WeSearch
Hub / Tags / Llm Agents
TAG · #LLM-AGENTS

Llm Agents coverage.

Every story in the WeSearch catalog tagged with #llm-agents, chronological, with view counts. Subscribe to the per-tag RSS feed to follow this topic in your reader of choice.

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"

RELATED TAGS
#ai1#runtime-safety1#elias-hossain1#md-mehedi-hasan-nipu1#tasfia-nuzhat-ornee1#rajib-rana1#niloofar-yousefi1#arxiv1
ARXIV.ORG

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-…

9 views ·
#profile-graph#memory#agents
ARXIV.ORG

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…

10 views ·
#artificial intelligence#runtime safety
ARXIV.ORG

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…

16 views ·
#agentabstain#agents#know
ARXIV.ORG

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 …

75 views ·
#toward#auditable#scientists
ARXIV.ORG

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…

29 views ·
#grounded#iterative#language
ARXIV.ORG

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…

31 views ·
#tool-augmented#agents#perform
GITHUB

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…

36 views ·
#show#agentnexus#coordinate
ARXIV CS.AI

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…

46 views ·
#artificial intelligence#machine learning#memory management
ARXIV CS.AI

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…

42 views ·
#artificial intelligence#machine learning#language models
ARXIV CS.AI

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…

39 views ·
#artificial intelligence#autonomous driving#machine learning
GITHUB

CVE-Bench: testing LLM agents on real-world vulnerability patches

Benchmarking LLMs on real-world CVE patching…

34 views ·
#ai#security#vulnerabilities
R/NETSEC

I evaluated 5 LLM agents on patching real-world CVEs. Here is what I found.

40 views ·
ARXIV.ORG

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,…

27 views ·
#artificial intelligence#machine learning#spreadsheets
DEV.TO (TOP)

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.…

28 views ·
#reinforcementlearning#llmagents#tooluse
ARXIV CS.AI

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…

37 views ·
#artificial intelligence#machine learning#language models
ARXIV CS.AI

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…

45 views ·
#artificial intelligence#machine learning#cuda
ARXIV CS.AI

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…

27 views ·
#cybersecurity#artificial intelligence#memory poisoning
ARXIV CS.AI

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…

36 views ·
#software engineering#artificial intelligence#machine learning
DEV.TO (TOP)

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...…

30 views ·
#security#ai#vulnerability-research
ARXIV CS.AI

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…

42 views ·
#artificial intelligence#machine learning#evaluation
ARXIV CS.AI

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…

33 views ·
#artificial intelligence#machine learning#cloud computing
ARXIV CS.AI

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…

29 views ·
#artificial intelligence#lipid design#nucleic acid delivery
R/DEVOPS

How are you securing the DBs when product teams deploy LLM agents?

31 views ·
DEV.TO (TOP)

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.…

17 views ·
#ai#opensource#python
ARXIV CS.AI

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 …

25 views ·
#artificial intelligence#machine learning#game theory
R/MACHINELEARNING

Sponsio: Deterministic Contract Layer for LLM Agents [P]

34 views ·
DEV.TO (TOP)

Distributed Tracing for LLM Agents: When MCP Makes Tool Calls Observable

How application observability extends to stochastic agent loops — and why the tool boundary...…

23 views ·
#ai#observability#llm
ARXIV.ORG

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…

31 views ·
#software engineering#artificial intelligence#code generation
DEV.TO (TOP)

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…

27 views ·
#nlp#research#llm
DEV.TO (TOP)

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...…

38 views ·
#ai#security#technology
ARXIV CS.AI

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 …

26 views ·
#artificial intelligence#machine learning#software engineering
ARXIV CS.AI

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…

31 views ·
#artificial intelligence#machine learning#software engineering
ARXIV CS.AI

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…

27 views ·
#artificial intelligence#privacy#machine learning
ARXIV CS.AI

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…

27 views ·
#artificial intelligence#finance#trading
ARXIV CS.AI

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 …

22 views ·
#artificial intelligence#programming#machine learning
ARXIV CS.AI

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…

17 views ·
#artificial intelligence#machine learning#software engineering
ARXIV CS.AI

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…

21 views ·
#artificial intelligence#machine learning#long-context
ARXIV CS.AI

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…

31 views ·
#artificial intelligence#software engineering#runtime architecture
ARIZEN

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.…

24 views ·
#artificial intelligence#machine learning#technology
ANTIREZ

A new EDIT tool for LLM agents

17 views ·
ARXIV CS.AI

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…

27 views ·
#artificial intelligence#machine learning#multiagent systems
ARXIV CS.AI

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…

23 views ·
#artificial intelligence#machine learning#toxic information
ARXIV CS.AI

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…

22 views ·
#artificial intelligence#machine learning#technology
ARXIV CS.AI

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…

24 views ·
#artificial intelligence#machine learning#memory selection
ARXIV CS.AI

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…

25 views ·
#artificial intelligence#machine learning#programming
ARXIV CS.AI

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 …

21 views ·
#artificial intelligence#memory safety#longitudinal study
MEDIUM

The Infrastructure Behind Making Local LLM Agents Useful

Lessons from building a fast, reliable single-cell analysis agent on open-weight models…

29 views ·
#technology#artificial intelligence#data analysis
GITHUB

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…

32 views ·
#technology#ai#communication
ARXIV CS.AI

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-…

25 views ·
#artificial intelligence#machine learning#autonomous agents
ARXIV CS.AI

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. …

32 views ·
#security#artificial intelligence#cryptography
GITHUB

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.…

22 views ·
#technology#software#ai
HACKER NEWS (AI / LLM)

Five LLM agents play Werewolf in-browser, each with a private DuckDB

29 views ·
ARXIV.ORG

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…

20 views ·
#artificial intelligence#machine learning#neuroscience