SeqFeed: Improving Agentic RTL Code Generation with Sequential Behavior Feedback

• URL: http://arxiv.org/abs/2608.16934v1
• Date: Sun, 09 Aug 2026 15:15:33 GMT
• Title: SeqFeed: Improving Agentic RTL Code Generation with Sequential Behavior Feedback
• Abstract summary: To generate correct RTL code, agents must understand sequential behavior, including how signals evolve and propagate over multiple clock cycles.<n>We propose textitSeqFeed, which comprises two complementary mechanisms: textitSeQuery and textitSeGraph
• Score: 15.691779408217814
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: RTL code generation is a critical stage in hardware design, and the emergence of agentic systems offers new opportunities to automate this process. To generate correct RTL code, agents must understand sequential behavior, including how signals evolve and propagate over multiple clock cycles. However, effectively conveying such temporal information to agents remains a significant challenge. RTL code does not expose cycle-level signal behavior for a specific execution, whereas full simulation waveforms are too voluminous and noisy for effective LLM analysis. To address these limitations, we study how human engineers reason about sequential behavior and identify three requirements for effective feedback: it should be event-addressable, dependency-traceable, and iteratively-queryable. Guided by these requirements, we propose \textit{SeqFeed}, which comprises two complementary mechanisms: (1) \textit{SeQuery}, an SQL-like waveform query language that enables agents to anchor queries to semantic events and sample signal values at relative time points; and (2) \textit{SeGraph}, a dependency graph that tracks signal propagation across clock cycles. Experimental results across multiple LLMs demonstrate the effectiveness of SeqFeed in improving pass rates. SeQuery and SeGraph are each effective independently and provide complementary benefits when used together.

Related papers

• Inference-Time Graph Engineering for Multi-Agent LLM Workflows [51.56038180639833]
  We introduce ReActNet, a training-free framework that compiles a query and a set of role-specialized agents into a sequence of directed communication graphs.<n>We show that ReActNet consistently improves over fixed-topology and learned-topology baselines while maintaining competitive inference cost.
  arXiv  Detail & Related papers  (2026-09-04T23:32:11Z)
• TELLER: Non-intrusive Cross-Layer Root-Cause Analysis for LLM Inference [47.62941623025392]
  We present TELLER, a non-intrusive and Log-aware LLM inference Root-cause analysis framework.<n>TELLER collects NVTX/CUPTI traces and service logs without modifying model binaries.<n>It reconstructs per-request call-chain trees and aligns log lines with corresponding execution steps.<n>On top of these representations, TELLER combines numeric candidate localization with a multimodal root-cause model.
  arXiv  Detail & Related papers  (2026-08-03T09:39:11Z)
• OSDAG: Online Scheduling for Efficient Multi-Robot Collaboration [2.2726869886741383]
  This paper presents OSDAG, a novel framework that integrates LLM-based task reasoning with Directed Acyclic Graph representation and constraint-aware online scheduling.<n> Experiments across five benchmark scenarios demonstrate that OSDAG achieves 5-15x faster reasoning time compared to dialogue-based methods, reduces makespan by up to 38% over sequential baselines, and maintains competitive success rates.
  arXiv  Detail & Related papers  (2026-06-13T11:22:34Z)
• UniRTL: Unifying Code and Graph for Robust RTL Representation Learning [25.37890373797555]
  We propose UniRTL, a multimodal pretraining framework that learns unified RTL representations by jointly leveraging code and CDFG.<n>UniRTL consistently outperforms prior methods, establishing it as a more robust and powerful foundation for advancing hardware design automation.
  arXiv  Detail & Related papers  (2026-05-29T09:18:23Z)
• Training LLMs for Multi-Step Tool Orchestration with Constrained Data Synthesis and Graduated Rewards [76.49428173793386]
  LLMs must invoke multiple dependent APIs in the correct order while propagating intermediate outputs.<n>Training models to handle such faces two obstacles: existing environments focus on simple per-turn function calls with simulated data, and binary rewards.<n>We present a framework addressing both challenges. First, we construct a reinforcement learning environment backed by a large-scale cache of real API responses, enabling a data synthesis pipeline that samples valid multi-step orchestration traces.<n>Second, we propose a graduated reward design that decomposes correctness into atomic validity and orchestration.
  arXiv  Detail & Related papers  (2026-03-25T18:31:39Z)
• Zero-Shot Instruction Following in RL via Structured LTL Representations [54.08661695738909]
  Linear temporal logic (LTL) is a compelling framework for specifying complex, structured tasks for reinforcement learning (RL) agents.<n>Recent work has shown that interpreting instructions as finite automata, which can be seen as high-level programs monitoring task progress, enables learning a single generalist policy capable of executing arbitrary instructions at test time.<n>We propose a novel approach to learning a multi-task policy for following arbitrary instructions that addresses this shortcoming.
  arXiv  Detail & Related papers  (2025-12-02T10:44:51Z)
• Execution Guided Line-by-Line Code Generation [48.996319645671605]
  We present a novel approach to neural code generation that incorporates real-time execution signals into the language model generation process.<n>Our method, Execution-Guided-Free Guidance, dynamically incorporates execution signals as the model generates code.<n> EG-CFG significantly improves code generation approaches, achieving state-of-the-art results across various levels of complexity.
  arXiv  Detail & Related papers  (2025-06-12T17:50:05Z)
• STLCG++: A Masking Approach for Differentiable Signal Temporal Logic Specification [9.039665244779185]
  We present STLCG++, a masking-based approach that parallelizes STL computation and backpropagation across timesteps.<n>We also introduce a smoothing technique to enable the differentiation of time interval bounds, thereby expanding STL's applicability in gradient-based optimization tasks.
  arXiv  Detail & Related papers  (2025-01-08T00:06:43Z)
• SignalGP-Lite: Event Driven Genetic Programming Library for Large-Scale Artificial Life Applications [62.997667081978825]
  Event-driven genetic programming representations have been shown to outperform traditional imperative representations on interaction-intensive problems. Event-driven approach organizes genome content into modules that are triggered in response to environmental signals. SignalGP library caters to traditional program synthesis applications.
  arXiv  Detail & Related papers  (2021-08-01T07:20:49Z)

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.