PulseAugur
EN
LIVE 21:11:30
ENTITY \tau2-bench

\tau2-bench

PulseAugur coverage of \tau2-bench — every cluster mentioning \tau2-bench across labs, papers, and developer communities, ranked by signal.

Show in brief
Total · 30d
5
11 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
3
7 over 90d
TIER MIX · 90D
TOPICS
SENTIMENT · 30D

2 day(s) with sentiment data

RECENT · PAGE 1/1 · 11 TOTAL
  1. TOOL · CL_340224 ·

    New AC3 method combats AI conversation context pollution

    Researchers have developed Agentic Conversation Context Curation (AC3), a novel method to combat context pollution in multi-turn AI conversations. This training-free approach uses a separate analyzer to consolidate the …

  2. TOOL · CL_324864 ·

    New FireFly pipeline generates verified tool-call data from real APIs

    Researchers have developed FireFly, a novel pipeline for generating verified tool-call data from real-world APIs. This method synthesizes tasks backward from observed outcomes, ensuring label correctness by construction…

  3. TOOL · CL_324395 ·

    New metric RSD enhances LLM agent consistency and performance

    Researchers have introduced Recursive Semantic Divergence (RSD), a new metric designed to evaluate and improve the consistency of Large Language Model (LLM) agents. LLM agents often exhibit unpredictable behavior, leadi…

  4. TOOL · CL_318476 ·

    Unsloth adds Recursive Flint, MOSS-Image, NVIDIA Nemotron Bolt E4B models

    Unsloth has released version 0.1.910-beta, introducing support for several new models including Recursive's Flint and MOSS-Image, as well as NVIDIA's Nemotron Bolt E4B. This update enables users to run these models loca…

  5. TOOL · CL_294019 ·

    Run Qwen 3.5 AI agents locally with OpenClaw and Ollama

    A guide demonstrates how to locally run the Qwen 3.5 language model with the OpenClaw agent framework using Ollama. This setup allows for persistent, 24/7 AI agent workflows on personal hardware without incurring cloud …

  6. TOOL · CL_244855 ·

    Paper questions LLM-agent leaderboard validity

    A new paper questions the validity of LLM-agent leaderboards, arguing that direct comparisons of ranked agents can be misleading. The authors highlight that differences in task mixtures, data sources, release details, a…

  7. SIGNIFICANT · CL_255602 ·

    TaichuAI releases ZDTaichu5.0-9B multimodal foundation model

    TaichuAI has released ZDTaichu5.0-9B, a multimodal foundation model designed for visual understanding, spatial reasoning, and agentic tasks. This model integrates a Qwen3.5-9B language backbone with a C-RADIOv4-H vision…

  8. RESEARCH · CL_218887 ·

    Apple's PROOF-Gen method enhances AI model distillation from failures

    Apple Machine Learning Research has introduced PROOF-Gen, a novel method for improving the distillation of tool-calling capabilities into deployable AI models. This technique addresses the limitations of traditional gen…

  9. TOOL · CL_205900 ·

    New research evaluates open-source AI model routers across benchmarks

    A new paper published on arXiv evaluates four open-source model routers, which are systems that delegate model selection in agentic frameworks. The study introduces a common measurement protocol to compare these routers…

  10. TOOL · CL_196307 ·

    llama.cpp fixes muse-glimmer tool call parsing issue

    The llama.cpp project has released an update (b10380) to fix an issue where the muse-glimmer model incorrectly handled tool calls. Previously, the model would sometimes absorb tool call markup into its response content,…

  11. RESEARCH · CL_105067 ·

    New method improves multi-turn AI agents with preference learning · 2 sources tracked

    Researchers have developed a novel method called ToolGraph, which enhances multi-turn tool-using agents by integrating schema-derived topology and transition weights from successful rollouts. This approach improves the …