53 stories tagged with #llm-agents, in publish-time order across the WeSearch catalog. Tag pages update as new stories ingest.
⌘ RSS feed for this tag → or search "Llm Agents"
Profile-Graph Memory for LLM Agents: Implicit Cross-Entity Traversal through Narrative Profiles
arXiv:2607.19359v1 Announce Type: new Abstract: Long-term memory is essential for LLM agents that interact across sessions, yet current memory benchmarks primarily evaluate single-…
NEXUS: Structured Runtime Safety for Tool-Using LLM Agents
arXiv:2607.19356v1 Announce Type: new Abstract: Tool-using LLM agents increasingly execute high-impact actions, making runtime safety monitoring essential. We present NEXUS (Neural…
AgentAbstain: Do LLM Agents Know When Not to Act?
Agent systems based on large language models (LLMs) are increasingly deployed for autonomous tasks, yet existing evaluations mostly focus on task success rather than whether agents…
Toward Auditable AI Scientists: A Hypothesis Evolution Protocol for LLM Agents
arXiv:2607.09195v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly expected to play a central role in AI-driven scientific discovery. Equipped with …
Grounded Iterative Language Planning: How Parameterized World Models Reduce Hallucination Propagation in LLM Agents
arXiv:2606.27806v1 Announce Type: new Abstract: World models for language agents come in two useful forms. An agent-based world model calls an LLM API and reasons flexibly in langu…
How Do Tool-Augmented LLM Agents Perform on Real-World Energy Analytics Tasks?
arXiv:2606.26346v1 Announce Type: new Abstract: Agentic benchmarks have emerged across general-purpose and domain-specific settings, including finance, coding, law, and drug discov…
Show HN: AgentNexus – coordinate LLM agents by service boundary, not role
A service-boundary-aware document exchange center for coordinating heterogeneous LLM code agents via MCP. Implements versioned Markdown store, pub-sub notifications, and diff-aware…
DELTAMEM: Incremental Experience Memory for LLM Agents via Residual Trees
Large Language Model (LLM)-based agents increasingly rely on memory to learn from experiences over continual interactions. However, storing experiences as independent, flat units l…
Uncertainty-Aware Clarification in LLM Agents with Information Gain
Large Language Model (LLM) agents often operate under underspecified user instructions, where latent uncertainty over user intent leads to erroneous tool actions. To address this c…
EvoDrive: Pareto Evolution for Safety-Critical Autonomous Driving via Self-Improving LLM Agents
Generating safety-critical scenarios is essential for validating and improving autonomous driving systems, yet it inherently requires maximizing adversariality to expose failures w…
CVE-Bench: testing LLM agents on real-world vulnerability patches
Benchmarking LLMs on real-world CVE patching…
I evaluated 5 LLM agents on patching real-world CVEs. Here is what I found.
Spreadsheet-RL: Advancing LLM Agents on Realistic Spreadsheet Tasks
Spreadsheet systems (e.g., Microsoft Excel, Google Sheets) play a central role in modern data-centric workflows. As AI agents grow increasingly capable of automating complex tasks,…
ARTIST: RL-Powered Tool Use for LLM Agents Explained
How Microsoft's ARTIST framework uses outcome-based RL to train LLMs that interleave tool calls inside reasoning chains — no step supervision required.…
AGORA: Adapter-Grounded Observation-Action Retention for Inference-Free Prompt Compression in LLM Agents
The token-level extractive compressors widely used for general LM context are structurally inappropriate for LLM agents: across 17 (env, backbone, method) cells spanning two indepe…
Towards Feedback-to-Plan Decisions for Self-Evolving LLM Agents in CUDA Kernel Generation
Large language models (LLMs) have shown strong empirical gains as self-evolving agents for CUDA kernel generation, driven by feedback-conditioned planning across generations. Howev…
MemMorph: Tool Hijacking in LLM Agents via Memory Poisoning
LLM-driven agents are capable of selecting external tools to complete users' tasks. However, attackers could compromise such process, steering agents toward inappropriate/wrong too…
SetupX: Can LLM Agents Learn from Past Failures in Functionality-Correct Code Repository Setup?
Functionality-correct repository setup aims to configure execution environments (e.g., dependencies, build scripts) to successfully execute a repository's documented features. It p…
LLM Agents Are Now Finding Zero-Days: How AI is Autonomously Rewriting the Rules of Vulnerability Research
LLM Agents Are Now Finding Zero-Days: How AI is Autonomously Rewriting the Rules of...…
Stop Comparing LLM Agents Without Disclosing the Harness
This position paper argues that, for long-horizon tasks evaluated across models with comparable frontier capability, the agent execution harness, namely the infrastructure layer th…
Hera: Learning Long-Horizon Coordination for Device-Cloud Collaborative LLM Agents
Large language model (LLM) agents excel at solving complex long-horizon tasks through autonomous interaction with environments. However, their real-world deployment faces a fundame…
LipoAgent: Coordinating Fine-Tuned LLM Agents for Safer Lipid Design
Lipid nanoparticles (LNPs) are among the most clinically mature platforms for nucleic acid delivery, yet designing lipids that are both effective and biologically safe remains a ma…
How are you securing the DBs when product teams deploy LLM agents?
GBase: Building LLM Agents That Actually Learn from Their Mistakes
A personal story about building an open-source framework for recursive self-improving agents — with real experimental results.…
PrefBench: Evaluating Zero-Shot LLM Agents in Hidden-Preference Personalized Pricing Negotiations
Personalized pricing negotiations are a challenging testbed for LLM agents because successful interaction does not guarantee profitable decision making. A seller may produce valid …
Sponsio: Deterministic Contract Layer for LLM Agents [P]
Distributed Tracing for LLM Agents: When MCP Makes Tool Calls Observable
How application observability extends to stochastic agent loops — and why the tool boundary...…
Constraint Decay: The Fragility of LLM Agents in Back End Code Generation
Large Language Model (LLM) agents demonstrate strong performance in autonomous code generation under loose specifications. However, production-grade software requires strict adhere…
LMR-BENCH: Can LLM Agents Reproduce NLP Research Code? (EMNLP 2025)
LMR-BENCH (EMNLP 2025) benchmarks LLM agents on reproducing code from 23 NLP papers. This PoC explains the masking methodology, evaluation axes, and what the results mean for AI-as…
I Built a Browser SDK That Detects LLM Agents. Here's How It Works.
Every bot detection system I've seen works with two actors: human or bot. Block the bot, let the...…
AgentAtlas: Beyond Outcome Leaderboards for LLM Agents
Large language model agents now act on codebases, browsers, operating systems, calendars, files, and tool ecosystems, but the benchmarks used to evaluate them are fragmented: each …
Insights Generator: Systematic Corpus-Level Trace Diagnostics for LLM Agents
Diagnosing failures in LLM agents remains largely manual. Practitioners inspect a small subset of execution traces, form ad-hoc hypotheses, and iterate. This process misses pattern…
POLAR-Bench: A Diagnostic Benchmark for Privacy-Utility Trade-offs in LLM Agents
LLM agents increasingly have access to private user data and act on the user's behalf when interacting with third-party systems. The user defines what may and must not be shared, a…
Agentic Trading: When LLM Agents Meet Financial Markets
A growing body of work explores how Large Language Models (LLMs) can be embedded in trading systems as agents that perceive market information, retrieve context, reason about decis…
Formal Skill: Programmable Runtime Skills for Efficient and Accurate LLM Agents
Large Language Model (LLM) agents increasingly act inside real workspaces, where tools and skills determine whether model reasoning becomes reliable action. Existing skills remain …
Prior Knowledge or Search? A Study of LLM Agents in Hardware-Aware Code Optimization
LLM discovery and optimization systems are increasingly applied across domains, implementing a common propose-evaluate-revise loop. Such optimization or discovery progresses via co…
PEEK: Context Map as an Orientation Cache for Long-Context LLM Agents
Large language model (LLM) agents increasingly operate over long and recurring external contexts, like document corpora and code repositories. Across invocations, existing approach…
A Methodology for Selecting and Composing Runtime Architecture Patterns for Production LLM Agents
Production LLM agents combine stochastic model outputs with deterministic software systems, yet the boundary between the two is rarely treated as a first-class architectural object…
When More Context Makes LLM Agents Worse
More context does not automatically improve reasoning. Extra tokens can dilute signal, blur control boundaries, and make agent behavior less reliable.…
A new EDIT tool for LLM agents
ANNEAL: Adapting LLM Agents via Governed Symbolic Patch Learning
LLM-based agents can recover from individual execution errors, yet they repeatedly fail on the same fault when the underlying process knowledge--operator schemas, preconditions, an…
State Contamination in Memory-Augmented LLM Agents
LLM agents increasingly rely on persistent state, including transcripts, summaries, retrieved context, and memory buffers, to support long-horizon interaction. This makes safety de…
NeuSymMS: A Hybrid Neuro-Symbolic Memory System for Persistent, Self-Curating LLM Agents
We present NeuSymMS, an adaptive memory system that enables large language model (LLM) agents to learn, remember, and reason about users across sessions via a hybrid neuro-symbolic…
Causal Intervention-Based Memory Selection for Long-Horizon LLM Agents
Long-horizon LLM agents rely on persistent memory to support interactions across sessions, yet existing memory systems often retrieve context using semantic similarity or broad his…
Harnessing LLM Agents with Skill Programs
Equipping LLM agents with reusable skills derived from past experience has become a popular and successful approach for tackling complex and long-horizon tasks. However, such lesso…
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents
Safety evaluations of memory-equipped LLM agents typically measure within-task safety: whether an agent completes a single scenario safely, often under adversarial conditions such …
The Infrastructure Behind Making Local LLM Agents Useful
Lessons from building a fast, reliable single-cell analysis agent on open-weight models…
Agent Braille – 8-bit state encoding for LLM agents, ~92% fewer tokens than JSON
Deterministic 8-bit machine-to-machine protocol for AI agent state. ~92% fewer state-tracking tokens on real Claude Code sessions, a proven single-bit-error-safe command code, f…
Look Before You Leap: Autonomous Exploration for LLM Agents
Large language model based agents often fail in unfamiliar environments due to premature exploitation: a tendency to act on prior knowledge before acquiring sufficient environment-…
Hidden in Memory: Sleeper Memory Poisoning in LLM Agents
Large language models are increasingly augmented with persistent memory, allowing assistants to store user-specific information across sessions for personalization and continuity. …
A chat-less interface to collaborate with LLM agents directly from your files
A good interface is invisible. Contribute to piqoni/piqo-extension development by creating an account on GitHub.…
Five LLM agents play Werewolf in-browser, each with a private DuckDB
HeLa-Mem: Hebbian Learning and Associative Memory for LLM Agents
Long-term memory is a critical challenge for Large Language Model agents, as fixed context windows cannot preserve coherence across extended interactions. Existing memory systems r…