44 articles mentioning Coding-Monkey-Gemma-GGUF
arXiv:2610.25916v2 Announce Type: replace-cross Abstract: As coding models and agent harnesses become more capable, reliable security verification is becoming a central bottleneck. Improving secure code generation requires a signal whose reported progress remains aligned with actual program behavior
arXiv:2610.27377v1 Announce Type: new Abstract: Large language model (LLM) agents now autonomously complete long-horizon tasks, such as repository-level coding, through hundreds of think-act steps, yet the experience each run produces is rarely reused on the next. Prior memory systems concentrate on
arXiv:2410.21647v5 Announce Type: replace-cross Abstract: Recently, a number of repository-level code generation benchmarks-such as CoderEval, DevEval, RepoEval, RepoBench, and LongCodeArena-have emerged to evaluate the capabilities of large language models (LLMs) beyond standalone benchmarks like H
arXiv:2610.28354v1 Announce Type: new Abstract: Spatial reasoning asks a model to work out where objects are in 3D space, how they relate to one another, and how they move. Agentic VLMs have recently brought large improvements on such tasks by letting the model actively gather evidence with 3D perce
arXiv:2610.27046v1 Announce Type: new Abstract: As AI systems begin to resolve open research problems, reliable verification becomes increasingly important. Formal mathematics provides a trusted framework for mathematical reasoning, enabling agents to produce machine-checkable proofs while conductin
arXiv:2610.27327v1 Announce Type: new Abstract: Coding agents can answer analytical questions over a data lake by discovering, cleaning, and joining the relevant data. However, they discard this work after each question and redo it from scratch for the next one. Tool evolution, which automatically b
arXiv:2606.28235v2 Announce Type: replace-cross Abstract: In July 2026, about 1,200 AI agents in an internal OpenAI evaluation, meant to run in isolation, used a shared package server as a message board, and about 700 of them joined an attack on Hugging Face. An automated scorer judged each agent on
OpenCode is an open source AI coding agent that's become a popular alternative to Claude Code and Cursor. But hackers got into part of its online platform and stole some users’ API keys, and the AI tools it turned to for help kept refusing to look at the malicious code.
Learn how OpenAI is improving ChatGPT across low-resource programming languages, with new evaluations for software engineering, SQLite, and COBOL migration.
arXiv:2610.10619v1 Announce Type: cross Abstract: Large language model (LLM) agents are rapidly reshaping software engineering, accompanied by an explosion of new code benchmarks. Yet nearly all existing benchmarks still rely on the same decades-old criterion: a solution is correct if it passes a fi
arXiv:2610.11593v1 Announce Type: cross Abstract: Coding agents produce large, tangled patches that mix multiple development purposes, making the code hard to review and maintain. Commit untangling offers the promise of organizing such large patches into untangled, manageable commits. This paper emp
arXiv:2610.11450v1 Announce Type: new Abstract: We study how a coding agent learns across a sequence of abstract reasoning tasks. The agent runs on a frozen foundation model inside a fixed harness and acts by writing and running Python and shell scripts. It retains no state across turns other than i
arXiv:2610.10610v1 Announce Type: cross Abstract: Repository benchmarks (e.g., SWE-bench) for coding agents often assume that lines of code edited can predict task difficulty, but such datasets' poor control over code and task types makes it hard to know which abilities truly drive agent errors. We
arXiv:2610.10961v1 Announce Type: cross Abstract: Coding agents increasingly share a workstation while drawing on separate providers and subscription allowances. A second agent can inspect a completed answer, but the call spends another pool and may provide no substantive finding. We describe an adv
arXiv:2610.08900v2 Announce Type: replace Abstract: Agentic coding makes code generation cheap, but reliable completion remains difficult: the agent that writes the code is a weak judge of whether it is done. We present Humanize, a multi-agent orchestration workflow for agentic coding built around j
arXiv:2610.08662v2 Announce Type: replace Abstract: As coding agents increasingly undertake real-world work autonomously, judging whether their risk treatments are warranted has become important. Existing work evaluates related agent behaviors from separate perspectives, but lacks a systematic frame
arXiv:2610.04838v2 Announce Type: replace Abstract: As coding agents take on long-horizon software evolution tasks spanning multiple files and stages, longer execution trajectories introduce two coupled challenges: (1) accumulated histories strain context budgets, and (2) repository changes can inva
arXiv:2609.33987v2 Announce Type: replace Abstract: Long-horizon coding agents need timely corrections, yet feedback can be ineffective or even harmful when it misjudges ongoing work or fails to address the underlying problem. Existing critics focus on evaluating trajectories and generating feedback
arXiv:2610.11559v1 Announce Type: cross Abstract: Coding assistants such as Claude Code and Codex have become a major application of LLM agents, yet existing benchmarks remain far from real-world use, particularly in task horizon and interaction length. Code assistants require completing long chains
arXiv:2603.28744v2 Announce Type: replace Abstract: The linear representation hypothesis states that neural network activations encode high-level concepts as linear mixtures. However, under superposition, this encoding is a projection from a higher-dimensional concept space into a lower-dimensional
arXiv:2610.07257v1 Announce Type: new Abstract: Developers increasingly run a fleet of coding agents side by side on one workstation. The tools they reach for, terminal multiplexers like tmux and a new generation of agent managers, were built to arrange windows, not to govern memory. When ten agents
arXiv:2610.08514v1 Announce Type: new Abstract: Execution feedback lets coding agents revise programs and learn from their own corrections. A correction's learning weight should reflect both the transitions supported by its executions and the amount of evidence behind that support. We introduce Effe
arXiv:2610.07261v1 Announce Type: new Abstract: A team of coding agents can look fine agent by agent yet fail as a team: each passes its own tests while the merged result is broken, and single-agent evaluation never catches it. As teams run several LLM coding agents in parallel on one codebase, the
arXiv:2610.09633v1 Announce Type: cross Abstract: The evaluation of coding agents generally strives to be as realistic as possible. In our study, we collect 4,782 agent sessions of real software engineers in JetBrains IDEs, which we call Production Sessions. Since our subject is interactive agents,
arXiv:2609.33678v3 Announce Type: replace Abstract: We introduce SWE-Game, a benchmark of 247 tasks grounded in 41 executable reference Godot games spanning 13 gameplay categories in 2D and 3D. Five task types cover development from a brief, implementation from a game design document, skeleton compl
arXiv:2606.05647v2 Announce Type: replace Abstract: AI coding agents are increasingly embedded in real-world software development, collaborating with human developers while gaining broader access to codebases and tools. This creates a new attack surface: an agent can exploit human trust to sabotage
arXiv:2610.01108v2 Announce Type: replace Abstract: Retrieval-based speculative decoding (SD) drafts tokens by copying continuations from existing text, which suits coding agents that repeatedly reproduce code, logs, and earlier attempts. Yet existing methods fall short in agent pipelines: much of t
arXiv:2604.22750v3 Announce Type: replace-cross Abstract: The wide adoption of AI agents in complex human workflows is driving rapid growth in LLM token consumption. When agents are deployed on tasks that require a significant amount of tokens, three questions naturally arise: (1) Where do AI agents
arXiv:2610.02456v1 Announce Type: cross Abstract: AI coding agents are untrusted system components, yet they require autonomy on the developer machines they run on. This contradiction is a security problem. Sandboxes provide an isolated environment, but for local macOS development, the existing loca
arXiv:2609.20822v2 Announce Type: replace-cross Abstract: Coding agents have emerged as a promising paradigm for robot manipulation: a language model writes the robot controller as a program, and agents built in this way now operate robots without robot-specific training. Whether this paradigm is al
arXiv:2610.02952v1 Announce Type: cross Abstract: Test-driven development gives AI coding agents executable requirements for implementing software. Because these agents can adapt their implementations to the examples they observe, passing a predetermined collection of tests can leave substantial par
arXiv:2609.39533v3 Announce Type: replace Abstract: During reinforcement learning with verifiable rewards (RLVR), large language models (LLMs) can exploit loopholes in their environments to obtain high rewards without improving the intended capabilities, i.e., reward hacking. Despite its risks to tr
arXiv:2610.00890v1 Announce Type: new Abstract: Coding agents often fail in the last mile: they build most of a feature but drop a requirement, test only the cases their implementation already handles, break behavior that was supposed to stay intact, or validate against an unchecked assumption. We a
arXiv:2609.39957v1 Announce Type: cross Abstract: Coding agents solve repository-level tasks through sequences of actions, where a single erroneous action can misdirect subsequent decisions and increase recovery costs. Existing approaches use execution feedback for recovery or specialized checks to
arXiv:2610.00650v1 Announce Type: cross Abstract: The performance of AI coding agents is highly dependent on their underlying coding rules. However, existing coding rules are typically hand-crafted and fixed, making the process labor-intensive and often suboptimal. In this work, we propose RuleEvolv
arXiv:2609.39022v2 Announce Type: replace-cross Abstract: Coding agents need to establish that a program satisfies a specification and that the specification captures the requested behavior. We study how expert diagnosis of verification failures can become reusable guidance for this work. Our approa
arXiv:2604.20779v2 Announce Type: replace Abstract: AI coding agents are being adopted at scale, yet we lack empirical evidence on how people actually use them and how much of their output is useful in practice. We present SWE-chat, the first large-scale dataset of real coding agent sessions collect
arXiv:2609.34422v2 Announce Type: replace-cross Abstract: Language-model agents increasingly tackle long-horizon tasks whose interaction histories exceed the model's active context. Recent work has begun to use reinforcement learning to make memory control part of the policy, often relying on predef
arXiv:2609.38606v1 Announce Type: cross Abstract: As vibe coding becomes increasingly capable and widespread, security vulnerabilities in even functionally correct solutions are a growing concern. When investigating functionally correct but insecure solutions, we find that the insecure agent is less
arXiv:2609.38345v1 Announce Type: cross Abstract: Multi-agent coding systems are designed to tackle complex software engineering tasks through collaboration. However, existing evaluations typically assume configured organizations are followed faithfully, whereas reality differs. This behavioral gap,
arXiv:2609.39081v1 Announce Type: cross Abstract: We spent five weeks using an LLM coding agent on open problems in coding theory: finding large sets of four-letter words, such as DNA barcodes, that stay far apart in edit distance. The agent wrote the verifiers and search code; a human chose the pro
arXiv:2609.29718v2 Announce Type: replace Abstract: Coding agents are increasingly moving beyond text-based software tasks to reconstruct visual targets through code. This capability, visual coding, requires agents to translate their understanding of visual targets into executable code. Slides provi
arXiv:2610.01023v1 Announce Type: cross Abstract: Coding agents can return plausible patches that omit required behavior. These failures are hard to review because long traces and confident summaries often hide what was missed. We ask when a nominally weaker reviewer can reliably decide whether a pa
arXiv:2609.37575v1 Announce Type: cross Abstract: We argue that dividing codec design into Coding for Machines (CfM) and Coding for Humans (CfH) is a misleading distinction for deciding what information a codec may discard. Receiver identity does not determine admissible information loss. The requir