language-model agents
PulseAugur coverage of language-model agents — every cluster mentioning language-model agents across labs, papers, and developer communities, ranked by signal.
4 day(s) with sentiment data
-
AI aids discovery of new quantum computing magic-state factories
Researchers have developed new AI-assisted methods to discover more efficient magic-state factories for fault-tolerant quantum computing. These methods leverage symmetry restrictions and language-model agents to overcom…
-
New ReFract benchmark tests language model agents' perspective awareness
Researchers have introduced ReFract, a new benchmark designed to evaluate the 'Perspective Awareness' of language model agents. This benchmark, comprising 150 expert-validated entries, assesses an agent's ability to tai…
-
New framework audits false alarms in language-model agent safety monitors
A new research paper introduces a novel framework for auditing false alarms generated by safety monitors in language-model agents. The proposed method addresses the challenge of distinguishing between genuine and false …
-
New research tackles long-horizon decision-making for language agents · 4 sources tracked
Researchers are developing new methods to improve the long-horizon decision-making capabilities of language agents. One approach, RELACE, uses retrospective likelihood scoring to assess actions based on their plausibili…
-
AI agents' belief formation mirrors complex social contagion dynamics
Researchers have developed a new model to understand how beliefs spread among AI agents, focusing on the dynamics of social contagion. The study empirically measures how language model agents adopt claims based on peer …
-
New distillation method improves small language model agents
Researchers have developed Harness-Aware Distillation (HAD), a new method for training smaller language model agents. HAD focuses on teaching the student agent the unique abilities of the teacher agent that are not prov…
-
AI agents exhibit complex adversarial market behavior beyond transactions
A new research paper titled "Your Agent Says Yes: Interpreting Adversarial Market Behavior Beyond Individual Transactions" explores how language-model agents can exhibit complex, adversarial market behaviors that are no…
-
New benchmarks reveal LLM agent limitations in multilingual tasks and collaboration
New research explores the capabilities of large language model (LLM) agents in complex, multilingual, and collaborative environments. WorldBench, a new benchmark, tests LLM agents across 1,600 tasks in seven languages a…
-
RePolicy uses reinforcement learning for agent safety policy invocation
Researchers have developed RePolicy, a novel agent safeguard that utilizes reinforcement learning to dynamically invoke safety policies for language model agents. This approach addresses limitations of current methods b…
-
AI Agents Can Be Misaligned in Groups Even If Aligned Alone
A new arXiv paper explores the phenomenon of "adversarial capture" in populations of language-model agents, where individual agents that are well-aligned in isolation can be influenced by others to make misaligned decis…
-
New audit predicts social mechanism scalability in agent societies
Researchers have developed a new audit method to predict how social mechanisms will perform as the number of interacting language-model agents increases. This audit assesses the frequency of a mechanism's operation, age…
-
New research reveals algorithmic collusion masked by competitive pricing in AI agents
A new research paper explores the concept of algorithmic collusion, demonstrating that competitive pricing can mask profitable conspiracies. The study reveals that bidding agents can coordinate through the distribution …
-
AI agents improve molecular property prediction via closed-loop research
Researchers have developed a closed-loop auto-research system that extends automated machine learning beyond fixed datasets to dynamically alter the research workflow. This system utilizes language-model agents to edit …
-
LLM Agents Optimize Costs via Skill Rewriting and Translation Policies
Researchers are exploring cost-aware strategies for large language model agents to improve efficiency and performance. One paper introduces a framework for skill rewriting that optimizes for cost by preserving essential…
-
AI agents evaluated for goal-directedness and state binding
Two new research papers explore the internal workings and evaluation of language agents. The first paper introduces a "causal state binding" framework to assess if agents' actions are truly driven by relevant internal s…
-
AI agents lack grounding for reputation mechanisms, study finds
A new research paper argues that current reputation mechanisms, effective for humans, are fundamentally unsuited for autonomous language model agents. The paper highlights that these agents are "dissociative," meaning t…
-
Paper: LLM agents' dissociative nature undermines reputation-based trust
A new paper argues that current reputation mechanisms, effective for humans, are fundamentally unsuited for autonomous language model agents. The authors contend that the dissociative nature of these agents, characteriz…
-
Language models show in-group bias in simulated agent interactions
Researchers have demonstrated that instruction-tuned language models exhibit in-group bias when interacting in simulated environments. In a multi-agent simulation, agents with visible group labels showed preferential tr…
-
New frameworks boost LLM agents' negotiation skills with emotional strategies
Researchers have developed two new frameworks, EmoDistill and EvoEmo, to enhance the negotiation capabilities of language model agents by incorporating emotional strategies. EmoDistill focuses on distilling emotional ne…
-
PACE framework enables small language models to self-evolve
Researchers have developed PACE, a novel framework for enabling small language model (SLM) agents to self-evolve without requiring model weight updates or access to frontier models. This two-timescale approach separates…