Scoped Verification for Reliable Long-Horizon Agentic Context Evolution under Distribution Shift

• URL: http://arxiv.org/abs/2607.09175v1
• Date: Fri, 10 Jul 2026 08:10:37 GMT
• Title: Scoped Verification for Reliable Long-Horizon Agentic Context Evolution under Distribution Shift
• Abstract summary: We propose Graph-Regularized Agentic Context Evolution (GRACE) to maintain persistent instruction component as a typed semantic graph.<n>We evaluate GRACE within a fixed telecom agent harness derived from $2$-bench under a controlled distribution-shift protocol.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deployed LLM agents rely on agentic context, the model-external textual control content assembled by an operational harness. In this work, the mutable component of that context is a persistent system-level instruction that is updated from operational experience while the model, tools, and harness remain fixed. Over long evolution horizons, flat-text maintenance makes verification increasingly difficult as accumulated instructions grow and interact. We propose Graph-Regularized Agentic Context Evolution (GRACE), which maintains the persistent instruction component as a typed semantic graph and validates proposed updates within the local typed neighborhoods of modified nodes. Accepted graph updates are reconstructed as incremental edits to the textual instruction checkpoint used at deployment. We evaluate GRACE within a fixed telecom agent harness derived from $τ^2$-bench under a controlled distribution-shift protocol. Across five independent replications, GRACE improves strict reliability, measured by pass^3, from the Gemini 2.5 Flash zero-shot value of 0.091 to 0.673$\pm$0.136 at the final checkpoint. This exceeds a Gemini 3.1 Pro zero-shot reference of 0.242 on the same held-out set, while the flat-text HCE baseline finishes at 0.191$\pm$0.051. These results identify two requirements for reliable long-horizon context evolution, a structural substrate that makes verification local and a consolidation mechanism that keeps accumulated instruction content usable.

Related papers

• HarnessEvolve: Learning from Reference Trajectories for Reliable Agent Self-Evolution [11.431479238875712]
  We introduce HarnessEvolve, a self-evolving framework that learns from reference trajectories to achieve reliable agent self-evolution.<n>We conduct extensive experiments on several benchmarks spanning open-domain and enterprise scenarios, using different models and agent frameworks.<n>Results demonstrate that HarnessEvolve consistently outperforms state-of-the-art baselines across all benchmarks and settings.
  arXiv  Detail & Related papers  (2026-09-01T07:31:18Z)
• EDGE: Engine for Deterministic Graph Evaluation through Conversation Simulation from Graph Structured DSL Configuration [0.518884791678612]
  We introduce a formal evaluation methodology that is grounded in AgentGraph, a planner powered by a domain specific language.<n>We leverage graph algorithms that exhaustively enumerate conversational paths, forming a comprehensive evaluation set that captures the agent's complete behavioral space.<n>To quantify reliability, we define novel metrics that measure response and trajectory determinism, structural adherence and semantic consistency.
  arXiv  Detail & Related papers  (2026-08-30T18:56:53Z)
• Living-Harness Is an Interactive-Agent Evolver [15.081919387954578]
  Large language model (LLM) agents may recover from a failure within an episode or after a retry, yet the same execution failure can recur in later tasks.<n>We propose $textbfLiving-Harness, a self-evolving agent harness that converts each completed trajectory and its evaluator signals into posterior evidence for bounded harness updates.
  arXiv  Detail & Related papers  (2026-07-29T08:20:11Z)
• VeriEvol: Scaling Multimodal Mathematical Reasoning via Verifiable Evol-Instruct [71.22358682581215]
  Scaling reinforcement learning for visual mathematical reasoning requires more than generating harder questions.<n>We instantiate this as VeriEvol, an iterative framework with two components.<n>On a five-benchmark visual-math suite, scaling evolved SFT data from 10K to 250K samples raises the mean accuracy from 35.42 to 54.73.
  arXiv  Detail & Related papers  (2026-06-22T16:17:30Z)
• Group-Graph Policy Optimization for Long-Horizon Agentic Reinforcement Learning [85.02566758103008]
  Group-Graph Policy Optimization (G2PO) is a novel group-based Reinforcement Learning algorithm tailored for multi-turn agentic tasks.<n>G2PO substantially outperforms state-of-the-art prompt-based and RL baselines, achieving remarkable success rate improvements of up to 22.2% over GRPO.
  arXiv  Detail & Related papers  (2026-06-22T08:12:47Z)
• KGEdit: Ambiguity-Aware Knowledge Graphs for Training-Free Precise Video Generation and Editing [24.315720861063397]
  KGEdit is a structured semantic control framework for text-to-video (T2V) diffusion models.<n>We first construct an ambiguity-aware knowledge graph (AAKG) to disentangle and disambiguate the input prompt.<n>We then design a structured semantic injection module (SSIM) to inject semantic signals into key layers of the diffusion Transformer.
  arXiv  Detail & Related papers  (2026-05-28T07:31:22Z)
• EGL-SCA: Structural Credit Assignment for Co-Evolving Instructions and Tools in Graph Reasoning Agents [35.25814217014108]
  We propose EGL-SCA, a verifier-centric dual-space framework for graph reasoning agents.<n>We show that EGL-SCA achieves a state-of-the-art 92.0% average success rate.
  arXiv  Detail & Related papers  (2026-05-11T11:09:32Z)
• Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses [57.20181537213498]
  Agentic Harness Engineering (AHE) is a closed loop that automates harness engineering.<n>AHE addresses challenges through three matched observability pillars.<n>Ten AHE lift pass@1 on Terminal-Bench 2 from 69.7% to 77.0%, surpassing the human-designed harness Codex-CLI.<n>On SWE-bench-verified it tops aggregate success at 12% fewer tokens than the seed, and on Terminal-Bench 2 it yields +5.1 to +10.1pp cross-family gains.
  arXiv  Detail & Related papers  (2026-04-28T16:55:02Z)
• Semantic Entanglement in Vector-Based Retrieval: A Formal Framework and Context-Conditioned Disentanglement Pipeline for Agentic RAG Systems [0.0]
  We formalize semantic entanglement as a model-relative measure of cross-topic overlap in embedding space.<n>We introduce the Semantic Disentanglement Pipeline (SDP), a four-stage preprocessing framework that restructures documents prior to embedding.<n>We evaluate SDP on a real-world enterprise healthcare knowledge base comprising over 2,000 documents across approximately 25 sub-domains.
  arXiv  Detail & Related papers  (2026-04-20T00:24:34Z)
• Autogenesis: A Self-Evolving Agent Protocol [60.15939127351914]
  We introduce Autogenesis Protocol (AGP), a self evolution protocol that decouples what evolves from how evolution occurs.<n>We present Autogenesis System (AGS), a self-evolving multi-agent system that dynamically instantiates, retrieves, and refines protocol-registered resources during execution.
  arXiv  Detail & Related papers  (2026-04-16T14:04:06Z)
• IMPACT: A Dataset for Multi-Granularity Human Procedural Action Understanding in Industrial Assembly [79.737814043505]
  IMPACT is a synchronized five-view RGB-D dataset for deployment-oriented industrial procedural understanding.<n>It is built around real assembly and disassembly of a commercial angle grinder with professional-grade tools.
  arXiv  Detail & Related papers  (2026-04-12T02:09:19Z)
• Cross-modal Proxy Evolving for OOD Detection with Vision-Language Models [59.242742594156546]
  CoEvo is a test-time framework that performs bidirectional, sample-conditioned adaptation of both textual and visual proxies.<n>CoEvo achieves state-of-the-art performance, improving AUROC by 1.33% and reducing FPR95 by 45.98% on ImageNet-1K compared to strong negative-label baselines.
  arXiv  Detail & Related papers  (2026-01-13T12:08:26Z)
• Open-Source Agentic Hybrid RAG Framework for Scientific Literature Review [2.092154729589438]
  We present an agentic approach that encapsulates the hybrid RAG pipeline within an autonomous agent.<n>Our pipeline ingests bibliometric open-access data from PubMed, arXiv, and Google Scholar APIs.<n>A Llama-3.3-70B agent selects GraphRAG (translating queries to Cypher for KG) or VectorRAG (combining sparse and dense retrieval with re-ranking)
  arXiv  Detail & Related papers  (2025-07-30T18:54:15Z)

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.