PulseAugur
EN
LIVE 10:05:50
ENTITY $\tau$-bench

$\tau$-bench

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

Show in brief
Total · 30d
13
29 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
9
23 over 90d
TIER MIX · 90D
TOPICS
RELATIONSHIPS
SENTIMENT · 30D

5 day(s) with sentiment data

RECENT · PAGE 1/2 · 32 TOTAL
  1. SIGNIFICANT · CL_352998 ·

    Tether AI Research releases BotPsy-0.8B agent model for on-device use

    Tether AI Research has released BotPsy-0.8B, an open-source, on-device agent model designed for function calling. Built upon Qwen3.5-0.8B, BotPsy-0.8B demonstrates significant improvements in tool use and agentic benchm…

  2. TOOL · CL_330426 ·

    Concordat library enforces AI agent conversation rules via session types

    A new Python library called Concordat has been developed to enforce rules for AI agents during conversations, moving beyond traditional prompt engineering. Concordat uses session types to define protocols as state machi…

  3. RESEARCH · CL_336225 ·

    New Agentic World Modeling enables LLM agents to scale without environment replicas · 2 sources tracked

    Researchers have developed Agentic World Modeling (AWM), a new method to improve large language model agents by enabling test-time scaling without needing to replicate entire environments. AWM reformulates next-observat…

  4. TOOL · CL_327118 ·

    New GEPA-Curator framework enhances AI agent learning by filtering task failures

    Researchers have introduced GEPA-Curator, a framework designed to improve the learning process for self-improving AI agents. This system addresses the issue of noisy or unreliable learning signals that can arise from ag…

  5. RESEARCH · CL_327138 ·

    New methods enhance efficiency in agent reinforcement learning · 2 sources tracked

    Researchers have developed two novel methods to improve the efficiency of reinforcement learning (RL) for language agents. EnvSched optimizes the scheduling of task instances and environments by learning from rollout hi…

  6. RESEARCH · CL_324449 ·

    New research tackles LLM agent security and protocol adherence

    Two new research papers address the security and reliability of Large Language Model (LLM) agents. The first, "Concordat," introduces a Python library that enforces protocol adherence for agents, preventing them from ta…

  7. RESEARCH · CL_319546 ·

    AI Agents Gain Autonomy with Agentic RAG for Enterprise Knowledge

    Enterprise AI agents are evolving beyond simple chatbots, with new architectures like Agentic RAG enabling them to autonomously search and synthesize information from diverse internal systems. This approach moves beyond…

  8. TOOL · CL_312430 ·

    New research questions effectiveness of AI context compaction for later queries

    A new research paper evaluates context compaction methods for language model agents, focusing on how well compacted context serves subsequent questions. The study found that while methods like GPT-6 Luna, guided by the …

  9. TOOL · CL_312287 ·

    New TURTLE benchmark evolves AI tool-use tasks for better scalability

    Researchers have developed TURTLE, an Unsupervised Environment Design approach to create self-tuning benchmarks for long-horizon tool use in AI assistants. This method uses a proposer, solver, and feedback generator LLM…

  10. TOOL · CL_301791 ·

    Researcher's conformal risk control gate limits LLM agent write errors on tau-bench

    A researcher developed a conformal risk control gate to manage LLM agent write actions, aiming to prevent incorrect modifications to data. The gate, evaluated on the tau-bench retail dataset using the glm-5.3-flash mode…

  11. TOOL · CL_300184 ·

    AI agent benchmarks flawed: simulated users break rules in 24% of successes

    A new benchmark called UserProxyBench, developed by Ashish Jain and Armaan Sandhu, reveals a significant flaw in current agent evaluation methods. The benchmark found that in nearly a quarter of successful runs, the sim…

  12. RESEARCH · CL_325254 ·

    New simulator StressSim exposes AI agent weaknesses · 2 sources tracked

    Researchers have developed StressSim, a novel framework for evaluating multi-turn AI agents by simulating adversarial users. This system aims to stress-test agents by creating challenging, yet valid, user interactions t…

  13. TOOL · CL_289251 ·

    New SELF framework enhances language agent training with environmental feedback

    Researchers have introduced a new framework called SELF (SELF-distilLation with environmental Feedback modeling) to improve language agents trained in interactive environments where direct rewards are unavailable. This …

  14. TOOL · CL_280118 ·

    New LiteTrajEval framework streamlines AI agent evaluation

    Researchers have developed LiteTrajEval, a new framework designed to make the evaluation of AI agent trajectories more efficient and cost-effective. This system uses pre-defined rule profiles to process agent outputs, i…

  15. TOOL · CL_275219 ·

    New ESCROW framework ensures AI agents maintain policy and auditability

    Researchers have developed ESCROW, a new framework designed for the continual maintenance of AI agents operating within enterprise workflows. This system focuses on ensuring agents adhere to policies, maintain auditabil…

  16. TOOL · CL_257642 ·

    LLM Gateways Emerge as Essential for AI Apps Amidst Provider Complexity

    The landscape of AI application development is shifting towards the necessity of LLM gateways, which act as central proxies to manage interactions with multiple AI model providers. These gateways offer benefits such as …

  17. TOOL · CL_235403 ·

    AI model evaluations can be misleading due to interface censoring

    A new research paper highlights a phenomenon called "Interface-Induced Trajectory Censoring" where the interface used to evaluate AI models can incorrectly report zero tool usage, even when the model is generating valid…

  18. TOOL · CL_229329 ·

    New SASST method improves AI agent stress testing rigor

    Researchers have developed a new method called Selection-Aware Semantic Stress Testing (SASST) to more rigorously evaluate interactive AI agents. SASST addresses a common issue where benchmarks select workflows and then…

  19. TOOL · CL_228739 ·

    New method tracks LLM agent reasoning trajectories for improved performance

    Researchers have developed a novel method to track the internal reasoning trajectories of Large Language Model (LLM) agents, particularly under resource constraints. By analyzing geometric signals like temporal curvatur…

  20. TOOL · CL_211954 ·

    New AI technique improves tool failure recovery for agents

    Researchers have developed a new technique called Outcome Monitors to improve the reliability of AI agents when interacting with external tools. These monitors detect violations of expected outcomes from tool calls, eve…