REVIEW 11 cited by
HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Large Language Models (LLMs) have revolutionized software engineering (SE), showcasing remarkable proficiency in various coding tasks. Despite recent advancements that have enabled the creation of autonomous software agents utilizing LLMs for end-to-end development tasks, these systems are typically designed for specific SE functions. We introduce HyperAgent, an innovative generalist multi-agent system designed to tackle a wide range of SE tasks across different programming languages by mimicking the workflows of human developers. HyperAgent features four specialized agents-Planner, Navigator, Code Editor, and Executor-capable of handling the entire lifecycle of SE tasks, from initial planning to final verification. HyperAgent sets new benchmarks in diverse SE tasks, including GitHub issue resolution on the renowned SWE-Bench benchmark, outperforming robust baselines. Furthermore, HyperAgent demonstrates exceptional performance in repository-level code generation (RepoExec) and fault localization and program repair (Defects4J), often surpassing state-of-the-art baselines.
Forward citations
Cited by 11 Pith papers
-
Remember Your Trace: Memory-Guided Long-Horizon Agentic Framework for Consistent and Hierarchical Repository-Level Code Documentation
MemDocAgent generates consistent hierarchical repository-level code documentation by combining dependency-aware traversal with memory-guided agent interactions that accumulate work traces.
-
Reasoning from Traces: Divergence-Guided Agentic Repair of WebAssembly Discrepancies
WasmMend uses differential trace analysis to localize native-versus-WebAssembly divergence and guides an LLM agent to patch the source, fixing 66.7% of 34 benchmark cases.
-
Autonomous Repair for Multi-Agent Systems via Monte-Carlo Tree Search
An MCTS-based repair loop with partial rollouts and an LLM-as-a-judge reward raises post-repair pass rates by 3–12% over DoVer, ReAct, and Reflexion baselines, backed by a new replayable benchmark StateMAS.
-
AgentRadio: Passive Awareness for Long-Horizon Multi-Agent Collaboration
Background mention-waiting lets four Claude Code agents share discoveries mid-execution and reach 62.1% on SWE-Atlas QnA versus 32.3% for one agent.
-
Temporary Authority, Permanent Effects: Commit-Time Authorization for LLM Agents
Under controlled authority invalidation, agents reach visible goals in 262/270 runs but only 55 remain authorized; CommitGuard blocks stale durable effects when runtimes emit boundary signals.
-
SWE-Adept: An LLM-Based Agentic Framework for Deep Codebase Analysis and Structured Issue Resolution
A two-agent LLM framework that combines agent-directed depth-first code search with step-indexed Git checkpointing resolves up to 4.3% more SWE-Bench issues than prior agentic methods.
-
UTBoost: Rigorous Evaluation of Coding Agents on SWE-Bench
UTBoost adds LLM-generated tests and a repaired log parser to SWE-Bench, uncovering 345 falsely-passing patches and causing dozens of leaderboard ranking shifts.
-
From Virtual Agents to Robot Teams: A Multi-Robot Framework Evaluation in High-Stakes Healthcare Context
Adding a structured knowledge base raised a simulated CrewAI healthcare robot team's process score from 45.29% to 72.94%, but five failure modes, including false completion and poor recovery, persisted.
-
From PowerPoint UI Sketches to Web-Based Applications: Pattern-Driven Code Generation for GIS Dashboard Development Using Knowledge-Augmented LLMs, Context-Aware Visual Prompting, and the React Framework
A knowledge-augmented LLM pipeline converts user-sketched UI wireframes from PowerPoint into modular React-based GIS dashboards, demonstrated on two environmental data applications.
-
The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks
AI coding agents that overthink, spending effort on internal reasoning instead of acting, perform worse, and selecting lower-overthinking attempts improves success by ~30% with 43% less compute.
-
OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation
A hierarchical multi-agent framework with a domain-agnostic planner trained by SFT and DPO achieves 69.70% on GAIA and lifts a Qwen2.5-32B planner by 16.37 points.
Discussion (0). Continue with ORCID to comment.