MARS (Multi-Agent Relay of Specialized LLMs) is a prompt-only framework that assigns specialized LLM agents—each focused on a particular algorithmic domain such as dynamic programming, graphs, or geometry—to collaboratively solve competitive programming problems. Retrieval-augmented generation selects a small team of relevant specialists for each problem, and the agents iteratively refine a C++17 solution through sandboxed testing, passing structured packets between them until a final infrastructure-fixer normalizes the code. On the CodeContests benchmark, MARS achieves a pass rate of 0.624 with Gemma 4, improving over direct prompting by 14.4 percentage points while reducing wall‑clock cost and token‑spend variance compared to CodeSIM.
Large Language Models excel at code generation, yet competitive programming exposes a persistent failure mode: existing multi-agent pipelines distribute work over generic planner, coder, and debugger...
arXiv:2608. 04804v1 Announce Type: cross Abstract: Frontier language models can resolve repository-level software issues, but each attempt is expensive, and existing routers select a model from the issue text alone.
arXiv:2606. 31174v1 Announce Type: new Abstract: Production large language-model (LLM) agents are increasingly deployed not as lone problem-solvers but as managers: a main model creates specialized subagents, delegates work, and orchestrates their parallel, asynchronous returns through dynamic workflows.
arXiv:2606. 10662v1 Announce Type: cross Abstract: Multi-agent systems (MAS) can scale large language model reasoning at test time by decomposing complex problems into parallel subtasks.
arXiv:2609.18959v1 Announce Type: new Abstract: LLM code-generation systems usually choose a target programming language before decoding and treat that choice as fixed. We show that, for language-fle...
arXiv:2604. 26963v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly deployed as the execution core of autonomous agents rather than as standalone text generators.
arXiv:2607. 20499v1 Announce Type: new Abstract: Large Language Models generate plausible backend code, but a single-pass paradigm provides no guarantee of correctness or runtime reliability.
UniACE is a unified framework that standardizes the evaluation of large language model (LLM) agents by representing each benchmark as an instruction–tool–environment triplet and running models through a shared, task‑agnostic harness in isolated runtimes. It preserves native success criteria, offers an offline mode for dynamic‑resource tasks, and standardizes efficiency metrics, execution records, and failure attribution. Applying UniACE to 7 benchmarks across 24 domains and 15 models revealed significant score shifts, ranking reversals, and sensitivity to evidence representation, highlighting the impact of evaluation configuration on reported agent performance.
arXiv:2609.38269v1 Announce Type: cross Abstract: Coding agents are increasingly asked to build software rather than patch it, yet benchmarks for from-scratch repository construction are mostly limit...
arXiv:2607. 20531v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly deployed over Model Context Protocol (MCP) servers, yet the benchmarks used to evaluate them score the final answer or a fixed "ground-truth" list of tools, both of which are fragile once the underlying data is live and stateful.
arXiv:2609.15982v1 Announce Type: cross Abstract: Skills extend an LLM agent beyond its parametric knowledge, and the gain they promise rests on picking the right one. Deployed harnesses route by pre...
arXiv:2608. 00101v1 Announce Type: cross Abstract: AI coding agents like GitHub Copilot, Claude Code, and Codex interleave multi-step LLM inference with tool execution, creating a workload different from chatbots.