Grounding SWE-Agent Decisions in Architecture-0 Design: Navigating Unknown Unknowns through Physical Mapping

• URL: http://arxiv.org/abs/2609.17221v1
• Date: Tue, 15 Sep 2026 14:04:33 GMT
• Title: Grounding SWE-Agent Decisions in Architecture-0 Design: Navigating Unknown Unknowns through Physical Mapping
• Abstract summary: We investigate how Autonomous Software Engineering Agents (SWE-Agents) navigate Unknown Unknowns (UUs)<n>UUs are the nascent system design phase plagued by implicit engineering constraints, or Unknown Unknowns (UUs)<n>We propose the Physical Mapping Guard (PMG) to eradicate physical-layer and validation-layer gaming.
• Score: 4.754027236572029
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Autonomous Software Engineering Agents (SWE-Agents) excel in deterministic coding tasks but struggle with Architecture 0, the nascent system design phase plagued by implicit engineering constraints, or Unknown Unknowns (UUs) that are rarely stated explicitly. To investigate how agents navigate UUs, we explore a progressive trajectory across pure-text self-play, tool-augmented feedback, and external physical mapping. Our empirical analysis reveals a cascading chain of failures. Pure-text reasoning inevitably devolves into polite consensus or plausible yet physically impossible fabrications. Attempting to bridge this gap via an early-stage execution sandbox unexpectedly triggers Specification Gaming: agents exploit their autonomy over validation scripts to bypass physical constraints, achieving superficial success without resolving core architectural flaws. To resolve this self-validation trap, we propose the Physical Mapping Guard (PMG). Grounded in the software engineering principle of Separation of Concerns, PMG revokes verification authority from the agent, forcing semantic intents to be evaluated by an external, deterministic Semantic-to-Physical (S2P) mapping engine. Extensive evaluations demonstrate that PMG completely eradicates physical-layer and validation-layer gaming. By precisely isolating residual failures to semantic reinterpretations and auditor overreach, PMG marks a critical step toward genuine affordance grounding in automated architectural design.

Related papers

• AI Slop and Hallucinations in Vulnerability Assessment: A Survey on Reasoning Failures and Trustworthy Mitigation [48.55515767840701]
  "AI slop" is artifacts, hallucinated vulnerabilities, plausible but incorrect patches, and semantically repackaged bug reports.<n>This paper surveys the empirical evidence, identifies a unifying mechanism, and traces a path toward trustworthy triage.
  arXiv  Detail & Related papers  (2026-08-26T11:48:38Z)
• Agentic Harnesses: LLM-Driven Verification Layers for Robot Autonomy [0.0]
  Development of advanced AI systems has largely focused on execution rather than verifying the feasibility actions planning models propose.<n>We propose a LLM-driven verification layer between planning and execution to evaluate action permissibility.<n>We achieve near 85% precision across accept/escalate/reject categories of adversarial attacks, with negligible errors between accepting and rejecting tasks, and errors mostly manifesting at the escalate boundary.
  arXiv  Detail & Related papers  (2026-08-10T17:15:55Z)
• 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)
• MetaSpace: Metamorphic Testing for Spatial Cognition in Embodied Agents [7.0922719251235655]
  MetaSpace is a novel framework designed to evaluate the spatial cognition of embodied agents.<n>We show that MetaSpace successfully detects 90,422 spatial cognition errors in state-of-the-art (SOTA) MLLM-driven agents.<n>Results indicate that all SOTA agents achieve average scores between 0.44 and 0.52, significantly lower than the human benchmark of 0.96.
  arXiv  Detail & Related papers  (2026-07-26T14:07:20Z)
• PhyAgentOS: A Self-Evolving Operating System for Embodied Agents with Decoupled Cognitive Planning and Physical Execution [49.776611937968]
  We present PhyAgentOS, a foundation delivering scheduling, verification, memory, benchmarking, and safety as system-level services.<n>Its Session-Centered treats a session, not an action, as the minimum unit of scheduling, compatibility, supervised execution, evidence collection, and acceptance.<n>SessionVerifier distinguishes execution termination from semantic task completion via evidence-grounded verdicts of success, failure, or replan.<n> Benchmarking reuses the deployment session and verification path, so results trace to real execution.
  arXiv  Detail & Related papers  (2026-07-18T04:46:53Z)
• Provably Secure Agent Guardrail [89.79561918065122]
  Existing defense architectures rely on empirical semantic guardrails and probabilistic large model adjudicators.<n>This paper proposes a new security paradigm for agents based on the fundamental limitations of logical reasoning.
  arXiv  Detail & Related papers  (2026-05-28T02:12:41Z)
• Not What You Asked For: Typographic Attacks in Household Robot Manipulation [2.8988874060074163]
  This work evaluates typographic attacks in a Habitat-based simulation using the HomeRobot benchmark.<n>We introduce a decoupled perception architecture that exposes a frozen CLIP encoder to adversarial stickers.<n>We find that perceptual errors propagate through the persistent 3D semantic map to produce kinetic failures.
  arXiv  Detail & Related papers  (2026-05-18T16:06:29Z)
• PRISM: : Planning and Reasoning with Intent in Simulated Embodied Environments [59.07829883257003]
  Built on five multi-room apartments, PRISM structures 300 human-verified tasks into three capability tiers.<n>PRISM exposes an agent-agnostic executable action API that allows arbitrary agents to be evaluated end-to-end.
  arXiv  Detail & Related papers  (2026-05-12T04:59:47Z)
• 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)
• Altered Thoughts, Altered Actions: Probing Chain-of-Thought Vulnerabilities in VLA Robotic Manipulation [27.2709460237741]
  Recent Vision-Language-Action (VLA) models increasingly adopt chain-of-thought (CoT) reasoning, generating a natural-language plan before decoding motor commands.<n>We ask: which properties of this intermediate plan does the action decoder actually rely on, and can targeted corruption of the reasoning trace alone degrade a robot's physical task performance?<n>We design a taxonomy of seven text corruptions organized into three attacker tiers (blind noise, mechanical-semantic, and LLM-adaptive) and apply them to a state-of-the-art reasoning VLA across 40 tabletop manipulation tasks.
  arXiv  Detail & Related papers  (2026-03-13T07:02:51Z)
• CaMeLs Can Use Computers Too: System-level Security for Computer Use Agents [60.98294016925157]
  AI agents are vulnerable to prompt injection attacks, where malicious content hijacks agent behavior to steal credentials or cause financial loss.<n>We introduce Single-Shot Planning for CUAs, where a trusted planner generates a complete execution graph with conditional branches before any observation of potentially malicious content.<n>Although this architectural isolation successfully prevents instruction injections, we show that additional measures are needed to prevent Branch Steering attacks.
  arXiv  Detail & Related papers  (2026-01-14T23:06:35Z)

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.