Search posts, papers, and topics
ActObs is a supervised fine-tuning method that trains agents to predict both actions and environmental observations from trajectories. This joint supervision improves subsequent reinforcement learning performance, leading to better exploration and task completion on benchmarks like Terminal-Bench 2.0 and aider-polyglot.
The talk argues that prompt engineering is a dead‑end and proposes building large evaluation/optimization pipelines (pass^k testing, adversarial scenario generation, automated prompt optimization) to make LLM agents reliable. It describes a workflow: generate tests, run them with/without a new “skill”, feed results to a genetic optimizer that mutates prompts, validate on hold‑out tests, and itera…
XConf (eXperiential Confidence) is a novel method for estimating language model confidence by leveraging the model's accumulated experience from past graded episodes. It significantly outperforms existing methods like self-consistency in discrimination and calibration, at a fraction of the computational cost, across various tasks.
GraphSkillEvo encodes LLM agent skills as directed graphs and applies population‑based evolution (mutation, crossover) to optimise them. Across five benchmarks it beats the SkillOpt baseline, gaining up to 4% accuracy on GPT‑5.4‑nano.
The paper introduces Gavel, a method that extracts a frozen LLM's internal routing signal via two trained linear maps, eliminating the need to embed skill descriptions in the prompt. Experiments on Qwen3‑32B show up to 13.4‑point improvements on task benchmarks and higher skill‑use accuracy compared to larger retrieval‑based systems.
Apple proposes a memory architecture for agentic LLMs that selectively persists reusable context (specs, schemas, configs, constraints) across sessions and users. Shared workspaces with role‑based access and a zero‑token data‑refresh mechanism cut token usage by 97×, reduce task time by 14×, and raise task‑completion rates to 96% versus 71%‑79% for baselines.
Stack Overflow for Agents, an API‑first knowledge exchange for AI agents, now ships a ChatGPT plugin and introduces Playbooks, a new post type for procedural workflows. The platform adds trust scores, reputation‑linked validation, and finer‑grained publishing controls to improve reliability and safety of shared agent knowledge.
Omnigent is a unified agent definition layer that lets you write an LLM‑agent once and run it on any harness (Claude Code, Codex, raw API). By plugging Nimble’s specialized web‑search API into the Omnigent web_search builtin, you get consistent, deeper, and cheaper web results – benchmark accuracy jumps from 46 % to 71 % and search cost halves. All model calls go through Databricks Foundation Mod…
The article explains that LLMs don’t have persistent personal memory; all “memory” is supplied by the surrounding application via the context window, summaries, or external storage. It outlines the distinction between trained weights, working‑memory (token context), and persistent application memory, shows how to construct API calls to preserve conversation state, and discusses the cost and laten…
Rails Hyperdrive is a development‑only Rails engine that mounts a Model Context Protocol (MCP) server and lets any gem ship agent knowledge (skills, agents, commands, guidelines) as markdown files. The engine adds no knowledge itself; companion gems provide the context‑aware artifacts that agents can query at runtime, avoiding token‑heavy guessing and stale schema reads. Installation is a single…
Deezer built QAradar, a workflow‑driven Slack‑bot that lets developers discover and run the exact automated tests covering their feature. By pre‑generating a clean test catalog and keeping the LLM in a fixed four‑step workflow, they avoided the complexity and cost of a full‑blown agent while dramatically reducing knowledge silos and friction for QA and developers.
Vercel’s `skills` CLI (v1.7.0) now lets you install agent skills directly from Notion pages or shared Notion skill packs. Use `npx skills add notion` to browse packs, or `npx skills add <PAGE_URL>` for a single skill. Authentication is handled via the `ntn` CLI, which requires a Notion personal access token. Permissions follow Notion’s page sharing model, so only users with view access can instal…
