
  Response-level aggregation collapses when corrupted agents form a local majority.<n>We propose the Token-Level Round-Robin (RR) Collaboration, where agents sequentially interleave generation within a shared auto-regressive context.<n>We prove that RR maintains robust accuracy well beyond this critical threshold.
  arXiv  Detail & Related papers  (2026-04-18T20:31:37Z)
• 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)
• SAGE: Scalable AI Governance & Evaluation [10.238041570564395]
  textbfSAGE is a framework that operationalizes high-quality human product judgment as a scalable evaluation signal.<n>SAGE was deployed within LinkedIn Search ecosystems and powered policy oversight that measured ramped model variants and detected regressions invisible to engagement metrics.
  arXiv  Detail & Related papers  (2026-02-08T06:42:50Z)
• Long-horizon Reasoning Agent for Olympiad-Level Mathematical Problem Solving [65.02106674311908]
  This paper introduces Intern-S1-MO, a long-horizon math agent that conducts multi-round hierarchical reasoning.<n>By maintaining a compact memory in the form of lemmas, Intern-S1-MO can more freely explore the lemma-rich reasoning spaces.<n> Experiments show that Intern-S1-MO can obtain 26 out of 35 points on the non-geometry problems of IMO2025, matching the performance of silver medalists.
  arXiv  Detail & Related papers  (2025-12-11T15:26:28Z)
• 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)

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.