arXiv AI
Jul 24
Delivery, Not Storage: Cue-Anchored Working Memory as a Harness Property for Coding Agents
arXiv:2607. 20972v1 Announce Type: new Abstract: Coding agents ship with one kind of memory: documents.
The Working Set of a Coding Agent: Coherence Debt in Repository-Scale Tasks
arXiv:2608. 16630v1 Announce Type: cross Abstract: Repository-scale coding requires an agent to keep tests, imports, configuration, and migration rules consistent within a bounded context window.
Related stories
arXiv AI
Jul 14
What Context Does a Coding Agent Actually Need to Act?
arXiv:2607. 09691v1 Announce Type: cross Abstract: A modern coding agent can hold an entire repository in its context window.
arXiv AI
Aug 6
EA-Graph: Artifact-Anchored Verification Memory for Coding Agents under Upstream Drift
arXiv:2608. 04278v1 Announce Type: cross Abstract: Coding agents increasingly work across sessions, but prose notes can preserve a conclusion without the program state that supported it.
arXiv AI
Jul 14
When Does Restricting a Coding Agent to execute_code Help? A Regime $\times$ Agent-Design Ablation
arXiv:2607. 10569v1 Announce Type: cross Abstract: Modern coding agents expose multiple tool surfaces -- IDE primitives, bash, and Model Context Protocol (MCP) code-execution -- and the field has shipped three contradictory claims about which one matters.
arXiv AI
5d ago
Dead text or binding clause? Measuring and restoring constraint influence in black-box LLM dialogues
arXiv:2608. 12599v1 Announce Type: new Abstract: Multi-turn dialogues let users revoke constraints as easily as impose them, but revocation does not reliably take effect: models keep enacting withdrawn requirements (occasionally beneath comments asserting their removal), a failure we call \emph{behavioral relapse}, or revocation inertia.
arXiv AI
Aug 6
ORCA-bench: How Ready Are Language Model Agents for Oncall?
arXiv:2607. 28545v2 Announce Type: replace-cross Abstract: Large language models can write, patch, and search code, but oncall root cause analysis (RCA) demands something different: reasoning over noisy metrics, logs, traces, and source code, starting from ambiguous user-facing reports, often hours after the incident began.
arXiv AI
5d ago
Capability Sheaves for Compositional Agent-Harness Repair: Controlled Quotients and a Real-Repository Stress Test
arXiv:2608. 13228v1 Announce Type: new Abstract: Agent harnesses combine retrieval, routing, state, provenance, and verification, but locally successful components may disagree on shared state.
arXiv Machine Learning
Jun 25
Reclaim Evaluation: A Lossy Memory Is Worse Than an Empty One
arXiv:2606. 25449v1 Announce Type: cross Abstract: A language model's memory can be worse than having no memory at all.
arXiv AI
Jun 6
TOKI: A Bitemporal Operator Algebra for Contradiction Resolution in LLM-Agent Persistent Memory
arXiv:2606. 06240v1 Announce Type: cross Abstract: Persistent memory for an LLM agent is a write-heavy substrate: every belief update is a versioned write, and a new claim may contradict a stored one.
arXiv AI
Jul 15
Do AI Agents Know When a Task Is Simple? Toward Complexity-Aware Reasoning and Execution
arXiv:2607. 13034v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly automate multi-step engineering and informatics workflows, yet they rarely ask how much effort a task actually requires.
Hugging Face Trending Papers
Jun 24
Reclaim Evaluation: A Lossy Memory Is Worse Than an Empty One
A language model's memory can be worse than having no memory at all. Give a model a memory that kept a wrong conclusion but dropped the work behind it, and it emits that stale value as a confident answer; give the same model an empty memory and it abstains.
arXiv AI
Jul 17
Why Git Is the Memory Solution for the Agentic Development Lifecycle
arXiv:2607. 14390v1 Announce Type: cross Abstract: Coding agents now produce a growing share of a team's code, while the reasoning behind each change -- the alternatives weighed, the constraints discovered, the approaches rejected -- is trapped in assistant transcripts that vanish with the session.